Updated on 2022/03/30

写真a

 
Deguchi Daisuke
 
Organization
Graduate School of Informatics Department of Intelligent Systems 1 Associate professor
Graduate School
Graduate School of Information Science
Graduate School of Informatics
Undergraduate School
School of Informatics Department of Computer Science
Title
Associate professor

Degree 1

  1. Doctor of Information Science ( 2006.3   Nagoya University ) 

Research Interests 5

  1. Computer Graphics

  2. Medical Image Processing

  3. Computer Vision

  4. Pattern Recognition

  5. Image Processing

Research Areas 2

  1. Others / Others  / Medical Systems

  2. Others / Others  / Perception Information Processing/Intelligent Robotics

Current Research Project and SDGs 2

  1. 過去と現在の対比による環境適応型画像認識に関する研究

  2. 実世界センシングにより得られる環境依存情報を活用した環境適応型画像認識に関する研究

Research History 6

  1. Department of Intelligent Systems, Graduate School of Informatics, Nagoya University   Associate professor

    2020.1

      More details

    Country:Japan

  2. Information Strategy Office, Information and Communications, Nagoya University   Associate professor

    2012.2 - 2019.12

      More details

    Country:Japan

  3. Graduate School of Information Science, Nagoya University   Assistant Professor

    2008.10 - 2012.1

      More details

    Country:Japan

  4. 名古屋大学大学院工学研究科   研究員

    2006.11 - 2008.9

      More details

    Country:Japan

  5. 名古屋大学大学院情報科学研究科   研究員

    2006.4 - 2006.10

      More details

    Country:Japan

  6. Japan Society for Promotion of Science

    2004.4 - 2006.3

      More details

    Country:Japan

▼display all

Education 3

  1. Nagoya University   Graduate School, Division of Information Science   Department of Media Science

    2003.4 - 2006.3

      More details

    Country: Japan

  2. Nagoya University   Graduate School, Division of Engineering   Department of Information Engineering

    2001.4 - 2003.3

      More details

    Country: Japan

  3. Nagoya University   Faculty of Engineering   Department of Information Engineering

    1997.4 - 2001.3

      More details

    Country: Japan

Professional Memberships 3

  1. IEEE

  2. 電子情報通信学会

  3. 情報処理学会

Committee Memberships 19

  1. 情報処理学会 コンピュータービジョンとイメージメディア研究会   幹事  

    2020.4   

  2. 画像の認識・理解シンポジウム MIRU2021   実行委員  

    2020 - 2021   

      More details

    Committee type:Academic society

  3. 情報処理学会 コンピュータービジョンとイメージメディア研究会   運営委員  

    2019.4 - 2020.3   

      More details

    Committee type:Academic society

  4. 電子情報通信学会情報・和文論文誌A編集委員会   編集委員  

    2018.6 - 2022.5   

  5. 電子情報通信学会情報・英文論文誌A編集委員会   編集委員  

    2018.6 - 2022.5   

  6. Ja Sakaiコミュニティ   副代表  

    2014.4 - 2020.3   

  7. 電子情報通信学会情報・英文論文誌D編集委員会   英文論文誌編集委員  

    2013.5 - 2017.5   

  8. 画像センシング技術研究会 SSII2013   実行委員 出版部会 副部会長  

    2012.9 - 2013.8   

  9. HCGシンポジウム2012   運営委員  

    2012.7 - 2012.12   

  10. Ja Sakai コミュニティ   幹事  

    2012.4 - 2014.3   

  11. ICPR 2012 Contest on Kitchen Scene Context based Gesture Recognition   Organizer  

    2011.10 - 2012.12   

  12. HCGシンポジウム2011   運営委員  

    2011.7 - 2011.12   

  13. 第15回パターン認識・マルチメディア理解アルゴリズムコンテスト   実行委員  

    2011.4 - 2011.9   

  14. HCGシンポジウム2010   運営委員  

    2010.7 - 2010.12   

  15. 第14回パターン認識・マルチメディア理解アルゴリズムコンテスト   幹事  

    2009.12 - 2011.3   

  16. 電子情報通信学会情報・システムソサイエティ ソサイエティ論文誌編集委員会   常任査読委員  

    2009.5   

  17. 電子情報通信学会パターン認識・メディア理解研究会 研究専門委員   専門委員  

    2009.4 - 2015.5   

  18. 電子情報通信学会ヒューマンコミュニケーショングループ 料理メディア研究会 研究専門委員会   幹事補佐  

    2009.4 - 2013.5   

  19. 第13回パターン認識・マルチメディア理解アルゴリズムコンテスト   実行委員  

    2009.4 - 2009.9   

▼display all

Awards 15

  1. MVE賞

    2020.3   電子情報通信学会 マルチメディア・仮想環境基礎研究専門委員会   心像性に基づく画像キャプショニングの検討

    梅村 和紀, カストナー マークアウレル, 井手 一郎, 川西 康友, 平山 高嗣, 道満 恵介, 出口 大輔, 村瀬 洋

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  2. 研究奨励賞

    2020.3   動的画像処理実利用化ワークショップDIA2020   超低解像度FIR画像内での人物位置と動作の違いに着目した骨格推定法の検討

    岩田 紗希, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 相澤 知禎

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  3. 優秀ポスター賞

    2019.12   一般社団法人大学ICT推進協議会   手書きレポートとLMSの連携を実現する名大版紙レポシステムの全学運用

    出口 大輔, 清谷 竣也, 大平 茂輝, 戸田 智基

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  4. 優秀論文賞

    2018.11   一般社団法人大学ICT推進協議会   名古屋大学におけるサーバ型紙レポート・LMS 連携システムの開発

    清谷 竣也, 伊藤 瑠哉, 岡本 康佑, 谷川 右京, 大平 茂輝, 出口 大輔, 戸田 智基

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  5. MVE賞

    2016.10   電子情報通信学会 マルチメディア・仮想環境基礎研究専門委員会   SNS 投稿写真の画像内容に基づく地域間の類似度算出に関する検討

    滝本 広樹, 川西 康友, 井手 一郎, 平山 高嗣, 道満 恵介, 出口 大輔, 村瀬 洋

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  6. Excellent Paper Award

    2016.2   Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV)   Human Wearable Attribute Recognition using Decomposition of Thermal Infrared Images

    Brahmastro Kresnaraman, Yasutomo Kawanishi, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

     More details

    Award type:Award from international society, conference, symposium, etc.  Country:Japan

  7. MVE賞

    2012.9   電子情報通信学会 マルチメディア・仮想環境基礎研究専門委員会  

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  8. 研究奨励賞

    2012.3   動的画像処理実利用化ワークショップDIA2012  

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

    2件受賞

  9. MVE賞

    2011.10   電子情報通信学会 マルチメディア・仮想環境基礎研究専門委員会  

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  10. 電子情報通信学会 学術奨励賞

    2010.3   電子情報通信学会  

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  11. 日本医用画像工学会論文賞

    2009.8   日本医用画像工学会  

     More details

    Award type:Honored in official journal of a scientific society, scientific journal  Country:Japan

  12. 日本コンピュータ外科学会講演論文賞

    2007.4   日本コンピュータ外科学会  

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  13. 日本医用画像工学会奨励賞

    2006.7   日本医用画像工学会  

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  14. 第14回コンピュータ支援画像診断学会大会・大会賞

    2004.12   コンピュータ支援画像診断学会  

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  15. CARS2004 Poster Award 1st Prize

    2004.6   18th International Congress on Computer Assisted Radiology and Surgery  

     More details

    Award type:Award from international society, conference, symposium, etc. 

▼display all

 

Papers 223

  1. Masked face recognition with mask transfer and self-attention under the COVID-19 pandemic Reviewed

    Zhang Meng, Rujie Liu, Daisuke Deguchi, Hiroshi Murase

    IEEE Access   Vol. 10   page: 20527 - 20538   2022.2

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Face masks bring a new challenge to face recognition systems especially against the background of the COVID-19 pandemic. In this paper, a method mitigating the negative effects of mask defects on face recognition is proposed. Firstly, a low-cost, accurate method of masked face synthesis, i.e. mask transfer, is proposed for data augmentation. Secondly, an attention-aware masked face recognition (AMaskNet) is proposed to improve the performance of masked face recognition, which includes two modules: a feature extractor and a contribution estimator. Therein, the contribution estimator is employed to learn the contribution of the feature elements, thus achieving refined feature representation by simple matrix multiplications. Meanwhile, the end-to-end training strategy is utilized to optimize the entire model. Finally, a mask-aware similarity matching strategy(MS) is taken to improve the performance in the inference stage. The experiments show that the proposed method consistently outperforms on three masked face recognition datasets: RMFRD [1], COX [2] and Public-IvS [3]. Meanwhile, qualitative analysis experiments using CAM [4] indicate that the contribution learned by AMaskNet is more conducive to masked face recognition.

    DOI: 10.1109/ACCESS.2022.3150345

  2. Active Learning for Human Pose Estimation based on Temporal Pose Continuity Reviewed

    Taro Mori, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Tetsuo Inoshita

    Proceedings of International Workshop on Advanced Image Technology (IWAIT) 2022     2022.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  3. Soft-boundary label relaxation with class placement constraints for semantic segmentation of the railway environment Reviewed

    Yuki Furitsu, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Hiroki Mukojima, Nozomi Nagamine

    Pattern Recognition Letters   Vol. 150   page: 258 - 264   2021.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1016/j.patrec.2021.07.014

  4. Pointedness of an Image: Measuring How Pointy an Image is Perceived Reviewed

    Chihaya Matsuhira, Marc A. Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    Proceedings of HCII 2021   Vol. 37   page: 137 - 144   2021.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    For computers to understand human perception, metrics that can capture human perception well are important. However, there are few metrics that characterize the visual perception of humans towards images. Therefore, in this paper, we propose a novel concept and a metric of pointedness of an image, which describes how pointy an image is perceived. The algorithm is inspired by the Features from Accelerated Segment Test (FAST) algorithm for corner detection which looks on the number of continuous neighboring darker pixels surrounding each pixel. We assume that this number would be proportional to the perceived pointedness in the region around the pixel. We evaluated our method towards how well it could capture the human perception of images. To compare the method with similar metrics that describe shapes, we prepared silhouette images of both artificial shapes and natural objects. The results showed that the proposed method gave nearly equivalent perceptual performance to other metrics and also worked in a larger variety of images.

    DOI: https://doi.org/10.1007/978-3-030-78635-9_20

  5. Best next-viewpoint recommendation by selecting minimum pose ambiguity for category-level object pose estimation Reviewed

    Nik Mohd Zarifie Hashim, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Journal of the Japan Society for Precision Engineering   Vol. 87 ( 5 ) page: 440 - 446   2021.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.2493/jjspe.87.440

  6. Odometry estimation from sparse LiDAR point cloud constrained by image feature correspondence Reviewed

    Masayuki Shimizu, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Journal of the Japan Society for Precision Engineering   Vol. 87 ( 5 ) page: 447 - 454   2021.5

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.2493/jjspe.87.447

  7. Proposal of a Light-Field Descriptor Considering Light-Ray Direction Reviewed

    Masayuki Shimizu, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Journal of the Japan Society for Precision Engineering   Vol. 87 ( 2 ) page: 197 - 205   2021.2

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.2493/jjspe.87.197

  8. ColAtt-Net: In Reducing the Ambiguity of Pedestrian Orientations on Attribute-Aware Semantic Segmentation Task Reviewed

    Mahmud Dwi Sulistiyo, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Takatsugu Hirayama, Hiroshi Murase

    IEEJ Transactions on Electrical and Electronic Engineering   Vol. 16 ( 2 ) page: 295 - 306   2021.2

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Semantic segmentation has become one of the trending topics in the world of computer vision and deep learning. Recently, due to an increasing demand to solve a semantic segmentation task simultaneously with attribute recognition of objects, a new task named attribute-aware semantic segmentation has been introduced. Since the task requires to handle pixel-wise object class estimation with its attributes such as a pedestrian’s body orientation, previous works had difficulties to handle ambiguous attributes such as body orientations in object-level, especially when segmenting the pedestrians with their attributes correctly. This paper proposes the ColAtt-Net that is an attribute-aware semantic segmentation model augmented by a column-wise mask branch to predict the pedestrians’ orientations in the horizontal perspective of the input image. We firmly assume that the pedestrians captured by a car-mounted camera are distributed horizontally so that for each column of the input image, the pedestrian pixels can be labeled with one orientation uniformly. In the proposed method, we split the output of the base semantic segmentation model into two branches; one branch for segmenting the object categories, while the other one, as the novel column-wise attribute branch, is to map the recognition of pedestrian’s orientations that are distributed horizontally. This method successfully enhances the performance of attribute-aware semantic segmentation by reducing the ambiguity on segmenting the pedestrian’s orientation. Improvements on the pedestrian orientation segmentation are confidently shown by the proposed method in the experimental results, both in quantitative and qualitative views. This paper also discusses how the improved performance becomes an advantage in the autonomous driving system.

    DOI: https://doi.org/10.1002/tee.23296

  9. LFIR2Pose: Pose Estimation from an Extremely Low-Resolution FIR Image Sequence Reviewed

    Saki Iwata, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa

    Proceedings of the 25th International Conference on Pattern Recognition     2021.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In this paper, we propose a method for human pose estimation from a Low-resolution Far-InfraRed (LFIR) image sequence captured by a 16 × 16 FIR sensor array. Human body estimation from such a single LFIR image is a hard task. For training the estimation model, annotation of the human pose to the images is also a difficult task for human. Thus, we propose the LFIR2Pose model which accepts a sequence of LFIR images and outputs the human pose of the last frame, and also propose an automatic annotation system for the model training. Additionally, considering that the scale of human body motion is largely different among body parts, we also propose a loss function focusing on the difference. Through an experiment, we evaluated the human pose estimation accuracy using an original data set, and confirmed that human pose can be estimated accurately from an LFIR image sequence.

  10. OMEga-GAN: Object Manifold Embedding GAN for Image Generation by Disentangling Parameters into Pose and Shape Manifolds Reviewed

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of the 25th International Conference on Pattern Recognition     page: 7945 - 7952   2021.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In this paper, we propose Object Manifold Embedding GAN (Ω-GAN) to generate images of variously shaped and arbitrarily posed objects from a noise variable sampled from a distribution defined over the pose and the shape manifolds in a vector space. We introduce Parametric Manifold Sampling to sample noise variables from a distribution over the pose manifold to conditionally generate object images in arbitrary poses by tuning the pose parameter. We also introduce Object Identity Loss for clearly disentangling the pose and shape parameters, which allows us to maintain the shape of the object instance when only the pose parameter is changed. Through evaluation, we confirmed that the proposed Ω-GAN could generate variously shaped object images in arbitrary poses by changing the pose and shape parameters independently. We also introduce an application of the proposed method for object pose estimation, through which we confirmed that the object poses in the generated images are accurate.

  11. Median-Shape Representation Learning for Category-Level Object Pose Estimation in Cluttered Environments Reviewed

    Hiroki Tatemichi, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Ayako Amma, Hiroshi Murase

    Proceedings of the 25th International Conference on Pattern Recognition     page: 4473 - 4480   2021.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In this paper, we propose an occlusion-robust pose
    estimation method of an unknown object instance in an
    object category from a depth image. In a cluttered
    environment, objects are often occluded mutually. For
    estimating the pose of an object in such a situation, a
    method that de-occludes the unobservable area of the object
    would be effective. However, there are two difficulties;
    occlusion causes offset between the actual object center
    and the center of its observable area, and different
    instances in a category may have different shapes. To cope
    with these difficulties, we propose a two-stage
    Encoder-Decoder model to extract features with objects
    whose centers are aligned to the image center. In the
    model, we also propose the Median-shape Reconstructor as
    the second stage to absorb shape variations in a category.
    By evaluating the method with both a large-scale virtual
    dataset and a real dataset, we confirmed the proposed
    method achieves good performance on pose estimation of an
    occluded object from a depth image.

  12. Human Skeleton Estimation Method Focusing on the Difference of Human Position and Action from an Extremely Low-Resolution FIR Image Sequence Reviewed

    Saki Iwata, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa

    Journal of the Japan Society for Precision Engineering   Vol. 87 ( 1 ) page: 99 - 106   2021.1

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  13. Imageability Estimation using Visual and Language Features Reviewed

    Chihaya Matsuhira, Marc A. Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    Proceedings of the 2020 International Conference on Multimedia Retrieval     page: 306–310   2020.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Imageability is a concept from Psycholinguistics quantizing the human perception of words. However, existing datasets are created through subjective experiments and are thus very small. Therefore, methods to automatically estimate the imageability can be helpful. For an accurate automatic imageability estimation, we extend the idea of a psychological hypothesis called Dual-Coding Theory, that discusses the connection of our perception towards visual information
    and language information, and also focus on the relationship between the pronunciation of a word and its imageability. In this research, we propose a method to estimate imageability of words
    using both visual and language features extracted from corresponding data. For the estimation, we use visual features extracted from low- and high-level image features, and language features extracted from textual features and phonetic features of words. Evaluations how that our proposed method can estimate imageability more accurately than comparative methods, implying the contribution of each feature to the imageability.

    DOI: 10.1145/3372278.3390731

  14. Modeling Eye-Gaze Behavior of Electric Wheelchair Drivers via Inverse Reinforcement Learning Reviewed

    Yamato Maekawa, Naoki Akai, Takatsugu Hirayama, Luis Yoichi Morales, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Proceedings of 2020 IEEE International Conference on Intelligent Transportation Systems     page: 158 - 164   2020.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    It is intuitively obvious that eye-gaze behaviors of experienced drivers are different from those of novice drivers. However, it is not easy to understand the difference in their behavior quantitatively. In this work, we present an explainable eye-gaze behavior modeling method for electric wheelchair drivers based on Inverse Reinforcement Learning (IRL). We first create feature maps that represent risk factors during driving. These feature maps are able to represent not only to what but also from where drivers pay attention. IRL uses the feature maps to learn the reward representing the eye-gaze behaviors and allows us to see important features via the automatic acquisition of the reward. Through analysis of the learned model, we show quantitative evidence that eye-gaze behaviors of experienced drivers are better-balanced by paying attention to multiple risks.

    DOI: 10.1109/ITSC45102.2020.9294255

  15. Estimating the imageability of words by mining visual characteristics from crawled image data Reviewed

    Marc Aurel Kastner, Ichiro Ide, Frank Nack, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Hiroshi Murase

    Multimedia Tools and Applications   Vol. 79 ( 25 ) page: 18167 - 18199   2020.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1007/s11042-019-08571-4

  16. Performance Boost of Attribute-aware Semantic Segmentation via Data Augmentation for Driver Assistance Reviewed

    Mahmud Dwi Sulistiyo, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Takatsugu Hirayama, Hiroshi Murase

        page: 293 - 298   2020.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper is an extension of our work in developing an attribute-aware semantic segmentation method which focuses on pedestrian understanding in a traffic scene. Recently, the trending topic of semantic segmentation has been expanded to be able to collaborate with the object’s attributes recognition task; Here, it refers to recognizing a pedestrian’s body orientation. The attribute-aware semantic segmentation can be more beneficial for driver assistance compared to the conventional semantic segmentation because it can provide a more informative output to the system. In this paper, we conduct a study of the data augmentation usage as an effort to enhance the performance of the attribute-aware semantic segmentation task. The experiments show that the proposed method in augmenting the training data is able to improve the model’s performance. We also demonstrate some of qualitative results and discuss the benefits to a driver assistance system.

    DOI: 10.1109/ICoICT49345.2020.9166219

  17. Estimation of the Number of Vehicles by Regression Based on Parts Detection Reviewed

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

      Vol. 32 ( 3 ) page: 705 - 712   2020.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  18. Simultaneous Image Matching for Person Re-identification via the Stable Marriage Algorithm Reviewed

    Nik Mohd Zarifie Hashim, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEEJ Transactions ON Electrical AND Electronic Engineering   Vol. 15 ( 6 ) page: 909 - 917   2020.4

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

  19. SOANets: Encoder-Decoder based Skeleton Orientation Alignment Network for White Cane User Recognition from 2D Human Skeleton Sequence Reviewed

    Naoki Nishida, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Jun Piao

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2020   Vol. 5   page: 435 - 443   2020.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In recent years, various facilities have been deployed to support visually impaired people. However, accidents caused by visual disabilities still occur. In this paper, to support the visually impaired people in public areas, we aim to identify whether a pedestrian image sequence obtained by a surveillance camera indicates the presence of a white cane user by analyzing the temporal transition of a human skeleton represented as 2D coordinates. Our previously proposed method aligns the orientation of the human skeletons to various orientations and identifies a white cane user from the corresponding sequences, relying on multiple classifiers related to each orientation. The method employs an exemplar-based approach to perform the alignment. However, it heavily depends on the number of exemplars and consumes excessive memory. In this paper, we propose a method to align 2D human skeleton representation sequence to various orientations using the proposed Skeleton Orientation Alignment Networks (SOANets) based on an encoder-decoder model. Using SOANets, we can obtain 2D skeleton representation sequences aligned to various orientations, extract richer skeleton features, and recognize white cane users accurately. We conducted an experiment to confirm that the
    proposed method improves the recognition rate by 16%, compared to the method that does not use the skeleton
    orientation alignment.

  20. Development and Evaluation of "KamiRepo" Web Service with Return of Handwritten Assignments via LMS Reviewed

    Shigeki Ohira, Shunya Seiya, Ryuya Ito, Kosuke Okamoto, Ukyo Tanikawa, Daisuke Deguchi, Tomoki Toda

      Vol. 6 ( 1 ) page: 52 - 68   2020.2

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  21. Occlusion-Aware Skeleton Trajectory Representation for Abnormal Behavior Detection Reviewed

    Onur Temuroglu, Yasutomo Kawanishi, Daisuke Deguchi, Takatsugu Hirayama, Ichiro Ide, Hiroshi Murase, Mayuu Iwasaki, Atsushi Tsukada

        2020.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Surveillance cameras are expected to play a large role in the development of ITS technologies. They can be used to detect abnormally behaving individuals which can then be reported to drivers nearby. There are multiple works that tackle the problem of abnormal behavior detection. However, most of these works make use of appearance features which have redundant information and are susceptible to noise. While there are also works that make use of pose skeleton representation, they do not consider well how to handle cases with occlusions, which can occur due to the simple reason of pedestrian orientation preventing some joints from appearing in the frame clearly. In this paper, we propose a skeleton trajectory representation that enables handling of occlusions. We also propose a framework for pedestrian abnormal behavior detection that uses the proposed representation and detect relatively hard-to-notice anomalies such as drunk walking. The experiments we conducted show that our method outperforms other representation methods.

  22. Browsing Visual Sentiment Datasets Using Psycholinguistic Groundings

    Marc Aurel Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Hiroshi Murase

    Lecture Note in Computer Science   Vol. 11962   page: 697 - 702   2020.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Recent multimedia applications commonly use text and imagery from Social Media for tasks related to sentiment research. As such, there are various image datasets for sentiment research for popular classification tasks. However, there has been little research regarding the relationship between the sentiment of images and its annotations from a multi-modal standpoint. In this demonstration, we built a tool to visualize psycholinguistic groundings for a sentiment dataset. For each image, individual psycholinguistic ratings are computed from the image's metadata. A sentiment-psycholinguistic spatial embedding is computed to show a clustering of images across different classes close to human perception. Our interactive browsing tool can visualize the data in various ways, highlighting different psycholinguistic groundings with heatmaps.

    DOI: 10.3758/s13428-018-1099-3

  23. More-Natural Mimetic Words Generation for Fine-Grained Gait Description Reviewed

    Hirotaka Kato, Takatsugu Hirayama, Ichiro Ide, Keisuke Doman, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

    Lecture Note in Computer Science   Vol. 11962   page: 214 - 225   2020.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    A mimetic word is used to verbally express the manner of a phenomenon intuitively. The Japanese language is known to have a greater number of mimetic words in its vocabulary than most other languages. Especially, since human gaits are one of the most commonly represented behavior by mimetic words in the language, we consider that it should be suitable for labels of fine-grained gait recognition. In addition, Japanese mimetic words have a more decomposable structure than these in other languages such as English. So it is said that they have sound-symbolism and their phonemes are strongly related to the impressions of various phenomena. Thanks to this, native Japanese speakers can express their impressions on them briefly and intuitively using various mimetic words. Our previous work proposed a framework to convert the body-parts movements to an arbitrary mimetic word by a regression model. The framework introduced a phonetic space" based on sound-symbolism, and it enabled fine-grained gait description using the generated mimetic words consisting of an arbitrary combination of phonemes. However, this method did not consider the "naturalness" of the description. Thus, in this paper, we propose an improved mimetic word generation module considering its naturalness, and update the description framework. Here, we define the co-occurrence frequency of phonemes composing a mimetic word as the naturalness. To investigate the co-occurrence frequency, we collected many mimetic words through a subjective experiment. As a result of evaluation experiments, we confirmed that the proposed module could describe gaits with more natural mimetic words while maintaining the description accuracy."

    DOI: 10.1007/978-3-030-37734-2_18

  24. Attribute-Aware Loss Function for Accurate Semantic Segmentation Considering the Pedestrian Orientations Reviewed

    Mahmud Dwi Sulistiyo, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Takatsugu Hirayama, Jiang-Yu Zheng, Hiroshi Murase

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences   Vol. E103-A ( 1 ) page: 231 - 242   2020.1

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Numerous applications such as autonomous driving, satellite imagery sensing, and biomedical imaging use computer vision as an important tool for perception tasks. For Intelligent Transportation Systems (ITS), it is required to precisely recognize and locate scenes in sensor data. Semantic segmentation is one of computer vision methods intended to perform such tasks. However, the existing semantic segmentation tasks label each pixel with a single object’s class. Recognizing object attributes, e.g., pedestrian orientation, will be more informative and help for a better scene understanding. Thus, we propose a method to perform semantic segmentation with pedestrian attribute recognition simultaneously. We introduce an attribute-aware loss function that can be applied to an arbitrary base model. Furthermore, a re-annotation to the existing Cityscapes dataset enriches the ground-truth labels by annotating the attributes of pedestrian orientation. We implement the proposed method and compare the experimental results with others. The attribute-aware semantic segmentation shows the ability to outperform baseline methods both in the traditional object segmentation task and the expanded attribute detection task.

    DOI: 10.1587/transfun.2019TSP0001

  25. Analysis of Effective Flicker Light Patterns to Improve the Pedestrian Detectability from a Driver for an Intelligent Headlight System Reviewed

    Takashi Maeda, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Journal of the Japan Society for Precision Engineering   Vol. 85 ( 12 ) page: 1157 - 1162   2019.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: https://doi.org/10.2493/jjspe.85.1157

  26. Cyclist Recognition via Size-Adaptable PointNet Reviewed

    Taiki Yamamoto, Fumito Shinmura, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Kazuki Kato, Hiroshi Murase

    Journal of the Japan Society for Precision Engineering   Vol. 85 ( 12 ) page: 1117 - 1126   2019.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.2493/jjspe.85.1117

  27. Scene-Adaptive Driving Area Prediction based on Automatic Label Acquisition from Driving Information Reviewed

    Takuya Migishima, Haruya Kyutoku, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Proceedings of the 5th IAPR Asian Conference on Pattern Recognition (ACPR2019)     2019.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  28. Semantic Segmentation of Railway Images Considering Temporal Continuity Reviewed

    Yuki Furitsu, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Hiroki Mukoujima, Nozomi Nagamine

    Proceedings of the 5th IAPR Asian Conference on Pattern Recognition (ACPR2019)     2019.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  29. An Analysis of How Driver Experience Affects Eye-Gaze Behavior for Robotic Wheelchair Operation Reviewed

    Yamato Maekawa, Naoki Akai, Takatsugu Hirayama, Luis Yoichi Morales, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Proceedings of 2019 IEEE International Conference on Computer Vision (ICCV) Workshops     page: 4443 - 4451   2019.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Drivers obtain information on surrounding environment using their eyesights. Experienced eye-gaze behavior is needed when driving at places where multiple risks exist to prepare for and avoid them. In this work, we analyze the change in eye-gaze behavior in such situations while a driver gains experience on the operation of a robotic wheelchair. Accurate distance information in the traffic environment is important to analyze the eye-gaze behavior. However, almost all previous works analyze eye-gaze behavior in a 2D environment, so they could not obtain accurate distance information. For this reason, we analyze eye-gaze behavior in 3D space. Concretely, we developed a novel eye-gaze behavior analysis platform based on a robotic wheelchair and estimated the driver's attention in 3D space. We try to analyze the eye-gaze behavior considering a useful field-of-view in 3D space based on the distance information instead of only the fixation point to investigate the objects that a driver implicitly pays attention to and from where s/he focuses on them. Results show that novice drivers pay attention to a single risk at a time. In contrast, they pay more attention to multiple risks simultaneously as they gain experience. Additionally, we discuss what features are effective to model the eye-gaze behavior based on the results.

    DOI: 10.1109/ICCVW.2019.00545

  30. Exemplar-based Pseudo-Viewpoint Rotation for White-Cane User Recognition from a 2D Human Pose Sequence Reviewed

    Naoki Nishida, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Jun Piao

        2019.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  31. Similar Seasonal-Geo-Region Mining based on Visual Concepts in Social Media Photos Reviewed

    Yasutomo Kawanishi, Ichiro Ide, Chen Lu, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    Proceedings of the 5th IEEE Conference on Multimedia BigData     page: 86 - 93   2019.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  32. Estimation of the attractiveness of food photography based on image features Reviewed

    Kazuma Takahashi, Tatsumi Hattori, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Trans. on Information and Systems   Vol. E102-D ( 8 ) page: 1590 - 1593   2019.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1587/transinf.2018EDL8219

  33. Hand Orientation Estimation in Probability Density Form

    Kazuaki Kondo, Daisuke Deguchi, Atsushi Shimada

        2019.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  34. Estimating the Imageability of a sentence for image caption evaluation

    Kazuki Umemura, Marc Aurel Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

        2019.4

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  35. Estimating the visual variety of concepts by referring to Web popularity Reviewed

    Marc Aurel Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Hiroshi Murase

    Multimedia Tools and Applications   Vol. 78 ( 7 ) page: 9463 - 9488   2019.4

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Increasingly sophisticated methods for data processing demand knowledge on the semantic relationship between language and vision. New fields of research like Explainable AI demand to step away from black-boxed approaches and understanding how the underlying semantics of data sets and AI models work. Advancements in Psycholinguistics suggest, that there is a relationship from language perception to how language production and sentence creation work. In this paper, a method to measure the visual variety of concepts is proposed to quantify the semantic gap between vision and language. For this, an image corpus is recomposed using ImageNet and Web data. Web-based metrics for measuring the popularity of sub-concepts are used as a weighting to ensure that the image composition in a dataset is as natural as possible. Using clustering methods, a score describing the visual variety of each concept is determined. A crowd-sourced survey is conducted to create ground-truth values applicable for this research. The evaluations show that the recomposed image corpus largely improves the measured variety compared to previous datasets. The results are promising and give additional knowledge about the relationship of language and vision.

    DOI: 10.1007/s11042-018-6528-x

  36. Person Re-Detection from an In-Vehicle Camera Video Referring to Observations from Other Vehicles

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    The Journal of the Institute of Image Electronics Engineers of Japan   Vol. 48 ( 2 ) page: 273 - 277   2019.4

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  37. Summarization of multiple news videos considering the consistency of audio-visual contents Reviewed

    Ye Zhang, Ryunosuke Tanishige, Ichiro Ide, Keisuke Doman, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

    International Journal of Semantic Computing   Vol. 13 ( 1 ) page: 135 - 155   2019.3

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1142/S1793351X19500016

  38. Hard Negative Mining from in-Vehicle Camera Images based on Multiple Observations of Background Patterns Reviewed

    Masashi Hontani, Haruya Kyutoku, David Robert Wong, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2019   Vol. 5   page: 435 - 442   2019.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In recent years, the demand for highly accurate pedestrian detectors has increased due to the development of advanced driving support systems.
    For the training of an accurate pedestrian detector, it is important to collect a large number of training samples.
    To support this, this paper proposes a ``hard negative'' mining method to automatically extract background images which tend to be erroneously detected as pedestrians.
    Negative samples are selected based on the assumption that frequent patterns observed multiple times in the same location are most likely parts of the background scene.
    As a result of an evaluation using in-vehicle camera images captured along the same route, we confirmed that the proposed method can automatically collect false positive samples accurately.
    We also confirmed that a highly accurate detector can be constructed using the additional negative samples.

  39. Next Viewpoint Recommendation by Pose Ambiguity Minimization for Accurate Object Pose Estimation Reviewed

    Nik Mohd Zarifie Hashim, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Ayako Amma, Norimasa Kobori

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2019   Vol. 5   page: 60 - 67   2019.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    3D object pose estimation by using a depth sensor is one of the important tasks in activities by robots. To reduce the pose ambiguity of an estimated object pose, several methods for multiple viewpoint pose estimation have been proposed. However, these methods need to select the viewpoints carefully to obtain better results. If the pose of the target object is ambiguous from the current observation, we could not decide where we should move the sensor to set as the next viewpoint. In this paper, we propose a best next viewpoint recommendation method by minimizing the pose ambiguity of the object by making use of the current pose estimation result as a latent variable. We evaluated viewpoints recommended by the proposed method and confirmed that it helps us to gain better pose estimation results than several comparative methods on a synthetic dataset.

  40. Pedestrian Intensive Scanning for Active-scan LIDAR Reviewed

    Taiki Yamamoto, Fumito Shinmura, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2019   Vol. 5   page: 313 - 320   2019.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In recent years, LIDAR is playing an important role as a sensor for understanding environments of a vehicle’s surroundings. Active-scan LIDAR is being actively developed as a LIDAR that can control the laser irradiation direction arbitrary and rapidly. In comparison with conventional uniform-scan LIDAR (e.g. Velodyne HDL-64e), Active-scan LIDAR enables us to densely scan even distant pedestrians. In addition, if appropriately controlled, this sensor has the potential to reduce unnecessary laser irradiations towards non-target objects. Although there are some preliminary studies on pedestrian scanning strategy for Active-scan LIDARs, in the best of our knowledge, an efficient method has not been realized yet. Therefore, this paper proposes a novel pedestrian scanning method based on orientation aware pedestrian likelihood estimation using the orientation-wise pedestrian’s shape models with local distribution of measured points. To evaluate the effectiveness of the proposed method, we conducted experiments by simulating Active-scan LIDAR using point-clouds from the KITTI dataset. Experimental results showed that the proposed method outperforms conventional methods.

  41. Voting-based Hand-Waving Gesture Spotting from a Low-Resolution Far-Infrared Image Sequence Reviewed

    Yasutomo Kawanishi, Chisato Toriyama, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

    Proceedings of 2018 IEEE International Conference on Visual Communications and Image Processing (VCIP2018)     2018.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    We propose a temporal spotting method of a hand gesture from a low-resolution far-infrared image sequence captured by a far-infrared sensor array. The sensor array captures the spatial distribution of far-infrared intensity as a thermal image by detecting far-infrared waves emitted from heat sources. It is difficult to spot a hand gesture from a sequence of thermal images captured by the sensor due to its low-resolution, heavy noise, and varying duration of the gesture. Therefore, we introduce a voting-based approach to spot the gesture with template matching-based gesture recognition. We confirm the effectiveness of the proposed temporal spotting method in several settings.

    DOI: 10.1109/VCIP.2018.8698650

  42. Gaze-inspired Learning for Estimating the Attractiveness of a Food Photo Reviewed

    Akinori Sato, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Proceedings of 20th IEEE Int. Symposium on Multimedia (ISM2018)     page: 36 - 43   2018.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    The number of food photos posted to the Web has been increasing. Most of the users prefer to post delicious-looking food photos. They, however, do not always look delicious. A previous work proposed a method for estimating the attractiveness of food photos, that is, the degree of how much a food photo looks delicious, as an assistive technology for taking a delicious-looking food photo. This method extracted image features from the entire food photo to evaluate the impression. In our work, we conduct a preference experiment where subjects are asked to compare a pair of food photos and measure their gaze. The proposed method extracts image features from local regions selected based on the gaze information and estimates the attractiveness of a food photo by learning regression parameters. Experimental results showed the effectiveness of extracting image features from outside the gaze regions rather than inside them.

    DOI: 10.1109/ISM.2018.00015

  43. Action Recognition Using a Far-Infrared Sensor Array by Convolutional RNN Reviewed

    Takayuki Kawashima, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

    Journal of the Japan Society for Precision Engineering   Vol. 84 ( 12 ) page: 1025 - 1032   2018.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  44. Pedestrian Detection from a Sparse LIDAR Point-Cloud Reviewed

    Yoshiki Tatebe, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Journal of the Japan Society for Precision Engineering   Vol. 84 ( 12 ) page: 1017 - 1024   2018.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.2493/jjspe.84.1017

  45. Localizing the Gaze Target of a Crowd of People Reviewed

    Yuki Kodama, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hidehisa Nagano, Kunio Kashino

        2018.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    What target is focused on by many people?
    Analysis of the target is a crucial task, especially in a cinema, a stadium, and so on.
    However, it is very difficult to estimate the gaze of each person in a crowd accurately and simultaneously with existing image-based eye tracking methods, since the image resolution of each person becomes low when we capture the whole crowd with a distant camera.
    Therefore, we introduce a new approach for localizing the gaze target focused on by a crowd of people.
    The proposed framework aggregates the individually estimated results of each person's gaze.
    It enables us to localize the target being focused on by them even though each person's gaze localization from a low-resolution image is inaccurate.
    We analyze the effects of an aggregation method on the localization accuracy using images capturing a crowd of people in a tennis stadium under the assumption that all of the people are focusing on the same target, and also investigate the effect of the number of people involved in the aggregation on the localization accuracy.
    As a result, the proposed method showed the ability to improve the localization accuracy as it is applied to a larger crowd of people.

  46. Analyzing Headlight Flicker Patterns for Improving the Pedestrian Detectability from a Driver Reviewed

    Takashi Maeda, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of 2018 IEEE 21st International Conference on Intelligent Transportation Systems (ITSC2018)     page: 3113 - 3118   2018.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In this paper, we analyze headlight flicker patterns which improve the pedestrian detectability from a driver. Recently, headlights are becoming capable of selectively projecting light on a pedestrian in addition to the normal forward projection. However, it is still not clear how the light should be
    projected to effectively improve the visibility of the pedestrian. We actually analyze nine flicker patterns by controlling duty ratios and durations of lighting time, and conduct experiments in field and laboratory settings. As a result, we reveal that a specific fundamental frequency is effective for improving the pedestrian detectability from a driver. We also conclude that the difference between the two settings are not significant.

  47. Estimating the Scene-wise Reliability of LiDAR Pedestrian Detectors Reviewed

    Haruya Kyutoku, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Kazuki Kato, Hiroshi Murase

    Proceedings of 2018 IEEE 21th International Conference on Intelligent Transportation Systems (ITSC2018)     page: 3511 - 3516   2018.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Nowadays, development of driving support systems and autonomous driving systems have become active.
    Pedestrian detection from in-vehicle sensors is one of the most important technologies for these systems.
    However, outputs of pedestrian detectors can not be fully trusted in real environments.
    Therefore, we propose an estimation system of pedestrian detector's reliabilities for a given scene.
    This paper proposes a scene-wise reliability calculation method for LiDAR-based detectors, and a construction method for their estimators.
    Here, the problem is how we can define the reliability.
    The proposed method defines the reliability considering oversights as the strictest threshold without oversights.
    Meanwhile, it defines the reliability considering false detections as the loosest threshold without false detections.
    Experimental results showed that the proposed method could properly represent the reliability of a given scene, and estimate their reliability.

  48. Attribute-aware Semantic Segmentation of Road Scenes for Understanding Pedestrian Orientations Reviewed

    Mahmud Dwi Sulistiyo, Yasutomo Kawanishi, Daisuke Deguchi, Takatsugu Hirayama, Ichiro Ide, Jiang-Yu Zheng, Hiroshi Murase

    Proceedings of 2018 IEEE 21th International Conference on Intelligent Transportation Systems (ITSC2018)     page: 2698 - 2703   2018.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Semantic segmentation is an interesting task for many deep learning researchers for scene understanding. However, recognizing details about objects’ attributes can be more informative and also helpful for a better scene understanding in intelligent vehicle use cases. This paper introduces a method for simultaneous semantic segmentation and pedestrian attributes recognition. A modified dataset built on top of the Cityscapes dataset is created by adding attribute classes corresponding to pedestrian orientation attributes. The proposed method extends the SegNet model and is trained by using both the original and the attribute-enriched datasets. Based on an experiment, the proposed attribute-aware semantic segmentation approach shows the ability to slightly improve the performance on the Cityscapes dataset, which is capable of expanding its classes in this case through additional data training.

  49. Estimation of Driver's Insight for Safe Passing based on Pedestrian Attributes Reviewed

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Takatsugu Hirayama, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    Proceedings of 2018 IEEE 21th International Conference on Intelligent Transportation Systems (ITSC2018)     page: 1041 - 1046   2018.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In order to reduce traffic accidents between a vehicle and a pedestrian, recognition of a pedestrian who has a possibility of collision with a vehicle should be helpful. However, since a pedestrian may suddenly change his/her direction and cross the road, it is difficult to predict his/her behavior directly. Here, we focus on the fact that experienced drivers usually pass by a pedestrian while preparing to step on the brake at any moment when they feel danger. If driver assistant systems can estimate such experienced driver’s decisions, they could early detect the pedestrian in danger of collision. Therefore, we classify the driver’s decisions into three types by referring to the accelerator operation of drivers, and propose a method to estimate the type of the driver’s decision. The drivers are considered to decide their actions focusing on various behaviors and states of a pedestrian, namely pedestrian’s attributes. Since the driver’s decisions change along the timeline, the use of a temporal context is considered to be effective. Thus, in this paper, we propose an estimation method using a recurrent neural network architecture with the pedestrian’s attributes as input. We constructed a dataset collected by experienced drivers in control of the vehicle and evaluated the performance, and then confirmed the effectiveness of the use of pedestrian’s attributes.

  50. Image Synthesis of Eye Areas for Perceptually Establishing Eye-contacts between Video Conference Participants Reviewed

    Takuya Inoue, Takatsugu Hirayama, Tomokazu Takahashi, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Takayuki Kurozumi, Kunio Kashino

    IEEJ Transactions on Electronics, Information and Systems   Vol. 138 ( 11 ) page: 1399 - 1409   2018.11

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: https://doi.org/10.1541/ieejeiss.138.1399

  51. Epipolar geometry-based ego-localization using an in-vehicle monocular camera

    Haruya Kyutoku, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

        2018.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Nowadays, development of driving support systems and autonomous driving systems have become active.
    Vehicle ego-localization using in-vehicle sensors is one of the most important technologies for these systems.
    Accordingly, various attempts to localize own vehicle from in-vehicle sensors have been made.
    In general, the estimation accuracy of the traveling direction is lower than in the lateral direction.
    Therefore, we propose a highly accurate method for ego-localization of the traveling direction based on epipolar geometry using an in-vehicle monocular camera.
    The proposed method makes correspondences between in-vehicle camera images and database images with location information, and calculates the location using locations annotated to the corresponding database images.
    However, there are many gaps due to the difference of speed and trajectory of vehicles even if the images are obtained along the same road.
    To overcome this problem, the distance between the input image and the database image is calculated by the distance metric based on the epipolar geometry and the local feature method.
    An experiment was conducted using actual images with correct locations, and we confirmed the effectiveness of the proposed method from its results.

  52. Vehicle counting via car parts detection from an in-vehicle camera image

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

        2018.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper proposes a method to count vehicles from an in-vehicle camera image by regression based on car parts detection. In the case of an in-vehicle camera image, since vehicles are frequently occluded by other vehicles in traffic congestion, it is difficult to accurately count vehicles. Therefore, we propose a method to count vehicles by regression based on the number of visible car parts. For this, we make an estimator by learning the relation between the number of visible car parts and that of vehicles by Support Vector Regression. We evaluated our method using in-vehicle camera images recorded in an actual environment, where the proposed method performed better than counting detected vehicles.

  53. People Tracking across Non-overlapping Camera Views via Camera Dropout and Trajectory Ensemble Reviewed

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Information and Systems   Vol. J101-D ( 8 ) page: 1079 - 1088   2018.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  54. Visualization of Real World Activity on Group Work

    Daisuke Deguchi, Kazuaki Kondo, Atsushi Shimada

    Proceedings of 20th International Conference on HCI International 2018 (HCII2018)   Vol. LNCS 10902   page: 23 - 37   2018.7

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

    Group work is widely introduced and practiced as a method to achieve the learning goal efficiently by collaborating group members. However, since most types of group works are carried out in the real environment, it is very difficult to perform formative assessment and real time evaluation without students' feedbacks. Therefore, there is a strong demand to develop a method that supports evaluation of group work. To support evaluation of group work, this paper proposes a method to visualize the real world activity during group work by using first person view cameras and wearable sensors. Here, the proposed method visualizes three scores: (1) individual attention, (2) hand visibility, (3) individual activity. To evaluate the performance and analyze the relationships between scores, we conducted experiments of Marshmallow challenge" that is a collaborative work to construct a tower using marshmallow and spaghetti within a limit of time. Through the experiments, we confirmed that the proposed method has potential to become a evaluation tool for visualizing the activity of the group work."

    DOI: 10.1007/978-3-319-91131-1_2

  55. Describing Gaits by Onomatopoeias with Sound Symbolism Reviewed

    Hirotaka Kato, Takatsugu Hirayama, Keisuke Doman, Ichiro Ide, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

    Transactions of the Japanese Society for Artificial Intelligence   Vol. 33 ( 4 ) page: 1 - 9   2018.7

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  56. Pedestrian Detectability Estimation Considering Visual Adaptation to Drastic Illumination Change Reviewed

    Yuki Imaeda, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Information and Systems   Vol. E101-D ( 5 ) page: 1457 - 1462   2018.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1587/transinf.2017EDL8215

  57. Development of 'KamiRepo' System with Automatic Student Identification to Handle Handwritten Assignments on LMS Reviewed

    Shunya Seiya, Ryuya Ito, Kosuke Okamoto, Ukyo Tanikawa, Shigeki Ohira, Daisuke Deguchi, Tomoki Toda

    Proceedings of 2018 the IEEE Global Engineering Education Conference (EDUCON2018)     page: 841 - 848   2018.4

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    A Learning Management System (LMS) has become a fundamental tool for higher education, and a framework to leverage digital education data in the LMS has attracted attention. On the other hand, there is strong demand to deal with various education data provided not only from electronic media but also non-electronic media, such as a handwritten assignment. To solve this problem, this paper describes the development of 'KamiRepo' system to make it possible to automatically upload handwritten assignments to the LMS. In this system, optical character recognition (OCR) is performed to identify scanned handwritten assignments of individual students and read their scores. Then, their scanned files automatically separated from the entire file of the scanned handwritten assignments are returned to the individual students through LMS together with their corresponding scores. Compared with a conventional system using the dedicated multifunction printer, our developed system is capable of 1) using general-purpose scanners, 2) using a user interface on Web browser, and 3) achieving accurate student identification. We have launched this system in our university in April 2017 and have evaluated its effectiveness. The experimental results using real data collected for 6 months showed that our system achieved 99.7% of success rate in the automatic upload process.

  58. A Preliminary Study on Optimizing Person Re-identification using Stable Marriage Algorithm Reviewed

    Nik Mohd Zarifie Hashim, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

        page: 6   2018.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Person re-identification gains an increasing interest
    in the surveillance image processing field due to its’ importance
    for security. Most approaches to solve the person re-identification
    problem match persons one-by-one. However, redundant match-
    ing where one of the person is selected for the matching pair
    several times often occurs. It also degrades the overall image
    matching performance. To overcome the issue, in this paper,
    we propose a method which solves the person re-identification
    problem for multiple persons simultaneously. Instead of one-
    by-one matching, we consider person re-identification as an
    instance of the Stable Marriage Problem (SMP). The result of an
    experiment showed that the proposed method outperforms some
    of the existing state-of-the-art methods applied to the VIPeR
    dataset.

  59. Efficient Pedestrian Scanning by Active Scan LIDAR Reviewed

    Taiki Yamamoto, Fumito Shinmura, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Proceedings of International Workshop on Advanced Image Technology (IWAIT) 2018     page: 1 - 4   2018.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  60. Pedestrian Detection from Sparse Point-Cloud using 3DCNN Reviewed

    Yoshiki Tatebe, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Utsushi Sakai

    Proceedings of International Workshop on Advanced Image Technology (IWAIT) 2018     page: 1 - 4   2018.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  61. Automatic selection of Web contents towards automatic authoring of a video biography Reviewed

    Ichiro Ide, Yasutomo Kawanishi, Kyoka Kunishiro, Frank Nack, Daisuke Deguchi, Hiroshi Murase

    Proceedings of 19th IEEE Int. Symposium on Multimedia (ISM2017)     page: 304 - 307   2017.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ISM.2017.54

  62. Summarization of news videos considering the consistency of auditory and visual contents Reviewed

    Ichiro Ide, Ye Zhang, Ryunosuke Tanishige, Keisuke Doman, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

    Proceedings of 19th IEEE Int. Symposium on Multimedia (ISM2017)     page: 193 - 199   2017.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ISM.2017.33

  63. Toward Describing Human Gaits by Onomatopoeias Reviewed

    Hirotaka Kato, Takatsugu Hirayama, Yasutomo Kawanishi, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV2017) Workshops     page: 1573 - 1580   2017.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  64. Driver's Decision Analysis in Terms of Pedestrian Attributes -A Case Study in Passing by a Pedestrian-

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    Proceedings of Workshop on Human Factors in Intelligent Vehicles     page: 32 - 36   2017.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In this paper, we report a case study on driver's decision in terms of pedestrian attributes. Among various traffic situations, the situation that a vehicle passes by a pedestrian is one of the major situations. To build a safety driving system that supports a non-experienced driver in such a situation, we analyzed how experienced drivers decide to handle the vehicle in such a situation. Since pedestrian’s behavior can be considered as a key factor for the decision, and also the behavior is different depending on their attributes," such as walking or stopping, noticing the vehicle or not, using a smartphone, etc., we analyzed what pedestrian's attributes affect the driver's decisions. For the analysis, we first built a large-scale dataset of driving data. Using the dataset, we clarified what attributes are dominant for the driver's decision."

  65. Detection of Similar Geo-Regions based on Visual Concepts in Social Photos Reviewed

    Hiroki Takimoto, Magali Philippe, Yasutomo Kawanishi, Ichiro Ide, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

        2017.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Travel destination recommendation is useful to support travel.Considering the recommendation of regions within the destination area to visit, it could be difficult for the users to explicitly indicate their preference.Therefore, we considered that it would be more intuitive to recommend regions in the destination area that are similar to a region already well-known to the user.Thus, in this paper, we propose a method for the detection of similar geo-regions based on Visual Concepts in social photos.We report experimental results and analyses by applying the proposed method to the YFCC100M dataset.

  66. Proposal of an encoded marker for working robots: An encoded marker easy to detect in various positions and under blur Reviewed

    Norimasa Kobori, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Electronics and Communications in Japan   Vol. 100 ( 10 ) page: 59 - 69   2017.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1002/ecj.11987

  67. Action Recognition from Extremely Low-Resolution Thermal Image Sequence Reviewed

    Takayuki Kawashima, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

    Proceedings of the 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS2017)     2017.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper proposes a Deep Learning-based action recognition method from an extremely low-resolution thermal image sequence. The method recognizes daily actions by humans (e.g. walking, sitting down, standing up, etc.) and abnormal actions (e.g. falling down) without privacy concerns. While privacy concerns can be ignored, it is difficult to compute feature points and to obtain a clear edge of the human body from an extremely low-resolution thermal image. To address these problems, this paper proposes a Deep Learning-based action recognition method that combines convolution layers and an LSTM layer for learning spatio-temporal representation, whose inputs are the thermal images and their frame differences cropped by the gravity center of human regions. The effectiveness of the proposed method was confirmed through experiments.

    DOI: 10.1109/AVSS.2017.8078497

  68. Estimation of the attractiveness of food photography focusing on main ingredients Reviewed

    Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Proceedings of 9th Workshop on Cooking and Eating Activities (CEA2017) in conjunction with IJCAI2017     page: 1 - 6   2017.8

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1145/3106668.3106670

  69. Regression of Feature Scale Tracklets for Decimeter Visual Localization Reviewed

    David Robert Wong, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Image and Vision Computing   Vol. 68   page: 53 - 63   2017.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Localization along a route is an everyday necessity for in-vehicle navigation systems, and a vital task for automated driving technologies. Visual ego-localization promises reliable accuracy even in challenging urban environments where Global Positioning Systems (GPSs) can fail. Using cameras for localization against a pre-constructed database requires either the creation of a dense three-dimensional feature point map and pose estimation of a query camera relative to this map, or image matching along a database route to determine the capture position of the query camera based on the most similar database image. While the latter method is potentially less computationally intensive and can provide a more compact database, localization accuracy is limited by the discrete positioning information at database frame capture locations. In this paper we propose an image matching method that makes use of image features which are pre-matched during database construction, allowing linear regression coefficients for the relationship between capture position and feature scale to be calculated. The capture position of matched query features can then be estimated to sub-database spacing resolution. By incorporating the visual localization system into a Bayes estimator, we demonstrate an average monocular vision localization accuracy of 0.33 m in tests on actual vehicle image streams.

    DOI: 10.1016/j.imavis.2017.07.004

  70. Headgear Recognition by Decomposing Human Images in the Thermal Infrared Spectrum Reviewed

    Brahmastro Kresnaraman, Yasutomo Kawanishi, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    Proceedings of the 15th International Conference on Quality in Research (QiR2017)     page: 164 - 168   2017.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Surveillance systems play a critical role in security and surveillance. A surveillance system with cameras that work in the visible spectrum is sufficient for most cases. However, problems may arise during the night, or in areas with less than ideal illumination conditions. Cameras with thermal infrared technology can be a better option in these situations since they do not rely on illumination to observe the environment. Furthermore, in our daily lives, it is common for humans to wear headgears such as glasses, masks, and hats. In surveillance, such headgears can be a hindrance to the identification of a person, and hence pose a certain degree of risk. This is not ideal in areas where the identity of a person is important, for example, in a bank. Therefore, in this paper we propose a headgear recognition method using an innovative decomposition approach on thermal infrared images. The decomposition method is based on Robust Principal Component Analysis, a modification of the popular Principal Component Analysis. The proposed method performs decomposition on a human image and isolates headgears in the image for recognition purposes. Experiments were conducted to evaluate the capability of the proposed method. The results show a positive outcome when compared with other methods.

    DOI: 10.1109/QIR.2017.8168475

  71. Trajectory Ensemble: Multiple Persons Consensus Tracking across Non-overlapping Multiple Cameras over Randomly Dropped Camera Networks Reviewed

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

        page: 1471 - 1477   2017.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Multiple person tracking over a camera network is usually performed by matching person images between adjacent cameras. It easily fails by a temporal appearance change of the persons caused by environmental illumination and observation orientation of a camera. To solve this problem, matching person images across not only adjacent cameras but also cameras multiple hops away in the camera network is effective, but such relaxation of spatiotemporal cues also cause tracking failure due to the increase of matching candidates. To avoid the failure, we introduce Random Camera Drop" to generate different camera networks which relax the spatio-temporal cues partially and randomly. We then, integrate tracking results over the networks to a consensus tracking result by a novel concept "Trajectory Ensemble", an extension of unsupervised ensemble learning for the multiple person tracking over a camera network problem. We evaluated the framework on several virtual datasets generated from a public dataset, "Shinpuhkan 2014 dataset" and confirmed that the proposed method achieves the highest tracking results among several comparative methods."

  72. Monocular Localization within Sparse Voxel Maps Reviewed

    David Robert Wong, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of the 2017 IEEE Intelligent Vehicles Symposium (IV2017)     page: 493 - 498   2017.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    We introduce a method that uses a single camera to localize a vehicle within a pre-constructed map consisting of a voxel occupancy grid and road-line marker positions. Sophisticated mapping hardware is capable of creating high accuracy 3D maps of road environments, but localizing a vehicle within such maps is one of the challenges at the forefront of automated driving. A solution which is robust to dynamic environments, while using only inexpensive sensors, is a difficult problem. In addition, maps that enable precise localization consume a lot of data which is impractical for the expansive environments encountered in real-world road networks. We show how using the area of edge regions shared between rendered views of a compact voxel map and in-vehicle camera images can be coupled with non-linear optimization methods to determine the camera position and pose.

  73. Proposal of a spectral random dots marker using local feature for posture estimation Reviewed

    Norimasa Kobori, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of IEEE Virtual Reality 2017     page: 223 - 224   2017.3

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/VR.2017.7892257

  74. Deep Manifold Embedding for 3D Object Pose Estimation Reviewed

    Hiroshi Ninomiya, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Norimasa Kobori, Yusuke Nakano

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2017   Vol. 5   page: 173 - 178   2017.3

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.5220/0006101201730178

  75. Human Wearable Attribute Recognition Using Probability-Map-Based Decomposition of Thermal Infrared Images Reviewed

    Brahmastro Kresnaraman, Yasutomo Kawanishi, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences   Vol. E100-A ( 3 ) page: 854 - 864   2017.3

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    This paper addresses the attribute recognition problem, a
    field of research that is dominated by studies in the visible spectrum. Only
    a few works are available in the thermal spectrum, which is fundamentally
    different from the visible one. This research performs recognition specif-
    ically on wearable attributes, such as glasses and masks. Usually these
    attributes are relatively small in size when compared with the human body,
    on top of a large intra-class variation of the human body itself, therefore
    recognizing them is not an easy task. Our method utilizes a decomposi-
    tion framework based on Robust Principal Component Analysis (RPCA) to
    extract the attribute information for recognition. However, because it is dif-
    ficult to separate the body and the attributes without any prior knowledge,
    noise is also extracted along with attributes, hampering the recognition
    capability. We made use of prior knowledge; namely the location where
    the attribute is likely to be present. The knowledge is referred to as the
    Probability Map, incorporated as a weight in the decomposition by RPCA.
    Using the Probability Map, we achieve an attribute-wise decomposition.
    The results show a significant improvement with this approach compared
    to the baseline, and the proposed method achieved the highest performance
    in average with a 0:83 F-score.

  76. Can We Detect Pedestrians using Low-resolution LIDAR? Reviewed

    Yoshiki Tatebe, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Utsushi Sakai

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2017   Vol. 5   page: 157 - 164   2017.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.5220/0006100901570164

  77. Wheelchair-user Detection Combined with Parts-based Tracking Reviewed

    Ukyo Tanikawa, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Ryo Kawai

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2017   Vol. 5   page: 165 - 172   2017.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.5220/0006101101650172

  78. Can a Driver Assistance System Determine if a Driver is Perceiving a Pedestrian? Reviewed

    Yuki Imaeda, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2017   Vol. 4   page: 611 - 616   2017.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.5220/0006229306110616

  79. Single Camera Vehicle Localization Using Feature Scale Tracklets Reviewed

    David Robert Wong, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences   Vol. E100-A ( 2 ) page: 702 - 713   2017.2

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Advances in intelligent vehicle systems have led to modern automobiles being able to aid drivers with tasks such as lane following and automatic braking. Such automated driving tasks increasingly require reliable ego-localization. Although there is a large number of sensors that can be employed for this purpose, the use of a single camera still remains one of the most appealing, but also one of the most challenging. GPS localization in urban environments may not be reliable enough for automated driving systems, and various combinations of range sensors and inertial navigation systems are often too complex and expensive for a consumer setup. Therefore accurate localization with a single camera is a desirable goal.
    In this paper we propose a method for vehicle localization using images captured from a single vehicle-mounted camera and a pre-constructed database.
    Image feature points are extracted, but the calculation of camera poses is not required---instead we make use of the feature points' scale.
    For image feature-based localization methods, matching of many features against candidate database images is time consuming, and database sizes can become large. Therefore, here we propose a method that constructs a database with pre-matched features of known good scale stability. This limits the number of unused and incorrectly matched features, and allows recording of the database scales into ``tracklets''. These ``Feature scale tracklets'' are used for fast image match voting based on scale comparison with corresponding query image features. This process reduces the number of image-to-image matching iterations that need to be performed while improving the localization stability. We also present an analysis of the system performance using a dataset with high accuracy ground truth. We demonstrate robust vehicle positioning even in challenging lane change and real traffic situations.

    DOI: 10.1587/transfun.E100.A.702

  80. A Classification Method of Cooking Operations Based on Temporal Patterns of Gaze Transitions and Blinks Reviewed

    Hiroya Inoue, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Transactions on Information and Systems   Vol. J100-A ( 1 ) page: 12 - 23   2017.1

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  81. Misclassification Tolerable Learning for Robust Pedestrian Orientation Classification Reviewed

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

        page: 481 - 486   2016.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In this paper, we propose a multiclass classifier training method which reduces fatal" misclassifications by cost-relaxation of "tolerable" misclassifications in one-against-all classifiers training, named misclassification tolerable learning. In a binary classifier in the one-against-all classifiers, we introduce a new class group "conceptually similar classes," whose class labels are similar to the positive class. In the case of pedestrian orientation classification, the conceptually similar classes are defined as neighboring orientations to the positive orientation. We consider the misclassification of the conceptually similar classes to the positive class as tolerable misclassification. By relaxing the cost of the tolerable misclassifications, our proposed classification method reduces fatal misclassifications of non-similar classes. We evaluated the cost-relaxation effectiveness on several public datasets and confirmed that the proposed method outperforms the normal SVM on all of the datasets in the soft criterion by achieving 78.63% recognition rate on PDC Dataset."

  82. Pedestrian Detection by Scene Adaptation Based on False Positive Mining Reviewed

    Yuki Suzuki, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Journal of the Japan Society for Precision Engineering   Vol. 82 ( 12 ) page: 1085 - 1091   2016.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.2493/jjspe.82.1085

  83. Recognition of Texting-While-Walking by Joint Features based on Arm and Head Poses Reviewed

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

        2016.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Pedestrians texting-while-walking" increase the risk of traffic accidents, since they are often not paying attention to their surrounding environments and fails to notice approaching vehicles. Thus, the recognition of texting-while-walking from an in-vehicle camera should be helpful for safety driving assistance. In this paper, we propose a method to recognize a pedestrian texting-while-walking from in-vehicle camera images. The proposed approach focuses on the characteristic relationship between the arm and the head poses observed during a texting-while-walking behavior. In this paper, Pose-Dependent Joint HOG feature is proposed as a novel feature, which uses parts locations as prior knowledge and describes the cooccurrence of the arm and the head poses. To show the effectiveness of the proposed method, we constructed a dataset and evaluated it."

  84. Moving camera background-subtraction for obstacle detection on railway tracks Reviewed

    Hiroki Mukoujima, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Masato Ukai, Nozomi Nagamine, Ryuta Nakasone

    Proceedings of 2016 IEEE International Conference on Image Processing (ICIP2016)     page: 3967 - 3971   2016.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper proposes a method for detecting obstacles using train frontal view videos.
    In recent years, obstacles detection using in-vehicle camera is actively developed for satisfying demands from various applications.
    In the field of obstacle detection, most methods employ machine learning approach, and they can detect only trained obstacles, such as pedestrian, bicycle, etc.
    Therefore, they cannot detect untrained general obstacles.
    To overcome this problem, this paper propose a background subtraction method using moving camera.
    The proposed method first computes frame-by-frame correspondences between the present and the database train frontal view image sequences, and detects obstacles by applying image subtraction to corresponding frames.
    To confirm the effectiveness of the proposed method, experiments were conducted by using several image sequences captured at the experimental railroad track.
    The experimental result showed that the proposed method could detect various obstacles accurately and effectively.

    DOI: 10.1109/ICIP.2016.7533104

  85. Subjective Sensing of Real World Activity on Group Study Reviewed

    Daisuke Deguchi, Kazuaki Kondo, Atsushi Shimada

    Proceedings of the 18th International Conference on Collaboration Technologies (CollabTech2016)     page: 5 - 8   2016.9

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

    Collaborative learning is efficient teaching/learning method, and it is widely introduced and practiced in various situations. However, it has a difficulty to perform formative assessment and real time evaluation without students' feedbacks. Therefore, demand for technologies to support formative assessment in collaborative learning is increasing. To tackle this problem, we have started the research project for automatic sensing and visualization of real world activities in collaborative learning. In this paper, we will report details about preliminary group work experiments and its results with visualization tool.

  86. Proposal of an Encoded Marker for Working Robots Reviewed

    Norimasa Kobori, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEEJ Transactions on Electronics, Information and Systems   Vol. 136 ( 9 ) page: 1367 - 1375   2016.9

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.1541/ieejeiss.136.1367

  87. Parts Selective DPM for detection of pedestrians possessing an umbrella Reviewed

    Yuto Shimbo, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of 2016 IEEE Intelligent Vehicles Symposium (IV2016)     page: 1053 - 1058   2016.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In recent years, pedestrian detection from an invehicle camera has been attracting attention.However, in the case of a raining situation, the detection accuracy decreases because the head of a pedestrian tends to be occluded by an umbrella. In oder to handle such cases, in this paper, as a variation of the Deformable Part Model (DPM) which is widely used in the field of object recognition, we propose Parts Selective DPM (PS-DPM)" which selectively chooses the original part filters and additional part filters trained independently. In the detection of pedestrians possessing an umbrella, the selection of head and umbrella parts will make pedestrian detection more robust to the occlusion. We conducted experiments to evaluate the performance of the proposed method. As a result, pedestrian detection with the proposed PS-DPM achieved high detection accuracy in rainy weather, compared with the detection by the conventional DPM. Moreover, we confirmed that it did not decrease the pedestrian detection accuracy in fine weather."

  88. Using Super-Pixels and Human Probability Map for Automatic Human Subject Segmentation Reviewed

    Esmaeil Pourjam, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences   Vol. E99-A ( 5 ) page: 943 - 953   2016.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Human body segmentation has many applications in a wide
    variety of image processing tasks, from intelligent vehicles to entertainment.
    A substantial amount of research has been done in the field of segmentation
    and it is still one of the active research areas, resulting in introduction of
    many innovative methods in literature. Still, until today, a method that can
    overcome the human segmentation problems and adapt itself to different
    kinds of situations, has not been introduced. Many of methods today try to
    use the graph-cut framework to solve the segmentation problem. Although
    powerful, these methods rely on a distance penalty term (intensity difference
    or RGB color distance). This term does not always lead to a good separation
    between two regions. For example, if two regions are close in color, even
    if they belong to two different objects, they will be grouped together, which
    is not acceptable. Also, if one object has multiple parts with different
    colors, e.g. humans wear various clothes with different colors and patterns,
    each part will be segmented separately. Although this can be overcome
    by multiple inputs from user, the inherent problem would not be solved.
    In this paper, we have considered solving the problem by making use of a
    human probability map, super-pixels and Grab-cut framework. Using this
    map relives us from the need for matching the model to the actual body,
    thus helps to improve the segmentation accuracy. As a result, not only the
    accuracy has improved, it also became comparable to the state-of-the-art
    interactive methods.

    DOI: 10.1587/transfun.E99.A.943

  89. A study on estimating the attractiveness of food photography Reviewed

    Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Proceedings of 2016 IEEE Second International Conference on Multimedia Big Data     page: 444 - 449   2016.4

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper proposes a method for estimating the attractiveness of food photos in order to assist a user to shoot them attractively.
    The proposed method extracts both color and shape features from input food images, and then integrates them according to a regression scheme.
    By this way, the proposed method estimates the attractiveness of an unknown food photo.
    We also created a food image dataset taken from various 3D-angles for each food category, and set target values of their attractiveness through subjective experiments.
    Then, we evaluated the performance of the proposed method in two different ways of constructing the attractiveness estimator: One that constructs it for each food category, and the other that constructs a common attractiveness estimator for all food categories.
    Experimental results showed the effectiveness of the proposed method in addition to the necessity for adaptively selecting the estimator depending on the appearance of foods for further performance improvement.

  90. Reconstructing Face Image from the Thermal Infrared Spectrum to the Visible Spetrum Reviewed

    Brahmastro Kresnaraman, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    Sensors, special issue on "Infrared and THz Sensing and Imaging"   Vol. 16 ( 4 ) page: 1 - 16   2016.4

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    During the night or in poorly lit areas, thermal cameras are a better choice instead of normal cameras for security surveillance because they do not rely on illumination. A thermal camera is able to detect a person within its view, but identification from only thermal information is not an easy task. The purpose of this paper is to reconstruct the face image of a person from the thermal spectrum to the visible spectrum. After the reconstruction, further image processing can be employed, including identification/recognition. Concretely, we propose a two-step thermal-to-visible-spectrum reconstruction method based on Canonical Correlation Analysis (CCA). The reconstruction is done by utilizing the relationship between images in both thermal infrared and visible spectra obtained by CCA. The whole image is processed in the first step while the second step processes patches in an image. Results show that the proposed method gives satisfying results with the two-step approach and outperforms comparative methods in both quality and recognition evaluations.

    DOI: 10.3390/s16040568

  91. Subtraction-Based General Forward Obstacle Detection from In-Vehicle Camera Images using Extended Census Transform Reviewed

    Haruya Kyutoku, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    IEEJ Transactions on Electronics, Information and Systems   Vol. 136 ( 4 ) page: 588 - 589   2016.4

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.1541/ieejeiss.136.588

  92. A classification method of cooking operations based on eye movement patterns Reviewed

    Hiroya Inoue, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of Ninth Biennial ACM Symposium on Eye Tracking Research and Applications (ETRA2016)     page: 205 - 208   2016.3

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1145/2857491.2857500

  93. HandWaving Gesture Detection Using a Far-Infrared Sensor Array with Thermo-Spatial Region of Interest Reviewed

    Chisato Toriyama, Yasutomo Kawanishi, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2016     page: 545 - 551   2016.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.5220/0005718105450551

  94. Image transformation of eye areas for synthesizing eye-contacts in video conferencing Reviewed

    Takuya Inoue, Tomokazu Takahashi, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Takayuki Kurozumi, Kunio Kashino

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2016   Vol. 3   page: 273 - 279   2016.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.5220/0005668702730279

  95. Human Wearable Attribute Recognition using Decomposition of Thermal Infrared Images Reviewed

    Brahmastro Kresnaraman, Yasutomo Kawanishi, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    Proceedings of the 22th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2016)     page: 123 - 127   2016.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper addresses an attribute recognition problem in thermal images, specifically on worn objects such as hat and glasses. Although attribute recognition is a growing research field, there are not much work done in thermal infrared spectrum. In this spectrum, since illumination is not a problem, it could be a better option to be used in nighttime or poorly lit areas. The proposed method uses only the attribute information and excludes the unnecessary information for the recognition. To achieve this, we propose attribute recognition based on feature decomposition using Robust Principal Component Analysis (RPCA). An experiment to evaluate the capability of the proposed method was conducted on the dataset created for this research. The results show that the proposed method outperformed the method without decomposition by 14% in average with a maximum of 27% increase in a specific attribute.

  96. Human Body Segmentation Using Texture Aware Grab-cut and Statistical Shape Models Reviewed

    Esmaeil Pourjam, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Proceedings of the 22th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2016)     page: 28 - 33   2016.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Segmentation is one of active areas in computer vision field with application in many areas from entertainment to intelligent vehicles (IVs). Among the objects, humans themselves have always been among the most interested subjects because of
    their special features. Since human body has an articulated structure, modeling and recognizing different variations in the body has proved to be very difficult. Wearing various kinds of clothes in different situations which can have a completely dissimilar appearance based on the clothing type, makes the modeling much more difficult. Add to this, the common problems of vision like illumination changes, blurring due to camera movements, etc. make the problem even more difficult. Thus having a system that can segment human subjects accurately can be useful in many applications. In this paper, we propose a system for segmenting human subjects using Statistical Shapes Models (SSM) feedback and a texture aware version of Grab-cut which incorporates texture feature for improving the segmentation accuracy. Our experiments show that the proposed system has an acceptable accuracy compared to the state-of-the art interactive methods and much better than the conventional ones.

  97. Human tracking using far-infrared sensor array (in Japanese) Reviewed

    Takashi Hosono, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

    IEICE Transactions on Information and Systems   Vol. J99-D ( 1 ) page: 119 - 129   2016.1

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.14923/transinfj.2015JDP7031

  98. Prediction of driver's pedestrian detectability considering characteristics of human fields-of-view while driving (in Japanese) Reviewed

    Ryunosuke Tanishige, Keisuke Doman, Daisuke Deguchi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Information and Systems   Vol. J99-D ( 1 ) page: 56 - 66   2016.1

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.14923/transinfj.2015HAP0015

  99. Position Interpolation using Feature Point Scale for Decimeter Visual Localization Reviewed

    David Robert Wong, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of 2015 IEEE International Conference on Computer Vision (ICCV2015) Workshops     page: 1 - 8   2015.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Vehicle ego-localization is a critical task not only for in-car navigation systems, but also for emerging intelligent and autonomous vehicle technologies. Visual localization methods that determine current location by performing image matching against a pre-constructed database have an accuracy limited by the spatial distance between database images. In this paper we propose a method that uses the scale of feature points to interpolate the position of the query image between two database images. We show how this simple contribution offers an appreciable improvement in localization accuracy with an extremely minimal increase in processing time, especially when used in conjunction with image matching methods that already monitor feature scale. Our experiments showed an increase of up to 33\% in average localization accuracy when compared to a method without any interpolation.

  100. Detector Ensemble based on False Positive Mining for Pedestrian Detection Reviewed

    Yuki Suzuki, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Proceedings of the 3rd IAPR Asian Conference on Pattern Recognition (ACPR2015)     2015.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  101. Generation of a video summary on a news topic based on SNS responses to news stories Reviewed

    Kosuke Kato, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Proc. 4th Int Workshop on Crowdsourcing for Multimedia (CrowdMM'15) in conjunction with ACMMM2015     page: 21 - 26   2015.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1145/2810188.2810189

  102. Distant Pedestrian Re-Detection from an in-Vehicle Camera based on Detections by Other Vehicles Reviewed

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    Proceedings of 2015 IEEE Conference on Intelligent Transportation Systems (ITSC2015)     page: 1215 - 1220   2015.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In this paper, we propose the re-detection paradigm, which is a detection with prior knowledge of the detection targets, and we introduce an implementation of the re-detection for distant pedestrian detection from an in-vehicle camera. We focus on the fact that other vehicles including forward vehicles can observe and detect pedestrians before the own vehicle observes them. Since appearances of pedestrians do not significantly change even though their locations are different, sharing images of the detected pedestrians among the vehicles, the own vehicle can use them as prior knowledge for detecting them again. Results of applying the proposed method to a dataset obtained by an in-vehicle camera demonstrate that the accuracy of pedestrian detection results can be significantly increased if prior knowledge of the pedestrians could be obtained.

    DOI: 10.1109/ITSC.2015.200

  103. Tastes and textures estimation of foods based on the analysis of its ingredients list and image Reviewed

    Hiroki Matsunaga, Keisuke Doman, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

      Vol. 9281   page: 326 - 333   2015.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Recently, the number of cooking recipes on the Web is increasing.
    However, it is difficult to search them by tastes or textures although
    they are actually important considering the nature of the contents.
    Therefore, we propose a method for estimating the tastes and the
    textures of a cooking recipe by analyzing them.
    Concretely, the proposed method refers to an ingredients feature from
    the ``ingredients list'' and image features from the ``food image'' in
    a cooking recipe.
    We confirmed the effectiveness of the proposed method through an
    experiment.

  104. Statistical Shape Feedback for Human Subject Segmentation Reviewed

    Esmaeil Pourjam, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEEJ Transactions on Electronics, Information and Systems   Vol. 135-C ( 8 ) page: 1000 - 1008   2015.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Human segmentation is one of the most interesting yet most challenging subjects in the field of object segmentation and image processing. It can be used in various types of applications from image retrieval to robotics and human machine interfaces, including even entertainment. Many researches have been done on this subject and it is still one of active research areas. But until now, a method for accurate segmentation in different conditions has not been introduced. In this paper, we present Statistical Shape Feedback Segmentation” (SSFSeg) method, which is a way to automatically segment human subjects (pedestrians) from single images. Our main contributions in this paper are: 1) Using human shape model as priors for Grab-cut segmentation. 2) Implementation of a feedback system which provides a coarse-to-fine way of generating more accurate shapes. For this task, we try to use masks generated by the Statistical Shape Model (SSM) algorithm as a prior input for the Grab-cut technique to segment the desired human subject in the image without user interaction. To achieve this, we propose a feedback framework for the SSM sample generation. Our experiments confirmed that the segmentation error of our proposed method is less than half of the Grab-cut method."

    DOI: 10.1541/ieejeiss.135.1000

  105. Typicality analysis of the combination of ingredients in a cooking recipe for assisting the arrangement of ingredients Reviewed

    Satoshi Yokoi, Keisuke Doman, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Proceedings of 2015 IEEE International Conference on Multimedia and Expo (ICME2012)     page: 1 - 6   2015.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    As the number of cooking recipes posted on the Web increases, it becomes difficult to find a cooking recipe that a user needs. Moreover, even if it can be done, it is still difficult for users to arrange the cooking recipe, for example, by replacing ingredients with different ones. To deal with such problems, we propose a framework for typicality analysis of the combination of ngredients. The framework calculates a typicality value for each combination of ingredients. The list of ingredients can be arranged by adjusting the typicality value by adding or removing ingredients iteratively. The effectiveness of the proposed framework was confirmed through subjective experiments.

  106. Pedestrian Orientation Classification Utilizing Single-Chip Coaxial RGB-ToF Camera Reviewed

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    Proceedings of Workshop on Environment Perception for Automated On-road Vehicles in conjunction with 2015 IEEE Intelligent Vehicles Symposium (IV2015)     page: 7 - 11   2015.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper proposes a method for pedestrian orientation classification. In image recognition, the accuracy is often degraded by the influence of background. In addition, it is also difficult to remove the background and extract only the human body from an image. To overcome these problems, we utilize a single-chip RGB-ToF camera. This camera can acquire RGB and depth images along the same optical axis at the same moment, and thus segmentation of the RGB image becomes easier by using the coaxial depth image. Our proposed method segmented a human body from its background accurately, which lead to the improvement of the accuracy of pedestrian orientation classification.

  107. Translating Apereo Software: A Case Study using Sakai and Transifex

    Yuji Tokiwa, Daisuke Deguchi, Juan Jose Merono Sanchez, Jose Mariano Lujan Gonzalez, Diego del Blanco Orobitg

        2015.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Web based translation support systems such as Crowdin and Transifex make it easy for regional Sakai communities to collaborate globally in translation. In the fall and winter of 2014, Spanish Sakai community and Japanese Sakai community are collaborating in translation of Sakai 10 using Transifex as a common translation platform. This collaboration brought a lot of things to two communities. For instance, to develop a tool to import resource bundle files to Transifex in a specific manner, we can have an ease of use platform to translate modular designed software such as Sakai. And this platform will be extended for every regional community and for every project in Apereo community.
    During this session we will talk about followings;
    (1) Overview
    (2) Benefits for Apereo community
    (3) Context dependent translation by gettext Portable Object
    (4) Community translation strategy in Sakai Spanish Users (S2U)
    (5) Automatized process by Jenkins

  108. Multi-modal scene duplicate detection from news videos focusing on human faces Reviewed

    Haruka Kumagai, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    International Journal of Semantic Computing   Vol. 9 ( 2 ) page: 215 - 237   2015.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    In this paper, as a tool for structuring a large volume of archived news videos according to their semantic contents, we propose a method that effectively detects scene duplicates, assuming the presence of a person speaking in the videos. A scene duplicate is defined here as a pair of video segments taken at the same event from different viewpoints. When considering scenes where a subject is speaking in news videos, referring to the audio channel could be effective to detect scene duplicates regardless of viewpoints. However, it cannot be relied on when external audio sources overlap the original one or when the subject is actually not speaking. In contrast, the image channel can be useful in most cases. However, significant difference in viewpoints could prevent accurate detection. Therefore, we propose a method that combines the results obtained from both audio and image channels in order to improve the accuracy of scene duplicate detection from news videos. The proposed method was evaluated through an experiment with actual broadcast news videos by comparing it with a conventional method. As a result, we confirmed that the detection accuracy significantly improved by the proposed method in both recall and precision.

    DOI: 10.1142/S1793351X15400048

  109. Localization of Open Source Softoware for Higher EducationCommon translation memory Reviewed

    Yuji Tokiwa, Daisuke Deguchi, Makoto Miyazaki, Naoshi Hiraoka, Toshihiro Kita, Shoji Kajita

    IPSJ Journal of Digital Practices   Vol. 6 ( 2 ) page: 79 - 88   2015.4

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  110. Adaptive Reference Image Selection for Temporal Object Removal from Frontal In-vehicle Camera Image Sequences Reviewed

    Toru Kotsuka, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2015     page: 233 - 239   2015.3

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In recent years, image inpainting is widely used to remove undesired objects from an image. Especially, the removal of temporal objects, such as pedestrians and vehicles, in street-view databases such as Google Street View has many applications in Intelligent Transportation Systems (ITS). To remove temporal objects, Uchiyama et al. proposed a method that combined multiple image sequences captured along the same route. However, when spatial alignment inside an image group does not work well, the quality of the output image of this method is often affected. For example, large temporal objects existing in only one image create regions that do not correspond to other images in the group, and the image created from aligned images becomes distorted. One solution to this problem is to select adaptively the reference image containing only small temporal objects for spatial alignment. Therefore, this paper proposes a method to remove temporal objects by integration of multiple image sequences with an adaptive reference image selection mechanism.

    DOI: 10.5220/0005357102330239

  111. Estimation of Human Orientation using Coaxial RGB-Depth Images Reviewed

    Fumito Shinmura, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2015     page: 113 - 120   2015.3

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Estimation of human orientation contributes to improving the accuracy of human behavior recognition. However,
    estimation of human orientation is a challenging task because of the variable appearance of the human
    body. The wide variety of poses, sizes and clothes combined with a complicated background degrades the
    estimation accuracy. Therefore, we propose a method for estimating human orientation using coaxial RGBDepth
    images. This paper proposes Depth Weighted Histogram of Oriented Gradients (DWHOG) feature
    calculated from RGB and depth images. By using a depth image, the outline of a human body and the texture
    of a background can be easily distinguished. In the proposed method, a region having a large depth gradient
    is given a large weight. Therefore, features at the outline of the human body are enhanced, allowing robust
    estimation even with complex backgrounds. In order to combine RGB and depth images, we utilize a newly
    available single-chip RGB-ToF camera, which can capture both RGB and depth images taken along the same
    optical axis. We experimentally confirmed that the proposed method can estimate human orientation robustly
    to complex backgrounds, compared to a method using conventional HOG features.

    DOI: 10.5220/0005305301130120

  112. Scene duplicate detection from news videos using image-audio matching focusing on human faces Reviewed

    Haruka Kumagai, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Proceedings of the 16th IEEE International Symposium on Multimedia (ISM2014)     page: 71 - 77   2014.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ISM.2014.43

  113. Event detection based on twitter enthusiasm degree for generating a sports highlight video Reviewed

    Keisuke Doman, Taishi Tomita, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

        page: 949 - 952   2014.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper presents a Twitter-based event detection method based on Twitter Enthusiasm Degrees (TED)" toward generating a highlight video of a sports game. Existing methods not only depend on both languages and sports types but also often falsely detect non-target events. In contrast, the proposed method detects sports events using TEDs calculated from several kinds of string features independent of languages and sports. We applied the proposed method to actual sports games, and compared the detected events with the events present in broadcasted highlight videos, and confirmed the effectiveness and the language and sports type independencies of the proposed method."

  114. Human Tracking using a Far-Infrared Sensor Array and a Thermo-Spatial Sensitive Histogram

    細野 峻司, 高橋 友和, 出口 大輔, 井手 一郎, 村瀬 洋, 相澤 知禎, 川出 雅人

    Proceedings of 2nd Workshop on User-Centred Computer Vision     2014.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  115. Prediction of Driver's Pedestrian Detectability by Image Processing Adaptive to Visual Fields of View Reviewed

    Ryunosuke Tanishige, Daisuke Deguchi, Keisuke Doman, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    Proceedings of 2014 IEEE Conference on Intelligent Transportation Systems (ITSC2014)     page: 1388 - 1393   2014.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  116. Vision-based Vehicle Localization using a Visual Street Map with Embedded SURF Scale Reviewed

    David Robert Wong, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of Computer Vision in Vehicle Technology with Special Session on Micro Aerial Vehicles (CVVT2014)     2014.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Accurate vehicle positioning is important not only for in-car navigation systems but is also a requirement for emerging autonomous driving methods. Consumer level GPS are inaccurate in a number of driving environments such as in tunnels or areas where tall buildings cause satellite shadowing. Current vision-based methods typically rely on the integration of multiple sensors or fundamental matrix calculation which can be unstable when the baseline is small.

    In this paper we present a novel visual localization method which uses a visual street map and extracted SURF image features. By monitoring the difference in scale of features matched between input images and the visual street map within a Dynamic Time Warping framework, stable localization in the direction of motion is achieved without calculation of the fundamental or essential matrices.

    We present the system performance in real traffic environments. By comparing localization results with a high accuracy GPS ground truth, we demonstrate that accurate vehicle positioning is achieved.

  117. Spatial People Density Estimation from Multiple Viewpoints by Memory Based Regression Reviewed

    Yoshimune Tabuchi, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Takayuki Kurozumi, Kunio Kashino

    Proceedings of the 22nd IAPR International Conference on Pattern Recognition (ICPR2014)     page: 2209 - 2214   2014.8

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Crowd analysis using cameras has attracted much attention for public safety and marketing. Among techniques of the crowd analysis, we focus on spatial people density estimation which estimates the number of people for each small area in a floor region. However, spatial people density cannot be estimated accurately for an area far from the camera because of the occlusion by people in a closer area. Therefore, we propose a method using a memory based regression method with images captured from cameras from multiple viewpoints. This method is realized by looking up a table that consists of correspondences between people density maps and crowd appearances. Since the crowd appearances include situations where various occlusions occur, an estimation robust to occlusion should be realized. In an experiment, we examined the effectiveness of the proposed method.

  118. Single Camera Vehicle Localization Using SURF Scale and Dynamic Time Warping Reviewed

    David Robert Wong, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of 2014 the IEEE Intelligent Vehicles Symposium (IV2014)     page: 681 - 686   2014.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Vehicle ego-localization is an essential process for many driver assistance and autonomous driving systems. The traditional solution of GPS localization is often unreliable in urban environments where tall buildings can cause shadowing of the satellite signal and multipath propagation. Typical visual feature based localization methods rely on calculation of the fundamental matrix which can be unstable when the baseline is small.
    In this paper we propose a novel method which uses the scale of matched SURF image features and Dynamic Time Warping to perform stable localization. By comparing SURF feature scales between input images and a pre-constructed database, stable localization is achieved without the need to calculate the fundamental matrix. In addition, 3D information is added to the database feature points in order to perform lateral localization, and therefore lane recognition.
    From experimental data captured from real traffic environments, we show how the proposed system can provide high localization accuracy relative to an image database, and can also perform lateral localization to recognize the vehicle's current lane.

  119. Estimation of Traffic Sign Visibility Considering Local and Global Features in a Driving Environment Reviewed

    Keisuke Doman, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase, Utsushi Sakai

    Proceedings of 2014 IEEE Intelligent Vehicles Symposium (IV2014)     page: 202 - 207   2014.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper proposes a camera-based visibility estimation method for a traffic sign.
    The visibility here indicates how a visual target is easy to be detected and recognized by a human driver (not a machine).
    This research aims at realizing a nuisance-free driver assistance system which sorts out information depending on the visibility of a visual target, in order to prevent driver distraction.
    Our previous study on estimating the visibility of a traffic sign considered only the effect of the local region around a target, assuming the situation that a driver's gaze is around it.
    The proposed method integrates both the local features and global features in a driving environment without such an assumption.
    The global features evaluate the positional relationships between traffic signs and the appearance around the fixation point of a driver's gaze, which considers the effect of the driver's entire field of view.
    Experimental results showed the effectiveness of incorporating the global features for estimating the visibility of a traffic sign.

  120. Ego-localization by Searching in a Streetview Database using a Sequence of Image Distance based on the Positional Relation between In-vehicle Cameras Reviewed

    Haruya Kyutoku, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    IEEJ Transactions on Electronics, Information and Systems   Vol. 134 ( 5 ) page: 702 - 710   2014.5

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.1541/ieejeiss.134.702

  121. Estimation of the Representative Story Transition in a Chronological Semantic Structure of News Topics Reviewed

    Kosuke Kato, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Proceedings of the 4th International Conference on Multimedia Retrieval (ICMR2014)     page: 487 - 491   2014.4

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    It is important to track the flow of topics to thoroughly understand the contents. Accordingly, a method that structures the chronological semantic relations between news stories, namely a 'topic thread structure' has been proposed.It allows the comprehensive understanding of a topic by chronologically tracking stories one by one from the initial story. However, this task imposes a user to watch many stories when it contains various sub-topics. Thus, we propose method that estimates the representative story transition in a topic thread structure. In the proposed method, features obtained from a story and those from the topic thread structure are used for the estimation. We confirmed the effectiveness of the proposed method by comparing the results obtained from the proposed method to the ground truth obtained from votes in a subjective experiment. However, this task imposes a user to watch many stories when it contains various sub-topics. Thus, we propose method that estimates the representative story transition in a topic thread structure. In the proposed method, features obtained from a story and those from the topic thread structure are used for the estimation. We confirmed the effectiveness of the proposed method by comparing the results obtained from the proposed method to the ground truth obtained from votes in a subjective experiment

  122. Can a Human be a Sensor? Reviewed

    Atsushi Shimada, Daisuke Deguchi, Kazuaki Kondo, Takuya Funatomi

    Proceedings of the 20th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2014)     page: 242 - 245   2014.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper discusses a novel sensing strategy to retrieve real-world information. Instead of using sensor devices such as cameras, microphones and so on, the proposed approach involves people in real-world sensing to acquire requested information as accurately and quickly as possible. We call the proposed sensing strategy as Human Cloud Sensing (HCS)". In this paper, we introduce the concept of HCS and report some experimental results which were conducted to investigate the feasibility of "Can a human be a sensor?"."

  123. Environment adaptive pedestrian detection using in-vehicle camera and GPS Reviewed

    Daichi Suzuo, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hiroyuki Ishida, Yoshiko Kojima

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2014     page: 354 - 361   2014.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In recent years, accurate pedestrian detection from in-vehicle camera images is focused to develop a safety driving assistance system. Currently, successful methods are based on statistical learning. However, in such methods, it is necessary to prepare a large amount of training images. Thus, the decrease in the number of training images degrades the detection accuracy. That is, in driving environments with few or no training images, it is difficult to detect pedestrians accurately. Therefore, we propose an approach that collects training images automatically to build classifiers for various driving environments. This is expected to realize highly accurate pedestrian detection by using an appropriate classifier corresponding to the current location. The proposed method consists of three steps; Classification of driving scenes, collection of non-pedestrian images and training of classifiers for each scene class, and associating a scene-class-specific classifier with GPS location information. Through experiments, we confirmed the effectiveness of the method compared to baseline methods.

    DOI: 10.5220/0004677003540361

  124. Exemplar-Based Human Body Super-Resolution for Surveillance Camera Systems Reviewed

    Kento Nishibori, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2014     page: 115 - 121   2014.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In this paper, we propose an exemplar-based super-resolution method applied to a human body in a surveillance video. Since persons are usually captured as low-resolution images by a video surveillance system, it is sometimes necessary to perform detection and identification of persons from not only a human face but also from the human body appearance. The super-resolution for a human body image is difficult because the appearances of person images vary according to the color of clothing and the posture of persons. Thus, we focus on the high-frequency components that could restore the lost high-frequency components of the low-resolution image regardless to the variation of the clothing. Therefore, the purpose of the work presented in this paper is to apply the exemplar-based super-resolution using high-frequency components for a low-resolution human body image to generate a high-resolution human body image so that both computer systems and humans can identify persons more accurately. As a result of experiments, we confirmed the effectiveness of the proposed super-resolution method.

    DOI: 10.5220/0004686101150121

  125. Scene dependent classifiers for pedestrian detection

    Hidefumi Yoshida, Daichi Suzuo, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

        2013.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  126. Automatic authoring of a domestic cooking video based on the description of cooking instructions Reviewed

    Yasuhiro Hayashi, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Proceedings of 5th International Workshop on Multimedia for Cooking and Eating Activities (CEA'13)     page: 21 - 26   2013.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1145/2506023.2506028

  127. Blur-invariant Traffic Sign Recognition Using Compact Local Phase Quantization Reviewed

    Saleh Aly, Daisuke Deguchi, Hiroshi Murase

    Proceedings of 2013 IEEE Conference on Intelligent Transportation Systems (ITSC2013)     page: 821 - 827   2013.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  128. Construction of a traffic sign detector based on voting type co-training Reviewed

    Yuji Kojima, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of 2013 IEEE Conference on Intelligent Transportation Systems (ITSC2013)     page: 1137 - 1142   2013.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  129. Prediction of Pedestrian Detectability for Drivers by Image Processing and its Driver Adaptation Reviewed

    Ryunosuke Tanishige, Daisuke Deguchi, Keisuke Doman, Yoshito Mekada, Ichiro Ide, Hiroshi Murase, Naoki Nitanda

    Proceedings of the 6th Biennial Workshop on Digital Signal Processing for In-Vehicle Systems (DSP2013)     page: 1 - 4   2013.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In recent years, advances in pedestrian detection technology have resulted in the development of driving assistance systems that notify the drivers of the presence of pedestrians. However, warning of all of the presence of pedestrians would confuse the driver. Therefore, the driver should only be notified of the less detectable pedestrians to avoid confusion. To achieve this, it is necessary to develop a method to predict the driver’s perception performance of pedestrian detectability. This paper proposes a method that predicts the pedestrian detectability considering the difference between individual drivers. The proposed method constructs a predictor specific to each driver, in order to predict the pedestrian detectability precisely. To obtain the ground truth of the pedestrian detectability, we conducted an experiment by human subjects using images from an in-vehicle camera including pedestrians. From the comparison between the output of the proposed method and the actual detectability, we confirmed that the proposed method significantly reduces the prediction error in comparison with the existing methods.

  130. Pedestrian Detection by Scene Dependent Classifiers with Generative Learning Reviewed

    Hidefumi Yoshida, Daichi Suzuo, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Takashi Machida, Yoshiko Kojima

    Proceedings of 2013 IEEE Intelligent Vehicles Symposium (IV2013)     page: 654 - 659   2013.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Recently, pedestrian detection from in-vehicle camera images is becoming an crucial technology for Intelligent Transportation Systems (ITS). However, it is difficult to detect pedestrians accurately in various scenes by obtaining training samples. To tackle this problem, we propose a method to construct scene dependent classifiers to improve the accuracy of pedestrian detection. The proposed method selects an appropriate classifier based on the scene information that is a category of appearance associated with location information. To construct scene dependent classifiers, the proposed method introduces generative learning for synthesizing scene dependent training samples. Experimental results showed that the detection accuracy of the proposed method outperformed the comparative method, and we confirmed that scene dependent classifiers improved the accuracy of pedestrian detection.

  131. Segmentation of Human Instances Using Grab-cut and Active Shape Model Feedback Reviewed

    Esmaeil Pourjam, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Proceedings of IAPR Conference on Machine Vision Applications (MVA) 2013     page: 77 - 80   2013.5

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  132. Cross-pose face recognition Reviewed

    Xi Li, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Transaction on Information and Systems, Special Section on Face Perception and Recognition   Vol. E96-D ( 3 ) page: 531 - 537   2013.3

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    This paper presents an approach for cross-pose face recognition by virtual view generation using an appearance clustering based local view transition model. Previously, the traditional global pattern based view transition model (VTM) method was extended to its local version called LVTM, which learns the linear transformation of pixel values between frontal and non-frontal image pairs from training images using partial image in a small region for each location, instead of transforming the entire image pattern. In this paper, we show that the accuracy of the appearance transition model and the recognition rate can be further improved by better exploiting the inherent linear relationship between frontal-nonfrontal face image patch pairs. This is achieved based on the observation that variations in appearance caused by pose are closely related to the corresponding 3D structure and intuitively frontal-nonfrontal patch pairs from more similar local 3D face structures should have a stronger linear relationship. Thus for each specific location, instead of learning a common transformation as in the LVTM, the corresponding local patches are first clustered based on an appearance similarity distance metric and then the transition models are leaned separately for each cluster. In the testing stage, each local patch for the input non-frontal probe image is transformed using the learned local view transition model corresponding to the most visually similar cluster. The experimental results on a real-world face dataset demonstrated the superiority of the proposed method in terms of recognition rate.

  133. Two-step super-resolution with binary and grid constraints for low resolution QR-code recognition Reviewed

    Yuji Kato, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Information and Systems   Vol. J96-D ( 2 ) page: 328 - 337   2013.2

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  134. Detection of Biased Broadcast Sports Video Highlights by Attribute-Based Tweets Analysis Reviewed

    Takashi Kobayashi, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Lecture Note in Computer Science   Vol. 7733   page: 364 - 373   2013.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    We propose a method for detecting biased-highlights in a broadcast sports video according to viewers’ attributes obtained from a large number of tweets. Recently, Twitter is widely used to make real-time play-by-play comments on TV programs, especially on sports games. This trend enables us to effectively acquire the viewers’ interests in a large mass. In order to make use of such tweets for highlight detection in broadcast sports video, the proposed method first performs an attribute analysis on the set of tweets issued by each user to classify which team he/she supports. It then detects biased-highlights by referring to the number of tweets made by viewers with a specific attribute.

    DOI: 10.1007/978-3-642-35728-2_35

  135. A Study of Gaze Estimation Using Head and Body Pose Information Reviewed

    Nobuhiro Funatsu, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of International Workshop on Advanced Image Technology (IWAIT) 2013     page: 231 - 235   2013.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Gaze estimation from an image is an important technique for tasks such as driver monitoring and measuring of advertising effectiveness. For this, most existing methods require a high quality image of eyes. However, It is difficult to obtain the eye images when eye occlusion occurs due to sunglasses or face rotation. Another approach approximates head directions to gaze directions. However, the gaze direction is affected not only by the head direction but also by the body direction. Thus, we are studying a method that estimates the gaze direction accurately using information on both head and body pose directions. Experimental result showed that the proposed method could estimate gaze directions more accurately than by using the information on only head directions.

  136. Estimation of the human performance for pedestrian detectability based on visual search and motion features Reviewed

    Masashi Wakayama, Daisuke Deguchi, Keisuke Doman, Ichiro Ide, Hiroshi Murase, Yukimasa Tamatsu

    Proceedings of the 21st IAPR International Conference on Pattern Recognition (ICPR2012)     page: 1940 - 1943   2012.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper proposes a method for estimating the human performance of pedestrian detectability from in-vehicle camera images in order to warn a driver of the positions of pedestrians in an appropriate timing. By introducing features related to visual search and motion of the target, the proposed method estimates the detectability of pedestrians accurately. Support Vector Regression (SVR) is used to estimate the detectability. Here, SVR is trained using features calculated by the proposed method with the ground truth obtained through experiments with human subjects. From experiments using in-vehicle camera images, we confirmed that the proposed features were effective to estimate the detectability of pedestrians.

  137. Virtual View Generation using Clustering based Local View Transition Model Reviewed

    Xi Li, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of ACCV Workshop on Face Analysis: The Intersection of Computer Vision and Human Perception     2012.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper presents an approach for realistic virtual view generation using appearance clustering based local view transition model, with its target application on cross-pose face recognition. Previously, the traditional global pattern based view transition model (VTM) method was extended to its local version called LVTM, which learns the linear transformation of pixel values between frontal and non-frontal image pairs using partial image in a small region for each location, rather than transforming the entire image pattern. In this paper, we show that the accuracy of the appearance transition model and the recognition rate can be further improved by better exploiting the inherent linear relationship between frontal-nonfrontal face image patch pairs. For each specific location, instead of learning a common transformation as in the LVTM, the corresponding local patches are first clustered based on appearance similarity distance metric and then the transition models are learned separately for each cluster. In the testing stage, each local patch for the input non-frontal probe image is transformed using the learned local view transition model corresponding to the most visually similar cluster. The experimental results on a real-world face dataset demonstrated the superiority of the proposed method in terms of recognition rate.

  138. Ego-Localization Based on Frame Correspondences between In-Vehicle Camera Images and Streetview Database Reviewed

    Haruya Kyutoku, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Information and Systems   Vol. J95-D ( 11 ) page: 1973 - 1982   2012.11

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  139. Subtraction-Based Forward Obstacle Detection Using Illumination Insensitive Feature for Driving-Support Reviewed

    Haruya Kyutoku, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    Proceedings of Computer Vision in Vehicle Technology: From Earth to Mars (CVVT2012)   Vol. Part II ( LNCS 7584 ) page: 515 - 525   2012.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper proposes a method for detecting general obstacles on a road by subtracting present and past in-vehicle camera images.
    The image-subtraction-based object detection approach can be applied to detect any kind of obstacles although the existing learning-based methods detect only specific obstacles.
    To detect general obstacles, the proposed method first computes a frame-by-frame correspondence between the present and the past in-vehicle camera image sequences, and then registrates road surfaces between the frames.
    Finally, obstacles are detected by applying image subtraction to the registrated road surface regions with an illumination insensitive feature for robust detection.
    Experiments were conducted by using several image sequences captured by an actual in-vehicle camera to confirm the effectiveness of the proposed method.
    The experimental results shows that the proposed method can detect general obstacles accurately at a distance enough to avoid them safely even in situations with different illuminations.

    DOI: 10.1007/978-3-642-33868-7_51

  140. Visibility Estimation of Traffic Signals under Rainy Weather Conditions for Smart Driving Support Reviewed

    Ryuhei Sato, Keisuke Doman, Daisuke Deguchi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase, Yukimasa Tamatsu

    Proceedings of 2012 IEEE Conference on Intelligent Transportation Systems (ITSC2012)     page: 1321 - 1326   2012.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    The aim of this work is to support a driver by
    notifying the information of traffic signals in accordance with
    their visibility. To avoid traffic accidents, the driver should
    detect and recognize surrounding objects, especially traffic
    signals. However, when driving a vehicle under rainy weather
    conditions, it is difficult for drivers to detect or to recognize
    objects existing in the road environment in comparison with fine
    weather conditions. Therefore, this paper proposes a method
    for estimating the visibility of traffic signals for drivers under
    rainy weather conditions by image processing. The proposed
    method is based on the concept of visual noise known in the
    field of cognitive science, and extracts two types of visual noise
    features which ware considered that they affect the visibility of
    traffic signals. We expect to improve the accuracy of visibility
    estimation by combining the visual noise features with the
    texture feature introduced in a previous work. Experimental
    results showed that the proposed method could estimate the
    visibility of traffic signals more accurately under rainy weather
    conditions.

    DOI: 10.1109/ITSC.2012.6338838

  141. Detection and classification of repetitious human motions combining shift variant and invariant features Reviewed

    Ichiro Ide, Taku Kuhara, Daisuke Deguchi, Tomokazu Takahashi, Hiroshi Murase

    Proceedings of the 3rd International Conference on Emerging Security Technologies (EST2012)     page: 86 - 89   2012.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/EST.2012.7

  142. Robust Face Super-Resolution Using Free-Form Deformations For Low-Quality Surveillance Video Reviewed

    Tomonari Yoshida, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of 2012 IEEE International Conference on Multimedia and Expo (ICME2012)     page: 368 - 373   2012.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ICME.2012.162

  143. Speech shot extraction from broadcast news videos Reviewed

    Shogo Kumagai, Keisuke Doman, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    International Journal of Semantic Computing   Vol. 6 ( 2 ) page: 179 - 204   2012.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    We propose a method for discriminating between a speech shot and a narrated shot to extract genuine speech shots from a broadcast news video. Speech shots in news videos contain a wealth of multimedia information of the speaker, and could thus be considered valuable as archived material. In order to extract speech shots from news videos, there is an approach that uses the position and size of a face region. However, it is difficult to extract them with only such an approach, since news videos contain non-speech shots where the speaker is not the subject that appears in the screen, namely, narrated shots. To solve this problem, we propose a method to discriminate between a speech shot and a narrated shot in two stages. The first stage of the proposed method directly evaluates the inconsistency between a subject and a speaker based on the co-occurrence between lip motion and voice. The second stage of the proposed method evaluates based on the intra- and inter-shot features that focus on the tendency of speech shots. With the combination of both stages, the proposed method accurately discriminates between a speech shot and a narrated shot. In the experiments, the overall accuracy of speech shots extraction by the proposed method was 0.871. Therefore, we confirmed the effectiveness of the proposed method.

    DOI: 10.1142/S1793351X12400077

  144. Real-time marker-free patient registration for electromagnetic navigated bronchoscopy: a phantom study Reviewed

    Daisuke Deguchi, Marco Feuerstein, Takayuki Kitasaka, Yasuhito Suenaga, Ichiro Ide, Hiroshi Murase, Kazuyoshi Imaizumi, Yoshinori Hasegawa, Kensaku Mori

    International Journal of Computer Assisted Radiology and Surgery   Vol. 7 ( 3 ) page: 359 - 369   2012.5

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (scientific journal)  

    Purpose
    To perform bronchoscopy safely and smoothly, it is very important to develop a bronchoscopic guidance system. Transbronchial lung biopsy (TBLB) with a bronchoscopic guidance system especially should permit safe image-guided procedures. Recently, electromagnetic tracking (EMT) is utilized to track the tip of the bronchoscope camera in real time. For most tracking methods using position sensors, registration between tracking data and previously acquired reference image data, such as CT image, is performed using natural landmarks of the patient or fiducial markers attached to the patient, whose positions need to be measured manually by the physician before the actual bronchoscopy. Therefore, this paper proposes a marker-free CT-to-patient registration method utilizing bronchoscope's position and orientation obtained by the EMT.

    Methods
    We developed a guidance system that is able to track the tip of the bronchoscope camera in real time. In the case of a guidance system that uses position sensors, natural landmarks of the patient or fiducial markers attached to the patient are needed to obtain the correspondence between EMT outputs and previously acquired reference image data, such as CT image. This paper proposes a registration method without landmarks or fiducials by estimating the transformation matrix between the patient and the CT image taken prior to the bronchoscopic examination. This estimation is performed by computing correspondences between the outputs of the EMT sensor and airways extracted from the CT image. As ambiguities between EMT measurements and their corresponding airway branches may arise at airway bifurcations, we introduce a stable airway branch selection mechanism for improving the robustness of the estimation of the transformation matrix. To evaluate the performance of the proposed method, we applied the method to a rubber bronchial phantom and added virtual breathing motion to the sensor output.

    Results
    Experimental results show that the accuracy of our proposed method is within 2.0-3.0 mm (without breathing motion) and 2.5-3.5 mm (with breathing motion). The proposed method could also track a bronchoscope camera in real time.

    Conclusions
    We developed a method for CT-to-patient registration using a position sensor without fiducial markers and natural landmarks. Endoscopic guided biopsy of lung lesions is feasible using a marker-free CT-to-patient registration method.

    DOI: 10.1007/s11548-011-0626-9

  145. Construction of a local attraction map according to social visual attention Reviewed

    Ichiro Ide, Jiani Wang, Masafumi Noda, Tomokazu Takahashi, Daisuke Deguchi, Hiroshi Murase

    Proceedings of the 5th International Conference on Intelligent Interactive Multimedia Systems and Services (IIMSS2012)     page: 153 - 162   2012.5

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1007/978-3-642-29934-6_15

  146. Development and comparison of new hybrid motion tracking for bronchoscopic navigation Reviewed

    Xiongbiao Luo, Marco Feuerstein, Daisuke Deguchi, Takayuki Kitasaka, Hirotsugu Takabatake, Kensaku Mori

    Medical Image Analysis   Vol. 16 ( 3 ) page: 577 - 596   2012.4

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    This paper presents a new hybrid camera motion tracking method for bronchoscopic navigation combining SIFT, epipolar geometry analysis, Kalman filtering, and image registration. In a thorough evaluation, we compare it to state-of-the-art tracking methods. Our hybrid algorithm for predicting bronchoscope motion uses SIFT features and epipolar constraints to obtain an estimate for inter-frame pose displacements and Kalman filtering to find an estimate for the magnitude of the motion. We then execute bronchoscope tracking by performing image registration initialized by these estimates. This procedure registers the actual bronchoscopic video and the virtual camera images generated from 3D chest CT data taken prior to bronchoscopic examination for continuous bronchoscopic navigation. A comparative assessment of our new method and the state-of-the-art methods is performed on actual patient data and phantom data. Experimental results from both datasets demonstrate a significant performance boost of navigation using our new method. Our hybrid method is a promising means for bronchoscope tracking, and outperforms other methods based solely on Kalman filtering or image features and image registration.

    DOI: 10.1016/j.media.2010.11.001

  147. Integration of generative learning and multiple pose classifiers for pedestrian detection Reviewed

    Hidefumi Yoshida, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Kunihiro Goto, Yoshikatsu Kimura, Takashi Naito

    Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2012   Vol. 1   page: 567 - 572   2012.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Recently, pedestrian detection from in-vehicle camera images is becoming an important technology in ITS (Intelligent Transportation System).
    However, it is difficult to detect pedestrians stably due to the variety of their poses and their backgrounds.
    To tackle this problem, we propose a method to detect various pedestrians from in-vehicle camera images by using multiple classifiers corresponding to various pedestrian pose classes.
    Since pedestrians’ pose varies widely, it is difficult to construct a single classifier that can detect pedestrians with various poses stably.
    Therefore, this paper constructs multiple classifiers optimized for variously posed pedestrians by classifying pedestrian images into multiple pose classes.
    Also, to reduce the bias and the cost for preparing numerous pedestrian images for each pose class for learning, the proposed method employs a generative learning method.
    Finally, the proposed method constructs multiple classifiers by using the synthesized pedestrian images.
    Experimental results showed that the detection accuracy of the proposed method outperformed comparative methods, and we confirmed that the proposed method could detect variously posed pedestrians stably.

    DOI: 10.5220/0003817305670572

  148. Construction of an accurate traffic sign detector by automatic gathering of traffic sign images based on retrospective tracking Reviewed

    Daisuke Deguchi, Keisuke Doman, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Information and Systems   Vol. J95-D ( 1 ) page: 76 - 84   2012.1

     More details

    Authorship:Lead author   Language:Japanese   Publishing type:Research paper (scientific journal)  

  149. Improvement of Vehicle Ego-localization by Sequential Matching of Feature-points from an Aerial Image and an In-vehicle Camera Image Reviewed

    Masafumi Noda, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Yoshiko Kojima, Takashi Naito

    IEICE Transactions on Information and Systems   Vol. J95-D ( 1 ) page: 111 - 121   2012.1

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  150. Estimation of traffic sign visibility based on the integration of contrast features and appearance features Reviewed

    Keisuke Doman, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase, Yukimasa Tamatsu

    IEICE Transactions on Information and Systems   Vol. J95-D ( 1 ) page: 122 - 130   2012.1

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  151. Classification of near-duplicate video clips in a large-scale broadcast video archive based on their appearance patterns Reviewed

    Yuji Shamoto, Ichiro Ide, Daisuke Deguchi, Tomokazu Takahashi, Hiroshi Murase

    Journal of Information Processing   Vol. 52 ( 12 ) page: 3593 - 3598   2011.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  152. Creation of a Sight-seeing Map with Visual Classification of Photos on the Web Reviewed

    Jiani Wang, Masafumi Noda, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Journal of Information Processing   Vol. 52 ( 12 ) page: 3588 - 3592   2011.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  153. Detection of Inconsistency between Subject and Speaker based on the Co-occurrence of Lip Motion and Voice Towards Speech Scene Extraction from News Videos Reviewed

    Shogo Kumagai, Keisuke Doman, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of 2011 IEEE International Symposium on Multimedia (ISM2011)     page: 311 - 318   2011.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    We propose a method to detect the inconsistency between a subject and the speaker for extracting speech scenes from news videos.
    Speech scenes in news videos contain a wealth of multimedia information, and are valuable as archived material.
    In order to extract speech scenes from news videos, there is an approach that uses the position and size of a face region.
    However, it is difficult to extract them with only such approach, since news videos contain non-speech scenes where the speaker is not the subject, such as narrated scenes.
    To solve this problem, we propose a method to discriminate between speech scenes and narrated scenes based on the co-occurrence between a subject's lip motion and the speaker's voice.
    The proposed method uses lip shape and degree of lip opening as visual features representing a subject's lip motion, and uses voice volume and phoneme as audio feature representing a speaker's voice.
    Then, the proposed method discriminates between speech scenes and narrated scenes based on the correlations of these features.
    We report the results of experiments on videos captured in a laboratory condition and also on actual broadcast news videos.
    Their results showed the effectiveness of our method and the feasibility of our research goal.

  154. Detection of Repetitive Cooking Motions in a Cooking Video Reviewed

    Taku Kuhara, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Information and Systems   Vol. J94-D ( 12 ) page: 1983 - 1985   2011.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  155. Generation of an In-Vehicle Camera Image Sequence without Temporary Objects by Selection of Partial Images from Multiple Image Sequences Reviewed

    Hiroyuki Uchiyama, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Information and Systems   Vol. J94-D ( 12 ) page: 2093 - 2104   2011.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  156. Scene Segmentation of Wedding Party Videos by Scenario-based Matching with Example Videos Reviewed

    Kazuki Sawai, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of the 19th ACM International Multimedia Conference (ACM-MM2011)     page: 1545 - 1548   2011.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  157. Accurate and Robust Attitude Estimation using MEMS Gyroscopes and a Monocular Camera Reviewed

    Norimasa Kobori, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

    Transactions of the Society of Instrument and Control Engineers   Vol. 47 ( 10 ) page: 442 - 449   2011.10

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  158. Low resolution QR-code recognition by applying super-resolution using the property of QR-codes Reviewed

    Yuji Kato, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

    Proceedings of the 11th International Conference on Document Analysis and Recognition (ICDAR2011)     page: 992 - 996   2011.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper proposes a method for low resolution QR-code recognition. A QR-code is a two-dimensional binary symbol that can embed various information such as characters and numbers. To recognize a QR-code correctly and stably,the resolution of an input image should be high. In practice,however, recognition of a QR-code is usually difficult due to
    low resolution when it is captured from a distance. In this paper, we propose a method to improve the performance of low resolution QR-code recognition by using the super-resolution technique that generates a high resolution image from multiple low-resolution images. Although a QR-code is a binary pattern, it is observed as a grayscale image due to the degradation through the capturing process. Especially the pixels around the borders between white and black regions become ambiguous. To overcome this problem, the proposed method introduces a binary pattern constraint to generate super-resolved images appropriate for recognition. Experimental results showed that a recognition rate of 98% an be achieved by the proposed method, which is a 15.7% improvement in comparison with a method using a conventional super-resolution method.

  159. Power-efficient hardware architecture of K-Means clustering with Bayesian-Information-Criterion processor for multimedia processing applications Reviewed

    Tse-Wei Chen, Chih-Hao Sun, Hsiao-Hang Su, Shao-Yi Chien, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEEE Journal on Emerging and Selected Topics in Circuits and Systems   Vol. 1 ( 3 ) page: 357 - 368   2011.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    A power-efficient K-Means hardware architecture that can automatically estimate the number of clusters in the clustering process is proposed. The contributions of this work include two main aspects. The first is the integration of the hierarchical data sampling in the hardware to accelerate the clustering speed. The second is the development of the Bayesian-Information-Criterion (BIC) Processor" to estimate the number of clusters of K-Means. The architecture of the "BIC Processor" is designed based on the simplification of the BIC computations, and the precision of the logarithm function is also analyzed. The experiments show that the proposed architecture can be employed in different multimedia applications, such as motion segmentation and edge-adaptive noise reduction. Besides, the gate count of the hardware is 51 K with the 90-nm complimentary metal-oxide-semiconductor technology. It is also shown that this work can achieve high efficiency compared with a GPU, and the power consumption scales well with the number of clusters and the number of dimensions. The power consumption ranges between 10.72 and 12.95 mW in different modes when the operating frequency is 233 MHz."

    DOI: 10.1109/JETCAS.2011.2165231

  160. Towards the Creation of a Cooking Recipe for Inexperienced Users by Supplementing Multimedia Information Reviewed

    Yuka Shidochi, Ichiro Ide, Yuichi Nakamura, Daisuke Deguchi, Tomokazu Takahashi, Hiroshi Murase

    IEICE Transactions on Information and Systems   Vol. J94-A ( 7 ) page: 544 - 547   2011.7

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  161. On-road Obstacle Detection by Comparing Present and Past In-vehicle Camera Images Reviewed

    Haruya Kyutoku, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    Proceedings of IAPR Conference on Machine Vision Applications (MVA) 2011     page: 357 - 360   2011.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  162. Estimation of Traffic Sign Visibility Considering Temporal Environmental Changes for Smart Driver Assistance Reviewed

    Keisuke Doman, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase, Yukimasa Tamatsu

    Proceedings of 2011 IEEE Intelligent Vehicles Symposium (IV2011)     page: 667 - 672   2011.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    We propose a visibility estimation method for traffic signs considering temporal environmental changes, as a part of work for the realization of nuisance-free driver assistance systems. Recently, the number of driver assistance systems in a vehicle is increasing. Accordingly, it is becoming important to sort out appropriate information provided from them, because providing too much information may cause driver distraction. To solve such a problem, we focus on a visibility estimation method for controlling the information according to the visibility of a traffic sign. The proposed method sequentially captures a traffic sign by an in-vehicle camera, and estimates its accumulative visibility by integrating a series of instantaneous visibility. By this way, even if the environmental conditions may change temporally and complicatedly, we can still accurately estimate the visibility that the driver perceives in an actual traffic scene. We also investigate the performance of the proposed method and show its effectiveness.

  163. Road Image Update using In-vehicle Camera Images and Aerial Image Reviewed

    Masafumi Noda, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Yoshiko Kojima, Takashi Naito

    Proceedings of 2011 IEEE Intelligent Vehicles Symposium (IV2011)     page: 460 - 465   2011.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Road image is becoming important for several
    applications such as car navigation systems, traffic environment
    research, city modeling. Usually, a road image can be obtained
    from an aerial image but the resolution of the aerial image is
    often low, or it contains occlusions by obstacles. Therefore, the
    update of road image is required. In this paper, we propose a
    road image mosaicing method using in-vehicle camera images
    and an aerial image. We first perform image registration of road
    regions between these images, and then, we generate a large road
    image by performing image mosaicing of road regions in invehicle
    camera images. In an experiment, we achieved resolution
    improvement and occlusions removal, and also succeeded in
    update of a large road image.

  164. 3-D Line Segment Reconstruction Using an In-Vehicle Camera for Free Space Detection Reviewed

    Hiroyuki Uchiyama, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

    Proceedings of 2011 IEEE Intelligent Vehicles Symposium (IV2011)     page: 290 - 295   2011.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Free space detection is very important for vehicle navigation and safe driving. 3-D line segment reconstruction
    of a street is important for the free space detection because a street-view includes many line segments. For the free space
    detection, we propose a method for reconstructing 3-D line segments in a streetscape using a monocular in-vehicle camera.
    The 3-D reconstruction of the line segments is achieved by using each three images from an image sequence. Once accurate
    camera poses of these images are obtained, one of the remaining crucial problems is to match the line segments between the
    images correctly. A strategy for finding correspondence of the line segments is as follows: First, the correspondences of line
    segment candidates are searched by using a two-view constraint. However, the two-view constraint has difficulty on determining
    an unique correspondence geometrically. Therefore, the candidates of the line segment correspondences are reduced using
    a three-view constraint. In order to improve the accuracy, the proposed method exploits a color feature of the line segment
    and a preliminary knowledge of the vehicle motion. Finally, the line segments are reconstructed using the correspondences.
    From an experimental result, we confirmed the effectiveness of the proposed method. Application to the free space detection
    demonstrated the usefulness of the reconstructed line segments.

  165. Intelligent Traffic Sign Detector: Adaptive Learning Based on Online Gathering of Training Samples Reviewed

    Daisuke Deguchi, Mitsunori Shirasuna, Keisuke Doman, Ichiro Ide, Hiroshi Murase

    Proceedings of 2011 IEEE Intelligent Vehicles Symposium (IV2011)     page: 72 - 77   2011.6

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper proposes an intelligent traffic sign detector using adaptive learning based on online gathering of training samples from in-vehicle camera image sequences. To detect traffic signs accurately from in-vehicle camera images, various training samples of traffic signs are needed. In addition, to reduce false alarms, various background images should also be prepared before constructing the detector. However, since their appearances vary widely, it is difficult to obtain them exhaustively by manual intervention. Therefore, the proposed method simultaneously obtains both traffic sign images and background images from in-vehicle camera images. Especially, to reduce false alarms, the proposed method gathers background images that were easily mis-detected by a previously constructed traffic sign detector, and re-trains the detector by using them as negative samples. By using retrospectively tracked traffic sign images and background images as positive and negative training samples, respectively, the proposed method constructs a highly accurate traffic sign detector automatically. Experimental results showed the effectiveness of the proposed method.

  166. Detection of Road Markings Recorded in In-Vehicle Camera Images by Using Position-Dependent Classifiers Reviewed

    Masafumi Noda, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Yoshiko Kojima, Takashi Naito

    IEEJ Transactions on Industry Applications   Vol. 131 ( 4 ) page: 466 - 474   2011.4

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.1541/ieejias.131.466

  167. Accurate and Robust Attitude Estimation of a Moving Vehicle Using MEMS Gyroscopes and a Monocular Camera Reviewed

    Norimasa Kobori, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

    Proceedings of 2010 Workshop on Picture Coding and Image Processing (WPCIP 2010)     2010.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    In order to estimate accurate attitude of mobile robots and vehicles, we propose a hybrid system which combines a lowcost monocular camera with a gyro sensor. A gyro sensor has drift errors that accumulate over time. On the other hand, a camera cannot obtain the rotation continuously in the case where feature points cannot be extracted from images, although the accuracy is better than a gyro sensor. To solve these problems, we propose a method for combining these sensors based on an Extended Kalman Filter.

  168. Ego-Localization by Spatio-Temporal Matching between Videos Obtained from Cameras with Different Viewing Angles Using an Extended DTW Method Reviewed

    Hiroyuki Uchiyama, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Information and Systems   Vol. J93-D ( 12 ) page: 2659 - 2665   2010.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  169. Multimedia supplementation to a cooking recipe text for facilitating its understanding to inexperienced users Reviewed

    Ichiro Ide, Yuka Shidochi, Yuichi Nakamura, Daisuke Deguchi, Tomokazu Takahashi, Hiroshi Murase

    Proceedings of the 2nd Workshop on Cooking and Eating Activities (CEA2010)     page: 242 - 247   2010.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  170. Frontal Face Generation from Multiple Low-Resolution Non-Frontal Faces for Face Recognition Reviewed

    Yuki Kono, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of the 10th International Workshop on Visual Surveillance 2010     2010.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  171. Improvement of a traffic sign detector by retrospective gathering of training samples from in-vehicle camera image sequences Reviewed

    Daisuke Deguchi, Keisuke Doman, Ichiro Ide, Hiroshi Murase

    Proceedings of Computer Vision in Vehicle Technology: From Earth to Mars (CVVT2010)     2010.11

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

  172. Vehicle Ego-localization by Matching In-vehicle Camera Images to an Aerial Image Reviewed

    Masafumi Noda, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Yoshiko Kojima, Takashi Naito

    Proceedings of Computer Vision in Vehicle Technology: From Earth to Mars (CVVT2010)     2010.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  173. Marker-Free Registration for Electromagnetic Navigation Bronchoscopy under Respiratory Motion

    Marco Feuerstein, Takamasa Sugiura, Daisuke Deguchi, Tobias Reichl, Takayuki Kitasaka, Kensaku Mori

    Proceedings of the 5th International Workshop on Medical Imaging and Augmented Reality (MIAR2010)   Vol. LNCS 6326   page: 237 - 246   2010.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  174. Construction of a traffic sign detector using generative learning method considering color variation Reviewed

    Keisuke Doman, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    IEICE Transactions on Information and Systems   Vol. J93-D ( 8 ) page: 1375 - 1385   2010.8

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  175. Removal of Moving Objects from a Street-View Image by Fusing Multiple Image Sequences Reviewed

    Hiroyuki Uchiyama, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

    Proceedings of the 20th IAPR International Conference on Pattern Recognition (ICPR2010)     page: 3456 - 3459   2010.8

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ICPR.2010.844

  176. Classification of near-duplicate video segments based on their appearance patterns Reviewed

    Ichiro Ide, Yuji Shamoto, Daisuke Deguchi, Tomokazu Takahashi, Hiroshi Murase

    Proceedings of the 20th IAPR International Conference on Pattern Recognition (ICPR2010)     page: 3129 - 3133   2010.8

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ICPR.2010.766

  177. Estimation of Traffic Sign Visibility Toward Smart Driver Assistance Reviewed

    Keisuke Doman, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase, Yukimasa Tamatsu

    Proceedings of 2010 IEEE Intelligent Vehicles Symposium (IV2010)     page: 45 - 50   2010.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/IVS.2010.5548137

  178. Construction of cascaded traffic sign detector using generative learning Reviewed

    Keisuke Doman, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    Proceedings of the 4th International Conference on Innovative Computing, Information and Control (ICICIC2009)     2009.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  179. Labeling News Topic Threads with Wikipedia Entries Reviewed

    Tomoki Okuoka, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Proceedings of the 1st International Workshop on Content-Based Audio/Video Analysis for Novel TV Services (CBTV2009)     page: 501 - 504   2009.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ISM.2009.67

  180. Automated Anatomical Labeling of Bronchial Branches Extracted from CT Datasets Based on Machine Learning and Combination Optimization and Its Application to Bronchoscope Guidance Reviewed

    Kensaku Mori, Shunsuke Ota, Daisuke Deguchi, Takayuki Kitasaka, Yasuhito Suenaga, Shingo Iwano, Yoshinori Hasegawa, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI2009)   Vol. LNCS 5762, Part II   page: 707 - 714   2009.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    This paper presents a method for the automated anatomical labeling of bronchial branches extracted from 3D CT images based on machine learning and combination optimization. We also show applications of anatomical labeling on a bronchoscopy guidance system. This paper performs automated labeling by using machine learning and combination optimization. The actual procedure consists of four steps: (a) extraction of tree structures of the bronchus regions extracted from CT images, (b) construction of AdaBoost classifiers, (c) computation of candidate names for all branches by using the classifiers, (d) selection of best combination of anatomical names. We applied the proposed method to 90 cases of 3D CT datasets. The experimental results showed that the proposed method can assign correct anatomical names to 86.9% of the bronchial branches up to the sub-segmental lobe branches. Also, we overlaid the anatomical names of bronchial branches on real bronchoscopic views to guide real bronchoscopy.

    DOI: 10.1007/978-3-642-04271-3_86

  181. Low-resolution Character Recognition by Video-based Super-resolution Reviewed

    大倉 直, 出口 大輔, 高橋 友和, 井手 一郎, 村瀬 洋

    Proceedings of the 10th International Conference on Document Analysis and Recognition (ICDAR2009)     page: 191 - 195   2009.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/ICDAR.2009.168

  182. Selective image similarity measure for bronchoscope tracking based on image registration Reviewed

    Daisuke Deguchi, Kensaku Mori, Marco Feuerstein, Takayuki Kitasaka, Calvin R. Maurer Jr., Yasuhito Suenaga, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Medical Image Analysis   Vol. 13 ( 4 ) page: 621 - 633   2009.6

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (scientific journal)  

    We propose a selective method of measurement for computing image similarities based on characteristic structure extraction and demonstrate its application to flexible endoscope navigation, in particular to a bronchoscope navigation system. Camera motion tracking is a fundamental function required for image-guided treatment or therapy systems. In recent years, an ultra-tiny electromagnetic sensor commercially became available, and many image-guided treatment or therapy systems use this sensor for tracking the camera position and orientation. However, due to space limitations, it is difficult to equip the tip of a bronchoscope with such a position sensor, especially in the case of ultra-thin bronchoscopes. Therefore, continuous image registration between real and virtual bronchoscopic images becomes an efficient tool for tracking the bronchoscope. Usually, image registration is done by calculating the image similarity between real and virtual bronchoscopic images. Since global schemes to measure image similarity, such as mutual information, squared gray-level difference, or cross correlation, average differences in intensity values over an entire region, they fail at tracking of scenes where less characteristic structures can be observed. The proposed method divides an entire image into a set of small subblocks and only selects those in which characteristic shapes are observed. Then image similarity is calculated within the selected subblocks. Selection is done by calculating feature values within each subblock. We applied our proposed method to eight pairs of chest X-ray CT images and bronchoscopic video images. The experimental results revealed that bronchoscope tracking using the proposed method could track up to 1600 consecutive bronchoscopic images (about 50s) without external position sensors. Tracking performance was greatly improved in comparison with a standard method utilizing squared gray-level differences of the entire images.

    DOI: 10.1016/j.media.2009.06.001

  183. An improved method for automated recognition of bronchial tree structure by optimizing combinations of candidate anatomical names Reviewed

    Takayuki Kitasaka, Shunsuke Ota, Daisuke Deguchi, Kensaku Mori, Yasuhito Suenaga, Yoshinori Hasegawa, Kazuyoshi Imaizumi, Shingo Iwano, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    International Journal of Computer Assisted Radiology and Surgery   Vol. 4   page: 327 - 328   2009.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  184. Ego-localization using Streetscape Image Sequences from In-vehicle Cameras Reviewed

    Hiroyuki Uchiyama, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

    Proceedings of 2009 IEEE Intelligent Vehicles Symposium (IV2009)     page: 185 - 190   2009.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/IVS.2009.5164275

  185. Automatic Calibration of an In-vehicle Gaze Tracking System Using Driver's Typical Gaze Behavior Reviewed

    Kenji Yamashiro, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase, Kazunori Higuchi, Takashi Naito

    Proceedings of 2009 IEEE Intelligent Vehicles Symposium (IV2009)     page: 998 - 1003   2009.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1109/IVS.2009.5164417

  186. Recognition of Road Markings from In-Vehicle Camera Images by a Generative Learning Method Reviewed

    Masafumi Noda, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Yoshiko Kojima, Takashi Naito

    Proceedings of IAPR Conference on Machine Vision Applications (MVA) 2009     page: 514 - 517   2009.5

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  187. A method for accelerating bronchoscope tracking based on image registration by using GPU Reviewed

    Takamasa Sugiura, Daisuke Deguchi, Marco Feuerstein, Takayuki Kitasaka, Yasuhito Suenaga, Kensaku Mori

    Proceedings of SPIE Medical Imaging 2009   Vol. 7261   page: 726108 - 1   2009.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  188. Automatic mediastinal lymph node detection in chest CT Reviewed

    Marco Feuerstein, Daisuke Deguchi, Takayuki Kitasaka, Shingo Iwano, Kazuyoshi Imaizumi, Yoshinori Hasegawa, Yasuhito Suenaga, Kensaku Mori

    Proceedings of SPIE Medical Imaging 2009   Vol. 7260   page: 1 - 11   2009.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  189. Development of a Common Platform for Computer-Aided Diagnosis of Medical Images Reviewed

    Yukitaka Nimura, Daisuke Deguchi, Takayuki Kitasaka, Yasuhito Suenaga, Kensaku Mori

    Medical Imaging Technology   Vol. 26 ( 5 ) page: 327 - 337   2008.11

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  190. PLUTO: A Common CAD Platform for Multiorgan Multidisease CAD (MoMd-CAD) Reviewed

    Yukitaka Nimura, Daisuke Deguchi, Takayuki Kitasaka, Kensaku Mori, Yasuhito Suenaga

    RSNA (Radiological Society of North America) Scientific Assembly and Annual Meeting Program 2008     page: 904   2008.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  191. A Method for Accelerating Bronchoscope Tracking Based on Image Registration by GPGPU Reviewed

    Takamasa Sugiura, Daisuke Deguchi, Takayuki Kitasaka, Kensaku Mori, Yasuhito Suenaga

    Proceedings of International Workshop on Augmented environments for Medical Imaging and Computer-aided Surgery (AMI-ARCS) 2008     page: 130 - 139   2008.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  192. Improvement of Accuracy of Marker-Free Bronchoscope Tracking Using Electromagnetic Tracker Based on Bronchial Branch Information Reviewed

    Kensaku Mori, Daisuke Deguchi, Takayuki Kitasaka, Yasuhito Suenaga, Yoshinori Hasegawa, Kazuyoshi Imaizumi, Hirotsugu Takabatake

    Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI2008)   Vol. LNCS 5242, Part II   page: 535 - 542   2008.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  193. Augmented display of anatomical names of bronchial branches for bronchoscopy assistance Reviewed

    Shunsuke Ota, Daisuke Deguchi, Takayuki Kitasaka, Kensaku Mori, Yasuhito Suenaga, Yoshinori Hasegawa, Kazuyoshi Imaizumi, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of the 4th International Workshop on Medical Imaging and Augmented Reality (MIAR2008)   Vol. LNCS 5128   page: 377 - 384   2008.8

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  194. An improved method for bronchoscope tracking using an electromagnetic tracker without fiducial markers Reviewed

    Daisuke Deguchi, Kazuyoshi Ishitani, Takayuki Kitasaka, Kensaku Mori, Yasuhito Suenaga, Yoshinori Hasegawa, Kazuyoshi Imaizumi

    Proceedings of the 22st International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS2008)   Vol. 3   page: S301   2008.6

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

  195. Automated anatomical labeling of bronchaial branches using multiple classifiers and its application to bronchoscopy guidance Reviewed

    Shunsuke Ota, Daisuke Deguchi, Takayuki Kitasaka, Kensaku Mori, Yasuhito Suenaga, Yoshinori Hasegawa, Kazuyoshi Imaizumi, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of the 22st International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS2008)   Vol. 3   page: S269   2008.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  196. Fiducial-free bronchoscope tracking using ultra-tiny electromagnetic tracker based on non-rigid transformation technique Reviewed

    Kensaku Mori, Kazuyoshi Ishitani, Daisuke Deguchi, Takayuki Kitasaka, Yasuhito Suenaga, Yoshinori Hasegawa, Kazuyoshi Imaizumi

    Proceedings of the 22st International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS2008)   Vol. 3   page: S105   2008.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  197. Automated anatomical labeling of bronchial branches using multiple classifiers and its application to bronchoscopy guidance based on fusion of virtual and real bronchoscopy Reviewed

    Shunsuke Ota, Daisuke Deguchi, Takayuki Kitasaka, Kensaku Mori, Yasuhito Suenaga, Yoshinori Hasegawa, Kazuyoshi Imaizumi, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of SPIE Medical Imaging 2008   Vol. 6916   page: 1 - 12   2008.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  198. Bronchoscope Tracking Without Fiducial Markers Using Ultra-tiny Electromagnetic Tracking System and Its Evaluation in Different Environments Reviewed

    Kensaku Mori, Daisuke Deguchi, Kazuyoshi Ishitani, Takayuki Kitasaka, Yasuhito Suenaga, Yoshinori Hasegawa, Kazuyoshi Imaizumi, Hirotsugu Takabatake

    Proceedings of the 10th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2007)   Vol. LNCS 4792, Part II   page: 644 - 651   2007.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  199. A method for bronchoscope tracking using position sensor without fiducial markers Reviewed

    Daisuke Deguchi, Kazuyoshi Ishitani, Takayuki Kitasaka, Kensaku Mori, Yasuhito Suenaga, Yoshinori Hasegawa, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of the 21st International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS2007)   Vol. 2   page: S11-S13   2007.6

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

  200. A method for bronchoscope tracking using position sensor without fiducial markers Reviewed

    Daisuke Deguchi, Kazuyoshi Ishitani, Takayuki Kitasaka, Kensaku Mori, Yasuhito Suenaga, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of SPIE Medical Imaging 2007   Vol. 6511   page: 1 - 0   2007.2

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

  201. Easy and stable bronchoscope camera calibration technique for bronchoscope navigation system Reviewed

    Kazuyoshi Ishitani, Daisuke Deguchi, Takayuki Kitasaka, Kensaku Mori, Yasuhito Suenaga, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of SPIE Medical Imaging 2007   Vol. 6509   page: 1 - 1   2007.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  202. Compensation of Electromagnetic trackintg system using an optical tracker and its application to bronchoscopy navigation system Reviewed

    Kensaku Mori, Kazuyoshi Ishitani, Daisuke Deguchi, Takayuki Kitasaka, Yasuhito Suenaga, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of SPIE Medical Imaging 2007   Vol. 6509   page: 1 - 0   2007.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  203. Evaluation of a prostate biopsy strategy for cancer detection using a computer simulation system with virtual needle biopsy for three-dimensional prostate models Reviewed

    Masanori Noguchi, Daisuke Deguchi, Junichiro Toriwaki, Kensaku Mori, Yoshito Mekada, Kei Matsuoka

    International Journal of Urology   Vol. 13 ( 10 ) page: 1296 - 1303   2006.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    AIM:We evaluated a prostate biopsy strategy for cancer detection using a computer simulation system with virtual needle biopsy for three-dimensional (3D) prostate models.
    METHODS:Two 3D prostate models with a volume of 25 cc or 50 cc were constructed from computed tomographic images of radical prostatectomy specimens. The peripheral zone (PZ) and transition zone (TZ) were arranged in the prostate models according to the anatomical information. Four thousand patterns of cancer lesions were automatically inserted into each prostate model with a proportion of 75% in PZ and 25% in TZ. Average hit rates (AHR) in prostate models were evaluated both with an increased number of biopsy cores and various angles of virtual needle biopsy. The influence of adding secondary tumors for hit rates was also evaluated.
    RESULTS:For both sizes, the laterally angled biopsy in 4-8 core biopsy schemes showed higher AHR than the vertical plane biopsy, while the vertical plane biopsy in 10-18 core biopsy schemes showed higher AHR than the laterally angled biopsy. A higher number of biopsy cores increased the AHR of secondary tumors.
    CONCLUSIONS:Our results suggest that it is important in prostate cancer detection to change the needle placement according to the number of biopsy cores and the size of the prostate.

    DOI: 10.1111/j.1442-2042.2006.01561.x

  204. A preliminary study on introduction of a magnetic tracking sensor for bronchoscope navigation system Reviewed

    Kazuyoshi Ishitani, Daisuke Deguchi, Takayuki Kitasaka, Kensaku Mori, Yasuhito Suenaga, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of International Workshop on Augmented environments for Medical Imaging and Computer-aided Surgery (AMI-ARCS) 2006     2006.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  205. Bronchoscope Tracking Based on Image Registration Using Multiple Initial Starting Points Estimated by Motion Prediction Reviewed

    Kensaku Mori, Daisuke Deguchi, Takayuki Kitasaka, Yasuhito Suenaga, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori, Calvin R. Maurer Jr.

    Proceedings of the 9th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2006)   Vol. LNCS 4191, Part II   page: 645 - 652   2006.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  206. Detection of liver cancer regions from dynamic CT images Reviewed

    Yuichiro Hayashi, Daisuke Deguchi, Takayuki Kitasaka, Kensaku Mori, Yoshito Mekada, Yasuhito Suenaga

    Proceedings of the 20th International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS2006)   Vol. 1   page: 524 - 525   2006.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  207. Image-based bronchoscope tracking using motion predication and multiple searches Reviewed

    Kensaku Mori, Daisuke Deguchi, Takayuki Kitasaka, Yasuhito Suenaga, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of the 20th International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS2006)   Vol. 1   page: 178 - 181   2006.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  208. A method for bronchoscope tracking by combining a position sensor and image registration Reviewed

    Daisuke Deguchi, Kenta Akiyama, Kensaku Mori, Takayuki Kitasaka, Yasuhito Suenaga, Calvin R. Maurer Jr., Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Computer Aided Surgery   Vol. 11 ( 3 ) page: 109 - 117   2006.5

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (scientific journal)  

    This paper describes a method for tracking a bronchoscope by combining a position sensor and image registration. A bronchoscopy guidance system is a tool for providing real-time navigation information acquired from pre-operative CT images to a physician during a bronchoscopic examination. In this system, one of the fundamental functions is tracking a bronchoscope's camera motion. Recently, a very small electromagnetic position sensor has become available. It is possible to insert this sensor into a bronchoscope's working channel to obtain the bronchoscope's camera motion. However, the accuracy of its output is inadequate for bronchoscope tracking. The proposed combination of the sensor and image registration between real and virtual bronchoscopic images derived from CT images is quite useful for improving tracking accuracy. Furthermore, this combination has enabled us to achieve a real-time bronchoscope guidance system. We performed evaluation experiments for the proposed method using a rubber phantom model. The experimental results showed that the proposed system allowed the bronchoscope's camera motion to be tracked at 2.5 frames per second.

  209. Branch identification method for CT-guided bronchoscopy based on eigenspace image matching between real and virtual bronchoscopic images Reviewed

    Riyoko Shinohara, Kensaku Mori, Daisuke Deguchi, Takayuki Kitasaka, Yasuhito Suenaga, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of SPIE Medical Imaging 2006   Vol. 6143   page: 14 - 1   2006.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  210. A method for automated liver region extraction basing upon estimation of CT value distributions from multi-phase CT images Reviewed

    Daisuke Deguchi, Yuichiro Hayashi, Takayuki Kitasaka, Kensaku Mori, Yoshito Mekada, Yasuhito Suenaga, Jun-ichi Hasegawa, Junichiro Toriwaki

    Journal of Computer Aided Diagnosis of Medical Images   Vol. 9 ( 4 ) page: 36 - 48   2006.1

     More details

    Authorship:Lead author   Language:Japanese   Publishing type:Research paper (scientific journal)  

  211. Development of a Virtual Needle Biopsy Simulation System for the Virtual Prostate Reviewed

    Daisuke Deguchi, Kensaku Mori, Yoshito Mekada, Jun-ichi Hasegawa, Junichiro Toriwaki, Masanori Noguchi

    Systems and Computers in Japan   Vol. 37 ( 1 ) page: 93 - 104   2006.1

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (scientific journal)  

    This paper discusses the virtual prostate needle biopsy system and the construction of the virtual prostate model, considering the actual distribution of prostate abnormalities. A needle biopsy simulation is performed for the constructed virtual prostate, and the actual biopsy procedure in the clinical situation is evaluated. The prostate needle biopsy is a histologic diagnosis procedure in which a sample is acquired from the prostate tissue by needle biopsy and is inspected under a microscope. In order to achieve reliable prostate needle biopsy, it is necessary to consider systematically and numerically the number of needles required, and their locations and insertion angles.
    For such a purpose, a system is developed in which a virtual prostate is constructed on a computer and the biopsy procedure is evaluated quantitatively by performing virtually the prostate needle biopsy. Furthermore, two different models are constructed, for the prostate with and without hypertrophy, based on the actual statistical distribution data for
    prostate abnormalities. Each model is partitioned into the peripheral zone and the transition zone. The constructed
    virtual prostate is input into the virtual needle biopsy simulation system, and three different systematic biopsy procedures actually used at clinical sites, and four different needle biopsy procedures, are experimentally evaluated.
    The experiments show that the insertion angle that maximizes the hit probability is not always the same as the
    insertion angle that maximizes cancer sample acquisition. It is evident that the proposed method can indicate a biopsy
    procedure which realizes a high hit probability with a small number of needles.

    DOI: 10.1002/scj.20181

  212. Hybrid Bronchoscope Tracking Using a Magnetic Tracking Sensor and Image Registration Reviewed

    Kensaku Mori, Daisuke Deguchi, Kenta Akiyama, Takayuki Kitasaka, Calvin R. Maurer Jr., Yasuhito Suenaga, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of the 8th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2005)   Vol. LNCS 3750, Part II   page: 543 - 550   2005.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  213. A method for bronchoscope tracking by combining a position sensor and image registration Reviewed

    Daisuke Deguchi, Kenta Akiyama, Takayuki Kitasaka, Kensaku Mori, Yasuhito Suenaga, Jun-ichi Hasegawa, Junichiro Toriwaki, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori

    Proceedings of the 19th International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS2005)   Vol. 1281   page: 630 - 635   2005.6

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1016/j.ics.2005.03.282

  214. Development of a method for automated liver region extraction from contrasted 3D abdominal X-ray CT images Reviewed

    Yuichiro Hayashi, Daisuke Deguchi, Kensaku Mori, Yoshito Mekada, Yasuhito Suenaga, Junichiro Toriwaki

    Journal of Computer Aided Diagnosis of Medical Images   Vol. 8 ( 1_3 ) page: 18 - 30   2004.11

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

  215. Fast and Accurate Bronchoscope Tracking using Image Registration and Motion Prediction Reviewed

    Jiro Nagao, Kensaku Mori, Tsutomu Enjoji, Daisuke Deguchi, Takayuki Kitasaka, Yasuhito Suenaga, Jun-ichi Hasegawa, Junichiro Toriwaki, Hirotsugu Takabatake, Hiroshi Natori

    Proceedings of the 7th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2004)   Vol. LNCS 3217, Part II   page: 551 - 558   2004.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  216. Improved camera-tracking method by combining motion prediction and image registration for bronchoscope navigation system Reviewed

    Kensaku Mori, Tsutomu Enjoji, Daisuke Deguchi, Takayuki Kitasaka, Yasuhito Suenaga, Junichiro Toriwaki, Hiroshi Natori, Hirotsugu Takabatake

    Proceedings of the 18th International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS2004)   Vol. 1268   page: 1261   2004.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  217. New image similarity measures for bronchoscope tracking based on image registration between virtual and real bronchoscopic images Reviewed

    Kensaku Mori, Tsutomu Enjoji, Daisuke Deguchi, Takayuki Kitasaka, Yasuhito Suenaga, Junichiro Toriwaki, Hirotsugu Takabatake, Hiroshi Natori

    Proceedings of SPIE Medical Imaging 2004   Vol. 5639   page: 165 - 176   2004.2

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  218. Development of a simulation system of the virtual needle biopsy for the virtual prostate Reviewed

    Daisuke Deguchi, Kensaku Mori, Yoshito Mekada, Jun-ichi Hasegawa, Junichiro Toriwaki, Masanori Noguchi

    IEICE Transactions on Information and Systems   Vol. J87-D-II ( 1 ) page: 281 - 289   2004.1

     More details

    Authorship:Lead author   Language:Japanese   Publishing type:Research paper (scientific journal)  

  219. New Image Similarity Measure for Bronchoscope Tracking Based on Image Registration Reviewed

    Daisuke Deguchi, Kensaku Mori, Yasuhito Suenaga, Jun-ichi Hasegawa, Junichiro Toriwaki, Hirotsugu Takabatake, Hiroshi Natori

    Proceedings of the 6th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2003)   Vol. LNCS 2878   page: 399 - 406   2003.11

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.1007/978-3-540-39899-8_50

  220. New calculation method of image similarity for endoscope tracking based on image registration in endoscope navigation Reviewed

    Daisuke Deguchi, Kensaku Mori, Yasuhito Suenaga, Jun-ichi Hasegawa, Junichiro Toriwaki, Hiroshi Natori, Hirotsugu Takabatake

    Proceedings of the 17th International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS2003)   Vol. 1256   page: 460 - 466   2003.6

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

  221. Tracking of a bronchoscope using epipolar geometry analysis and intensity-based image registration of real and virtual endoscopic images Reviewed

    Kensaku Mori, Daisuke Deguchi, Jun Sugiyama, Yasuhito Suenaga, Junichiro Toriwaki, Calvin R. Maurer Jr., Hirotsugu Takabatake, Hiroshi Natori

    Medical Image Analysis   Vol. 6   page: 321 - 336   2002.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    This paper describes a method for tracking the camera motion of a flexible endoscope, in particular a bronchoscope, using epipolar geometry analysis and intensity-based image registration. The method proposed here does not use a positional sensor attached to the endoscope. Instead, it tracks camera motion using real endoscopic (RE) video images obtained at the time of the procedure and X-ray CT images acquired before the endoscopic examination. A virtual endoscope system (VES) is used for generating virtual endoscopic (VE) images. The basic idea of this tracking method is to find the viewpoint and view direction of the VES that maximizes a similarity measure between the VE and RE images. To assist the parameter search process, camera motion is also computed directly from epipolar geometry analysis of the RE video images. The complete method consists of two steps: (a) rough estimation using epipolar geometry analysis and (b) precise estimation using intensity-based image registration. In the rough registration process, the method computes camera motion from optical flow patterns between two consecutive RE video image frames using epipolar geometry analysis. In the image registration stage, we search for the VES viewing parameters that generate the VE image that is most similar to the current RE image. The correlation coefficient and the mean square intensity difference are used for measuring image similarity. The result obtained in the rough estimation process is used for restricting the parameter search area. We applied the method to bronchoscopic video image data from three patients who had chest CT images. The method successfully tracked camera motion for about 600 consecutive frames in the best case. Visual inspection suggests that the tracking is sufficiently accurate for clinical use. Tracking results obtained by performing the method without the epipolar geometry analysis step were substantially worse. Although the method required about 20 s to process one frame, the results demonstrate the potential of image-based tracking for use in an endoscope navigation system.

    DOI: 10.1016/S1361-8415(02)00089-0

  222. Camera motion tracking of real bronchoscope using epipolar geometry analysis and CT derived bronchoscopic images Reviewed

    Daisuke Deguchi, Kensaku Mori, Jun-ichi Hasegawa, Junichiro Toriwaki, Hirotsugu Takabatake, Hiroshi Natori

    Proceedings of SPIE Medical Imaging 2002   Vol. 4683   page: 30 - 41   2002.2

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

  223. A method for tracking the camera motion of real endoscope by epipolar geometry analysis and virtual endoscopy system Reviewed

    Kensaku Mori, Daisuke Deguchi, Jun-ichi Hasegawa, Yasuhito Suenaga, Junichiro Toriwaki, Hirotsugu Takabatake, Hiroshi Natori

    Proceedings of the 4th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2001   Vol. LNCS 2208   page: 1 - 8   2001.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

▼display all

Books 3

  1. モビリティイノベーションシリーズ⑤ 自動運転

    村瀬 洋, 出口 大輔, 新村 文郷, 平山 高嗣, 川西 康友, 久徳 遙矢, 他( Role: Joint author ,  4章 認知:外界センサによる草稿環境認識)

    オーム社  2021.1 

     More details

    Language:Japanese

  2. 統計的学習の基礎 -データマイニング・推論・予測-

    杉山将, 井手剛, 神嶌敏弘, 栗田 多喜夫, 前田 英作, 他( Role: Joint translator)

    共立出版  2014.6 

     More details

    Language:Japanese

  3. 医用画像解析ハンドブック

    藤田広志, 石田隆行, 桂川茂彦, 他( Role: Joint author)

    オーム社  2012.11 

     More details

    Language:Japanese

MISC 12

  1. 車載カメラを用いた周囲環境認識技術

    出口 大輔

    車載テクノロジー   Vol. 6 ( 8 ) page: 9 - 9   2019.5

     More details

    Language:Japanese  

  2. Driving Intelligence for Automated Vehicles and Future Perspective

    Tatsuya Suzuki, Naoki Akai, Daisuke Deguchi

      Vol. 34 ( 2 ) page: 206 - 206   2019.3

     More details

    Language:Japanese  

  3. Action recognition based on the temporal patterns of gaze information -Recognition of cooking operations based on gaze transition and blinks-

    Ichiro Ide, Takatsugu Hirayama, Hiroya Inoue, Keisuke Doman, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

      Vol. 29 ( 6 ) page: 14 - 14   2018.6

     More details

    Language:Japanese  

  4. Environment Understanding Based on Deep Learning

    Daisuke Deguchi, Yasutomo Kawanishi, Hiroshi Murase

    Japanese Journal of Optics   Vol. 47 ( 3 ) page: 106 - 106   2018.3

     More details

    Language:Japanese  

  5. A study on detection of the type of a baggage utilizing multiple-viewpoints human images

    Yasutomo Kawanishi, Yasuhiro Asai, Kento Nishibori, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomokazu Takahashi

      Vol. 27 ( 3 ) page: 19 - 19   2016.3

     More details

    Language:Japanese  

  6. 空間的な人数分布推定のための記憶型回帰

    田渕 義宗, 出口 大輔, 井手 一郎, 村瀬 洋, 高橋 友和, 黒住 隆行, 柏野 邦夫

    画像ラボ   Vol. 25 ( 12 ) page: 55 - 55   2014.12

     More details

    Language:Japanese  

    カメラを用いた群集解析は公共の安全やマーケテイングなどに需要がある。我々は群集解析の中でも、小領域毎の人数を求める空間的な人数分布推定の実現を目指している。 しかし、カメラから離れた場所では人物閣の遮蔽が発生するため、空間的な人数分布を正しく推定することは困難である。そこで本稿では、複数視点、のカメラから撮影された画像を用いて記憶型回帰により人数分布を推定する手法を紹介する。本手法は、人数分布と群集の見えの対応表を用いるものであり、予め群集の見えに遮蔽が含まれているため、遮蔽に頑健な人数分布推定手法が実現される。

  7. 空撮画像と車載カメラ画像の対応付けによる自車位置推定

    野田 雅文, 高橋 友和, 出口 大輔, 井手 一郎, 村瀬 洋, 小島 祥子, 内藤 貴志

    O plus E   Vol. 34 ( 6 ) page: 522 - 522   2012.6

     More details

    Language:Japanese  

    本稿では、空撮画像と車載カメラ画像の対応付けにより自車の位置を推定する手法について述べた.提案手法は、複数時刻の車載カメラ画像を利用することで、自車位置の推定性能の向上を図ったものである.実験により、推定性能の向上を確認し、提案手法の有効性を確認する.

  8. Image Recognition and GPU

    Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

      Vol. 28 ( 3 ) page: 28 - 28   2010.4

     More details

    Language:Japanese  

  9. PLUTO: 医用画像診断支援共通プラットフォーム

    二村 幸孝, 出口 大輔, 北坂 孝幸, 森 健策, 末永 康仁

    Medical Imaging Technology   Vol. 26 ( 3 ) page: 187 - 187   2008.5

     More details

    Language:Japanese  

  10. CAD最前線2007 III 統合化システム 多臓器・多疾病医用画像診断支援システム「PLUTO」

    二村 幸孝, 出口 大輔, 北坂 孝幸, 森 健策

    INNERVISIONインナービション   Vol. 22 ( 12 ) page: 45 - 45   2007.12

     More details

    Language:Japanese  

  11. 学会参加だより「MICCAI2006」

    出口 大輔

    CADM News Letter   ( 49 ) page: 14 - 14   2007.1

     More details

    Language:Japanese  

  12. 学会参加だより MICCAI2006

    出口 大輔

    Medical Imaging Technology   Vol. 24 ( 5 ) page: 433 - 433   2006.11

     More details

    Language:Japanese  

▼display all

Presentations 667

  1. 人物姿勢と注視対象配置制約を使用した後ろ向き人物の注視領域推定

    弓矢 隼大, 出口 大輔, 川西 康友, 村瀬 洋

    情報処理学会全国大会 第84回  2022.3.5 

     More details

    Event date: 2022

    Language:Japanese   Presentation type:Oral presentation (general)  

  2. Active Learning for Human Pose Estimation based on Temporal Pose Continuity International conference

    Taro Mori, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Tetsuo Inoshita

    International Workshop on Advanced Image Technology (IWAIT) 2022  2022.1.6 

     More details

    Event date: 2022

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Hybrid (The Hong Kong Polytechnic University and online)  

  3. A Preliminary Study on 4D Scene Modeling from Live-action Video Including Pedestrians

    田中 来樹, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

    IEICE General Conference  2021.3.12 

     More details

    Event date: 2021

    Language:Japanese   Presentation type:Oral presentation (general)  

  4. LFIR2Pose: Pose Estimation from an Extremely Low-Resolution FIR Image Sequence International conference

    Saki Iwata, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa

    25th International Conference on Pattern Recognition  2021.1.13 

     More details

    Event date: 2021

    Language:English   Presentation type:Poster presentation  

    Venue:Milan, Italy (Virtual)  

    In this paper, we propose a method for human pose estimation from a Low-resolution Far-InfraRed (LFIR) image sequence captured by a 16 × 16 FIR sensor array. Human body estimation from such a single LFIR image is a hard task. For training the estimation model, annotation of the human pose to the images is also a difficult task for human. Thus, we propose the LFIR2Pose model which accepts a sequence of LFIR images and outputs the human pose of the last frame, and also propose an automatic annotation system for the model training. Additionally, considering that the scale of human body motion is largely different among body parts, we also propose a loss function focusing on the difference. Through an experiment, we evaluated the human pose estimation accuracy using an original data set, and confirmed that human pose can be estimated accurately from an LFIR image sequence.

  5. Median-Shape Representation Learning for Category-Level Object Pose Estimation in Cluttered Environments International conference

    Hiroki Tatemichi, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Ayako Amma, Hiroshi Murase

    25th International Conference on Pattern Recognition  2021.1.13 

     More details

    Event date: 2021

    Language:English   Presentation type:Poster presentation  

    Venue:Milan, Italy (Virtual)  

    In this paper, we propose an occlusion-robust pose
    estimation method of an unknown object instance in an
    object category from a depth image. In a cluttered
    environment, objects are often occluded mutually. For
    estimating the pose of an object in such a situation, a
    method that de-occludes the unobservable area of the object
    would be effective. However, there are two difficulties;
    occlusion causes offset between the actual object center
    and the center of its observable area, and different
    instances in a category may have different shapes. To cope
    with these difficulties, we propose a two-stage
    Encoder-Decoder model to extract features with objects
    whose centers are aligned to the image center. In the
    model, we also propose the Median-shape Reconstructor as
    the second stage to absorb shape variations in a category.
    By evaluating the method with both a large-scale virtual
    dataset and a real dataset, we confirmed the proposed
    method achieves good performance on pose estimation of an
    occluded object from a depth image.

  6. OMEga-GAN: Object Manifold Embedding GAN for Image Generation by Disentangling Parameters into Pose and Shape Manifolds International conference

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    25th International Conference on Pattern Recognition  2021.1.13 

     More details

    Event date: 2021

    Language:English   Presentation type:Poster presentation  

    Venue:Milan, Italy (Virtual)  

    In this paper, we propose Object Manifold Embedding GAN (Ω-GAN) to generate images of variously shaped and arbitrarily posed objects from a noise variable sampled from a distribution defined over the pose and the shape manifolds in a vector space. We introduce Parametric Manifold Sampling to sample noise variables from a distribution over the pose manifold to conditionally generate object images in arbitrary poses by tuning the pose parameter. We also introduce Object Identity Loss for clearly disentangling the pose and shape parameters, which allows us to maintain the shape of the object instance when only the pose parameter is changed. Through evaluation, we confirmed that the proposed Ω-GAN could generate variously shaped object images in arbitrary poses by changing the pose and shape parameters independently. We also introduce an application of the proposed method for object pose estimation, through which we confirmed that the object poses in the generated images are accurate.

  7. A Study on Product Image Impression Estimation considering the Customer's Attributes

    中本 麻友, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, 中澤 満, チェ ヨンナム, シュテンガー ビヨン

    IEICE General Conference  2021.3.10 

     More details

    Event date: 2021

    Language:Japanese   Presentation type:Oral presentation (general)  

  8. A Preliminary Study on Belongings Category and Weight Recognition based on Walking Skeleton Trajectory

    水野 雅也, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase, 井下哲夫

    IEICE General Conference  2021.3.11 

     More details

    Event date: 2021

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:オンライン  

  9. A Preliminary Study on Eye Contact Detection for Distant Pedestrians using an In-vehicle Camera

    畑 隆聖, Daisuke Deguchi, Takatsugu Hirayama, Yasutomo Kawanishi, Hiroshi Murase

    IEICE General Conference  2021.3.11 

     More details

    Event date: 2021

    Language:Japanese   Presentation type:Oral presentation (general)  

  10. 個人差を考慮した歩き方からの手荷物の重さ推定の検討

    水野 雅也, 川西 康友, 出口 大輔, 村瀬 洋

    パターン認識・メディア理解研究会(PRMU)  2021.12.17 

     More details

    Event date: 2021

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:オンライン  

  11. 人物姿勢と注視対象配置制約に基づく後ろ向き人物の注視領域推定

    弓矢 隼大, 川西 康友, 出口 大輔, 村瀬 洋, 細野 峻司

    第24回画像の認識・理解シンポジウム(MIRU)  2021.7.30 

     More details

    Event date: 2021

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:Online  

  12. 情報エントロピーにもとづく車両歩行者インタラクションモデルの検討

    新村 文郷, 赤井 直紀, 川西 康友, 平山 高嗣, 劉 海龍, 出口 大輔, 村瀬 洋

    第22回計測自動制御学会システムインテグレーション部門講演会  2021.12.16 

     More details

    Event date: 2021

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:オンライン  

  13. 観衆の顔向きの時空間統合によるステージ上の注目対象及び注目度の推定

    武田 一馬, 川西 康友, 平山 高嗣, 出口 大輔, 井手 一郎, 村瀬 洋, 柏野 邦夫

    パターン認識・メディア理解研究会(PRMU)  2021.12.17 

     More details

    Event date: 2021

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:オンライン  

  14. 人物姿勢と注視対象配置制約に基づく後ろ向き人物の注視領域推定

    弓矢 隼大, 川西 康友, 出口 大輔, 村瀬 洋, 細野 峻司

    コンピュータビジョンとイメージメディア研究会(CVIM)  2021.5.21 

     More details

    Event date: 2021

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:Online  

  15. 人物姿勢と注視対象配置制約に基づく後ろ向き人物の注視領域推定

    弓矢 隼大, 川西 康友, 出口 大輔, 村瀬 洋, 細野 峻司

    第24回画像の認識・理解シンポジウム(MIRU)  2021.7.30 

     More details

    Event date: 2021

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:Online  

  16. 歩き方の特徴に着目した所持物の種類・重さ認識の検討

    水野 雅也, 川西 康友, 出口 大輔, 村瀬 洋, 井下 哲夫

    第24回画像の認識・理解シンポジウム(MIRU)  2021.7.29 

     More details

    Event date: 2021

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:Online  

  17. Pointedness of an Image: Measuring How Pointy an Image is Perceived International conference

    Chihaya Matsuhira, Marc A. Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    HCII 2021  2021.7.29 

     More details

    Event date: 2021

    Language:English   Presentation type:Poster presentation  

    Venue:Virtual  

    For computers to understand human perception, metrics that can capture human perception well are important. However, there are few metrics that characterize the visual perception of humans towards images. Therefore, in this paper, we propose a novel concept and a metric of pointedness of an image, which describes how pointy an image is perceived. The algorithm is inspired by the Features from Accelerated Segment Test (FAST) algorithm for corner detection which looks on the number of continuous neighboring darker pixels surrounding each pixel. We assume that this number would be proportional to the perceived pointedness in the region around the pixel. We evaluated our method towards how well it could capture the human perception of images. To compare the method with similar metrics that describe shapes, we prepared silhouette images of both artificial shapes and natural objects. The results showed that the proposed method gave nearly equivalent perceptual performance to other metrics and also worked in a larger variety of images.

    DOI: https://doi.org/10.1007/978-3-030-78635-9_20

  18. 姿勢変化の連続性に着目した人物姿勢推定器の能動学習

    森 太郎, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋, 井下 哲夫

    第24回画像の認識・理解シンポジウム(MIRU)  2021.7.28 

     More details

    Event date: 2021

    Language:Japanese   Presentation type:Poster presentation  

    Venue:online  

  19. Tell as you imagine: Sentence imageability-aware image captioning International conference

    Kazuki Umemura, Marc A. Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    27th Int. Conf. on Multimedia Modeling (MMM2021)  2021.6.24 

     More details

    Event date: 2021

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Online  

    DOI: 10.1007/978-3-030-67835-7_6

  20. Imageability Estimation using Visual and Language Features International conference

    Chihaya Matsuhira, Marc A. Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    2020 International Conference on Multimedia Retrieval  2020.10.28 

     More details

    Event date: 2020

    Language:English   Presentation type:Poster presentation  

    Venue:Dublin, Ireland (Virtual)  

    Imageability is a concept from Psycholinguistics quantizing the human perception of words. However, existing datasets are created through subjective experiments and are thus very small. Therefore, methods to automatically estimate the imageability can be helpful. For an accurate automatic imageability estimation, we extend the idea of a psychological hypothesis called Dual-Coding Theory, that discusses the connection of our perception towards visual information
    and language information, and also focus on the relationship between the pronunciation of a word and its imageability. In this research, we propose a method to estimate imageability of words
    using both visual and language features extracted from corresponding data. For the estimation, we use visual features extracted from low- and high-level image features, and language features extracted from textual features and phonetic features of words. Evaluations how that our proposed method can estimate imageability more accurately than comparative methods, implying the contribution of each feature to the imageability.

    DOI: 10.1145/3372278.3390731

  21. A study on image captioning considering its imageability

    Kazuki Umemura, Marc Aurel Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2020.3.5 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:オンライン  

  22. Typicality evaluation of food-type specific presentation

    Masamu Nakamura, Yasutomo Kawanishi, Keisuke Doman, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2020.3.5 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:オンライン  

  23. A Preliminary Study on Improving a Cyclist Detector Using Weakly Supervised Learning

    Taro Mori, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    IEICE General Conference  2020.3.3 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:広島大学  

  24. A Preliminary Study on Multi-Target Attention Degree Estimation based on the Movement of Gaze Points

    Kazuma Takeda, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hidehisa Nagano, Kunio Kashino

    IEICE General Conference  2020.3.3 

     More details

    Event date: 2020

    Language:Japanese  

  25. A Preliminary Study on Vehicle Localization Utilizing Multiple Driving Image Sequences

    Yuta Goto, Haruya Kyutoku, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    IEICE General Conference  2020.3.3 

     More details

    Event date: 2020

    Language:Japanese  

  26. SOANets: Encoder-Decoder based Skeleton Orientation Alignment Network for White Cane User Recognition from 2D Human Skeleton Sequence International conference

    Naoki Nishida, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Jun Piao

    International Conference on Computer Vision Theory and Applications (VISAPP) 2020  2020.2.27 

     More details

    Event date: 2020

    Language:English   Presentation type:Poster presentation  

    Venue:Grand Hotel Excelsior Malta  

    In recent years, various facilities have been deployed to support visually impaired people. However, accidents caused by visual disabilities still occur. In this paper, to support the visually impaired people in public areas, we aim to identify whether a pedestrian image sequence obtained by a surveillance camera indicates the presence of a white cane user by analyzing the temporal transition of a human skeleton represented as 2D coordinates. Our previously proposed method aligns the orientation of the human skeletons to various orientations and identifies a white cane user from the corresponding sequences, relying on multiple classifiers related to each orientation. The method employs an exemplar-based approach to perform the alignment. However, it heavily depends on the number of exemplars and consumes excessive memory. In this paper, we propose a method to align 2D human skeleton representation sequence to various orientations using the proposed Skeleton Orientation Alignment Networks (SOANets) based on an encoder-decoder model. Using SOANets, we can obtain 2D skeleton representation sequences aligned to various orientations, extract richer skeleton features, and recognize white cane users accurately. We conducted an experiment to confirm that the
    proposed method improves the recognition rate by 16%, compared to the method that does not use the skeleton
    orientation alignment.

  27. Occlusion-Aware Skeleton Trajectory Representation for Abnormal Behavior Detection International conference

    Onur Temuroglu, Yasutomo Kawanishi, Daisuke Deguchi, Takatsugu Hirayama, Ichiro Ide, Hiroshi Murase, Mayuu Iwasaki, Atsushi Tsukada

    The International Workshop on Frontiers of Computer Vision (IW-FCV)  2020.2.20 

     More details

    Event date: 2020

    Language:English   Presentation type:Oral presentation (general)  

    Venue:指宿ふれあいプラザなのはな館  

    Surveillance cameras are expected to play a large role in the development of ITS technologies. They can be used to detect abnormally behaving individuals which can then be reported to drivers nearby. There are multiple works that tackle the problem of abnormal behavior detection. However, most of these works make use of appearance features which have redundant information and are susceptible to noise. While there are also works that make use of pose skeleton representation, they do not consider well how to handle cases with occlusions, which can occur due to the simple reason of pedestrian orientation preventing some joints from appearing in the frame clearly. In this paper, we propose a skeleton trajectory representation that enables handling of occlusions. We also propose a framework for pedestrian abnormal behavior detection that uses the proposed representation and detect relatively hard-to-notice anomalies such as drunk walking. The experiments we conducted show that our method outperforms other representation methods.

  28. Browsing Visual Sentiment Datasets Using Psycholinguistic Groundings International conference

    Marc Aurel Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Hiroshi Murase

    Lecture Note in Computer Science  2020.1.4 

     More details

    Event date: 2020

    Language:English  

    Venue:Deajeon Convention Center, Daejeon, Korea  

    Recent multimedia applications commonly use text and imagery from Social Media for tasks related to sentiment research. As such, there are various image datasets for sentiment research for popular classification tasks. However, there has been little research regarding the relationship between the sentiment of images and its annotations from a multi-modal standpoint. In this demonstration, we built a tool to visualize psycholinguistic groundings for a sentiment dataset. For each image, individual psycholinguistic ratings are computed from the image's metadata. A sentiment-psycholinguistic spatial embedding is computed to show a clustering of images across different classes close to human perception. Our interactive browsing tool can visualize the data in various ways, highlighting different psycholinguistic groundings with heatmaps.

    DOI: 10.3758/s13428-018-1099-3

  29. More-Natural Mimetic Words Generation for Fine-Grained Gait Description International conference

    Hirotaka Kato, Takatsugu Hirayama, Ichiro Ide, Keisuke Doman, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

    Lecture Note in Computer Science  2020.1.4 

     More details

    Event date: 2020

    Language:English   Presentation type:Poster presentation  

    Venue:Deajeon Convention Center, Daejeon, Korea  

    A mimetic word is used to verbally express the manner of a phenomenon intuitively. The Japanese language is known to have a greater number of mimetic words in its vocabulary than most other languages. Especially, since human gaits are one of the most commonly represented behavior by mimetic words in the language, we consider that it should be suitable for labels of fine-grained gait recognition. In addition, Japanese mimetic words have a more decomposable structure than these in other languages such as English. So it is said that they have sound-symbolism and their phonemes are strongly related to the impressions of various phenomena. Thanks to this, native Japanese speakers can express their impressions on them briefly and intuitively using various mimetic words. Our previous work proposed a framework to convert the body-parts movements to an arbitrary mimetic word by a regression model. The framework introduced a phonetic space" based on sound-symbolism, and it enabled fine-grained gait description using the generated mimetic words consisting of an arbitrary combination of phonemes. However, this method did not consider the "naturalness" of the description. Thus, in this paper, we propose an improved mimetic word generation module considering its naturalness, and update the description framework. Here, we define the co-occurrence frequency of phonemes composing a mimetic word as the naturalness. To investigate the co-occurrence frequency, we collected many mimetic words through a subjective experiment. As a result of evaluation experiments, we confirmed that the proposed module could describe gaits with more natural mimetic words while maintaining the description accuracy."

    DOI: 10.1007/978-3-030-37734-2_18

  30. 視覚特徴と言語特徴を用いた単語の心像性推定の検討

    松平 茅隼, カストナー マークアウレル, 井手 一郎, 川西 康友, 平山 高嗣, 道満 恵介, 出口 大輔, 村瀬 洋

    言語処理学会 第26回年次大会  2020.3.9 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Poster presentation  

    Venue:オンライン  

  31. Modeling Eye-Gaze Behavior of Electric Wheelchair Drivers via Inverse Reinforcement Learning International conference

    Yamato Maekawa, Naoki Akai, Takatsugu Hirayama, Luis Yoichi Morales, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    2020 IEEE International Conference on Intelligent Transportation Systems  2020.9.21 

     More details

    Event date: 2020

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Rhodes, Greece (Virtual)  

    It is intuitively obvious that eye-gaze behaviors of experienced drivers are different from those of novice drivers. However, it is not easy to understand the difference in their behavior quantitatively. In this work, we present an explainable eye-gaze behavior modeling method for electric wheelchair drivers based on Inverse Reinforcement Learning (IRL). We first create feature maps that represent risk factors during driving. These feature maps are able to represent not only to what but also from where drivers pay attention. IRL uses the feature maps to learn the reward representing the eye-gaze behaviors and allows us to see important features via the automatic acquisition of the reward. Through analysis of the learned model, we show quantitative evidence that eye-gaze behaviors of experienced drivers are better-balanced by paying attention to multiple risks.

    DOI: 10.1109/ITSC45102.2020.9294255

  32. A study on a coloring method for document overviews

    Chihaya Matsuhira, Marc Aurel Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2020.9.9 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:オンライン  

  33. ソフト順序制約付きラベル境界緩和法に基づく 列車前方映像のセマンティックセグメンテーション

    振津 勇紀, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    第23回画像の認識・理解シンポジウム(MIRU)  2020.8.5 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:Online  

  34. 移動する複数物体への群衆からの4次元注目度ヒートマップ生成の初期検討

    武田 一馬, 川西 康友, 平山 高嗣, 出口 大輔, 井手 一郎, 村瀬 洋, 永野 秀尚, 柏野 邦夫

    第23回画像の認識・理解シンポジウム (MIRU2020)  2020.8.5 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Poster presentation  

    Venue:オンライン  

  35. 複数画像系列の重み付き統合による自車位置推定

    後藤 優太, 久徳 遙矢, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    第23回画像の認識・理解シンポジウム(MIRU)  2020.8.5 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Poster presentation  

    Venue:Online  

  36. 物体の同一性を評価する誤差関数の導入による姿勢・形状変化を独立に扱える GAN の提案

    川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    第23回画像の認識・理解シンポジウム(MIRU)  2020.8.4 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Poster presentation  

    Venue:Online  

  37. 物体追跡を活用したCenterNetの弱教師あり学習

    森 太郎, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2020.8.4 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Poster presentation  

    Venue:Online  

  38. Performance Boost of Attribute-aware Semantic Segmentation via Data Augmentation for Driver Assistance International conference

    Mahmud Dwi Sulistiyo, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Takatsugu Hirayama, Hiroshi Murase

    The 8th IEEE International Conference on Information and Communication Technology  2020.6.24 

     More details

    Event date: 2020

    Language:English   Presentation type:Oral presentation (general)  

    This paper is an extension of our work in developing an attribute-aware semantic segmentation method which focuses on pedestrian understanding in a traffic scene. Recently, the trending topic of semantic segmentation has been expanded to be able to collaborate with the object’s attributes recognition task; Here, it refers to recognizing a pedestrian’s body orientation. The attribute-aware semantic segmentation can be more beneficial for driver assistance compared to the conventional semantic segmentation because it can provide a more informative output to the system. In this paper, we conduct a study of the data augmentation usage as an effort to enhance the performance of the attribute-aware semantic segmentation task. The experiments show that the proposed method in augmenting the training data is able to improve the model’s performance. We also demonstrate some of qualitative results and discuss the benefits to a driver assistance system.

    DOI: 10.1109/ICoICT49345.2020.9166219

  39. Preliminary Study on Attention Degree Estimation for Multiple Objects Based on Similarity between Gaze-Point and Gaze-Target Movements

    Kazuma Takeda, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hidehisa Nagano, Kunio Kashino

    2020.5.15 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:オンライン  

  40. On the quantification of the mental image of visual concepts for multi-modal applications

    Marc Aurel Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Hiroshi Murase

    2020.5.7 

     More details

    Event date: 2020

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Online  

  41. Prediction of Pedestrians' Road Crossing at Intersection based on Estimation of Head Orientation

    高木 俊平, 梅村 充一, 牛田 勝憲, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

    IEICE General Conference  2020.3.19 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Oral presentation (general)  

  42. 超低解像度FIR画像内での人物位置と動作の違いに着目した骨格推定法の検討

    岩田 紗希, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 相澤 知禎

    動的画像処理実利用化ワークショップ(DIA)  2020.3.10 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:国立沖縄工業高等専門学校  

    近年,高齢化の進展により,独居高齢者に向けた見守りシステムが注目されている.しかし,見守りシステムにはプライバシーの問題が存在する.そこで我々はプライバシーの問題を軽減でき,さらに暗闇での撮影にも強い赤外線センサアレイを用いて撮影した超低解像度FIR画像系列から人物の骨格を推定する手法を提案してきた.本発表では特に超低解像度FIR画像内での人物位置と動作の違いに着目した骨格推定法について検討する.具体的には,超低解像度FIR画像内で人物位置に依存しない特徴を抽出するため,低解像度画像において影響が大きいと考えられる中間層でのPoolingをせずに,特徴抽出の最後にGlobalMaxPoolingを導入する.さらに動作の種類に合わせて,時系列情報と空間的情報を有効活用できるネットワークを提案する.実験では,赤外線センサアレイの画角内の様々な位置で人物を撮影したデータセットを用いて,従来手法と提案手法で特定の人物位置で学習を行ない,未学習位置で骨格推定精度を評価した.その結果,人物の動作を滑らかに推定でき,定量的にも精度が向上することを確認した.

  43. 車両の進路情報を条件とした cGAN による走路推定

    右島 琢也, 久徳 遙矢, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    動的画像処理実利用化ワークショップ(DIA)  2020.3.10 

     More details

    Event date: 2020

    Language:Japanese   Presentation type:Poster presentation  

    Venue:国立沖縄工業高等専門学校  

    近年,自動運転に関する研究開発が活発になされており,限定された環境下ではあるものの公道での走行実験等も進められている.しかし,交差点は事故の危険性が高く,交差点を含む一般道を状況に応じて安全に走 行するための課題は多い.このような背景から,車載カメラを用いて詳細に周囲環境を認識し,周囲の状況を考慮 して安全に走行できる道路上の領域(走路)を推定する技術が求められている.そこで本発表では,車載カメラ画像と,目的地までの経路から得られる車両の進路情報を条件(Condition)とした,conditional GANの枠組みを利用して走行すべき走路を推定する手法を提案する.実走行データから構築したデータセットを用いた評価実験により,画像のみを入力とする比較手法に比べて,提案手法では走路推定精度が15.0%向上することを確認した.

  44. Occlusion-Robust Pose-Feature Representation Learning for Object Pose Estimation from a Depth Image

    Hiroki Tatemichi, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Ayako Amma

    IEICE Technical Report (PRMU)  2019.12.20 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大分大学  

  45. 3つの学習特徴に基づく料理レシピの地域属性推定

    伊藤 耀一朗, 道満 恵介, 川西 康友, 平山 高嗣, 井手 一郎, 出口 大輔, 村瀬 洋

    電子情報通信学会魅力工学研究会シンポジウム2019  2019.8.28 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Poster presentation  

    Venue:名古屋大東山校舎  

  46. 見えに基づく同一料理カテゴリの料理に関する典型度分析

    中村 真務, 川西 康友, 道満 恵介, 平山 高嗣, 井手 一郎, 出口 大輔, 村瀬 洋

    電子情報通信学会魅力工学研究会シンポジウム2019  2019.8.28 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Poster presentation  

    Venue:名古屋大東山校舎  

  47. 欠損復元AutoEncoderによる遮蔽に頑健な物体姿勢推定の検討

    立道 大樹, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 安間 絢子

    画像の認識・理解シンポジウム(MIRU)  2019.8.1 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Poster presentation  

    Venue:グランキューブ大阪(大阪府立国際会議場)  

    近年,日常生活の支援のために家庭環境にロボットが導入されつつある.ロボットが物体を持ち運ぶためには,物体の姿勢を推定する必要があるが,物体が密集して存在する場合,他の物体に遮蔽されることで観測値に欠損が生じ,姿勢推定が困難である.欠損を復元するようにAutoEncoderを学習し,Encoder部分から得られる特徴ベクトルを姿勢推定に用いる手法があるが,この手法は欠損による物体中心の位置ずれを考慮していないため,欠損が大きいほど精度が低い.本発表では,欠損を復元できるように学習したAutoEncoderを,位置ずれの補正をしながら2回適用することで,観測値の欠損と位置ずれに対処した姿勢推定手法を提案する.また,パラメトリック固有空間法を拡張し,複数物体の姿勢変化からなる多様体上で姿勢補間することにより,同一クラスに属する未知形状の物体の未知姿勢であっても姿勢推定ができる手法を提案する.

  48. 走行履歴情報からの状況適応型走路の自動獲得

    右島 琢也, 久徳 遙矢, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2019.8.1 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Poster presentation  

    Venue:グランキューブ大阪(大阪府立国際会議場)  

    近年,自動運転技術が注目を集めており,その実現に向けた研究開発が盛んである.自動運転の実現のため,安全に走行可能な道路領域を推定する走路推定技術が求められている.走路の推定には周囲環境認識技術が不可欠であり,セマンティックセグメンテーションがその中で重要な役割を担うと期待されている.これまでに,セマンティックセグメンテーションを走路推定に用いる試みは行われているが,道路上に存在する他の車両や歩行者との接触は考慮されていない.我々は接触を回避した走路を得るために,車速の変化に着目して自車両の減速行動を学習し,複数フレームを用いて他物体の動きを学習することにした.本発表では,自車速を用いて車両の走行履歴情報を画像上に投影することで,多数のラベル画像を自動的に獲得し,他物体との接触がない走路(状況適応型走路)を推定する手法を提案する.名古屋駅周辺の走行履歴情報を用いて提案手法の評価を行なった結果,自動獲得した画像から走路推定器を構築できることを確認した.

  49. Typicality analysis of a food within a food category based on its appearance

    Masamu Nakamura, Yasutomo Kawanishi, Keisuke Doman, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2019.8.29 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学 ベンチャー・ビジネス・ラボラトリー  

  50. On Visualizing Psycholinguistic Groundings for Sentiment Image Datasets

    Marc Aurel Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Hiroshi Murase

    Meeting on Image Recognition & Understanding  2019.8.1 

     More details

    Event date: 2019

    Language:English  

    Venue:グランキューブ大阪(大阪府立国際会議場)  

    Recent multimedia applications commonly use text and imagery from Social Media for tasks related to sentiment research. As such, there are various image datasets for sentiment research for popular classification tasks. However, there has been little research regarding the relationship between the sentiment of images and its annotations from a multi-modal standpoint. In this research, we built a tool to visualize psycholinguistic groundings for a sentiment dataset. For each image, individual psycholinguistic ratings are computed from the image's metadata. A sentiment-psycholinguistic spatial embedding is computed to show a clustering of images across different classes close to human perception. Our interactive browsing tool can visualize the data in various ways, highlighting different psycholinguistic groundings with heatmaps.

  51. Viewpoint Recommendation for Object Pose Estimation via Pose Ambiguity Minimization

    Nik Mohd Zarifie Hashim, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    The 22nd Meeting on Image Recognition and Understanding (MIRU)  2019.8.1 

     More details

    Event date: 2019

    Language:English   Presentation type:Poster presentation  

    Venue:Osaka International Convention Center  

    Recently, helper robots become popular in our social life, especially for helping the elderly and the disabled people to perform their daily tasks at home. To handling objects, object pose estimation from a depth image is an essential task of the helper robots. However, an object’s pose is often ambiguous from an observation from only a single viewpoint. If we can observe the object from additional viewpoints, the pose estimation result will be better. Thus, we propose a next viewpoint recommendation method based on pose ambiguity minimization. We confirmed and showed the proposed method outperformed other comparative methods on synthetic object images.

  52. Visualization of group work via sensing of real world activities

    Daisuke Deguchi

    2019.6.26 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:京都大学  

  53. Hand Orientation Estimation in Probability Density Form International conference

    Kazuaki Kondo, Daisuke Deguchi, Atsushi Shimada

    The Fourth International Workshop on Egocentric Perception, Interaction and Computing  2019.6.17 

     More details

    Event date: 2019

    Language:English   Presentation type:Poster presentation  

    Venue:Long Beach Convention Center, Long Beach, CA USA  

  54. 超低解像度遠赤外線画像からの人物骨格推定の検討

    岩田 紗希, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 相澤 知禎

    画像センシングシンポジウム(SSII)  2019.6.13 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Poster presentation  

    Venue:パシフィコ横浜アネックスホール  

    近年,高齢化社会の進展が問題となっており、高齢者の健康の暮らしのためには身体機能の維持が必須である.そのためには日常的に,身体の動きを把握する必要があるが,センサ装着が必要な方法や可視光カメラを用いる方法ではセンサの装着忘れやプライバシの問題がある.
    そこで,超低解像度遠赤外線画像を用いた骨格推定法を提案する.現在,高解像度な可視光画像からの骨格推定は可能であるため,本手法では可視光カメラと赤外線カメラで同時に撮影をするシステムを構築し,学習データを収集する.それを用いて,ニューラルネットワークを学習し,超低解像度遠赤外線画像から直接骨格を推定する.

  55. A Preliminary Study on Integrating Camera and LiDAR Pedestrian Detections Adaptive to Surrounding Environmental Conditions

    Haruya Kyutoku, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Kazuki Kato, Hiroshi Murase

    IEICE Technical Report (PRMU)  2019.5.30 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:国立オリンピック記念青少年総合センター  

  56. A Study on Human Pose Estimation from an Extremely Low-Resolutiohn FIR image Sequence

    Saki Iwata, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa

    Japan-Taiwan Joint Workshop on Multimedia and HCI  2019.4.14 

     More details

    Event date: 2019

    Language:English   Presentation type:Oral presentation (general)  

    Venue:國立成功大學(臺灣,臺南)  

  57. A Study on Occlusion-Robust Object Pose Estimation with a De-occluding AutoEncoder

    Hiroki Tatemichi, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Ayako Amma

    Japan-Taiwan Joint Workshop on Multimedia and HCI  2019.4.14 

     More details

    Event date: 2019

    Language:English   Presentation type:Poster presentation  

    Venue:國立成功大學(臺灣,臺南)  

  58. Estimating the Imageability of a sentence for image caption evaluation International conference

    Kazuki Umemura, Marc Aurel Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    Japan-Taiwan Joint Workshop on Multimedia and HCI  2019.4.13 

     More details

    Event date: 2019

    Language:English   Presentation type:Poster presentation  

    Venue:國立成功大學(臺灣,臺南)  

  59. 'KamiRepo' System with Automatic Student Identification to Handle Handwritten Assignments on LMS

    Daisuke Deguchi

    2019.3.25 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:法政大学 市ケ谷キャンパス  

  60. 時系列平滑化を用いた列車前方映像に対するセマンティックセグメンテーション手法の検討

    振津 勇紀, 新村 文郷, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋, 向嶋 宏記, 長峯 望

    電子情報通信学会総合大会  2019.3.20 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:早稲田大学 西早稲田キャンパス  

  61. 畳み込みの多段階分解によるSemantic Segmentationの高速化

    野田 紘司, 久徳 遙矢, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    電子情報通信学会総合大会  2019.3.20 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:早稲田大学 西早稲田キャンパス  

    近年,Semantic Segmentationは自動運転や高度運転支援の要素技術として注目を集めている.しかし,高精度なSemantic Segmentation手法の計算コストは高く,実時間処理は困難である.従って,精度を維持したまま,より高速に計算する手法が求められている.Semantic Segmentationの処理は,畳み込み演算の計算時間が大部分を占める.提案手法では,XceptionモジュールのDepthwise convolutionを垂直・水平方向に分解することで畳み込み演算のさらなる高速化を試みる.実験により,mIoUの低下を抑えつつ,パラメータ数と実行時間を削減可能なことを確認した.

  62. A Study on the Pose Estimation of an Occluded Object by a De-occluding AutoEncoder

    Hiroki Tatemichi, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Ayako Amma

    2019 IEICE General Conference  2019.3.20 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:早稲田大学 西早稲田キャンパス  

  63. Analyzing Changes of Eye Gaze Movements as Becoming Skilled at Driving an Electric Wheel Chair

    Yamato Maekawa, Naoki Akai, Luis Yoichi Morales, Takatsugu Hirayama, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    2019 IEICE General Conference  2019.3.20 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:早稲田大学 西早稲田キャンパス  

  64. 超低解像度遠赤外線画像からの人物姿勢推定の初期検討

    岩田 紗希, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 相澤 知禎

    情報処理学会全国大会  2019.3.15 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:福岡大学七隈キャンパス  

    近年,高齢化社会の進展が問題となっており、高齢者の健康の暮らしのためには身体機能の維持が必須である.そのためには日常的に,身体の動きを把握する必要があるが,センサ装着が必要な方法や可視光カメラを用いる方法ではセンサの装着忘れやプライバシの問題がある.
    そこで,超低解像度遠赤外線画像を用いた姿勢推定法を提案する.現在,高解像度な可視光画像からの骨格推定は可能であるため,本手法では可視光カメラと赤外線カメラで同時に撮影をするシステムを構築し,学習データを収集する.それを用いて,ニューラルネットワークを学習し,超低解像度遠赤外線画像から直接姿勢を推定する.

  65. 画像キャプションの質的評価に向けた文の心像性推定手法の検討

    梅村 和紀, カストナー マークアウレル, 井手 一郎, 川西 康友, 平山 高嗣, 道満 恵介, 出口 大輔, 村瀬 洋

    言語処理学会年次大会  2019.3.14 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  66. A preliminary study on estimating word imageability labels using Web image data mining

    Marc Aurel Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Hiroshi Murase

    2019.3.14 

     More details

    Event date: 2019

    Language:English   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  67. LIDARから得られる3D点群を用いた自転車認識

    山本 大貴, 新村 文郷, 出口 大輔, 川西 康友, 井手 一郎, 加藤 一樹, 村瀬 洋

    動的画像処理実利用化ワークショップ(DIA)  2019.3.8 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Poster presentation  

    Venue:北九州国際会議場  

  68. 事例ベースの姿勢正規化による白杖利用者認識に向けた検討

    西田 尚樹, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 朴 君

    動的画像処理実利用化ワークショップ(DIA)  2019.3.7 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Poster presentation  

    Venue:北九州国際会議場  

    本研究では,視覚障害者を支援するために,人物の姿勢変化から歩行者系列が白杖利用者か否か分類す
    ることを目的とする.しかし,人物の向きによって画像上の人物姿勢は大きく異なるため,分類しなければなら
    ない姿勢パターンが多くなり,分類が困難となる.そこで本発表では,事例ベースで様々な向きの姿勢をある1つ
    の向きの姿勢に正規化する手法を提案する.分類する姿勢のパターンが限定されることにより,高精度の分類が
    可能となる.評価実験において,提案手法により認識率が 5% 向上することを確認した.

  69. 運転者による歩行者の見つけやすさ向上のためのヘッドライトシステム

    前田 高志, 平山 高嗣, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    動的画像処理実利用化ワークショップ(DIA)  2019.3.7 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:北九州国際会議場  

    夜間における歩行者の交通死亡事故が多発しており,その原因として運転者による歩行者の視認が困難であることが挙げられる.近年,通常の前方照射に加えて選択的照射が可能なヘッドライトが開発されており,その技術を活かして歩行者に選択的に光を照射することで歩行者の見つけやすさを向上させることが考えられる.我々はこれまでに点滅に着目して効果的な照射法を検討し,特定の周波数において点滅光の照射が効果的であることを確認しているが, 1 つの固定された周辺光条件しか想定していなかった.そこで本研究では,周辺光条件ごとに効果的な点滅照射を分析する.具体的には,運転環境を模擬した臨場感のある仮想環境において 6 種類の周辺光条件を設定し,通常のロービーム照射,ハイビーム照射および 7 種類の点滅周波数を用いて実験を行なった.実験結果から,点滅照射が見つけやすさ向上に有効であることや,異なる周辺光条件では効果的な周波数が異なることを確認した.

  70. SNS投稿写真のVisual Conceptに基づく時空間類似地域マイニング

    陳 璐, 川西 康友, 井手 一郎, 平山 高嗣, 道満 恵介, 出口 大輔, 村瀬 洋

    データ工学と情報マネジメントに関するフォーラム(DEIM)  2019.3.4 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:ホテルオークラJRハウステンボス  

    旅行を計画する際,満足のいく計画を立てるためには,旅先の雰囲気を予め把握することが重要である.ある地域の訪問予定時の雰囲気が,既に知っている地域のある時期の雰囲気と似ていることが分かれば,その地域の訪問時の雰囲気を直感的に把握することできる.これを実現するため,我々は旅行者の体験を反映した大量のSNS投稿写真に着目した.具体的には,写真に付随する時空間情報を用いて写真をクラスタリングし「時期情報付き地域」を獲得し,写真のVisual Conceptに基づいて時空間類似地域をマイニングすることで,時期を考慮した類似地域の組を獲得する手法を提案する.手法の有用性を示すため,Flickr に投稿された写真を用いて時空間類似地域マイニング実験を行った.また,被験者実験を通して,提案手法の妥当性を確認した.

  71. 画像付き料理レシピの地域属性推定の検討

    伊藤 耀一朗, 道満 恵介, 川西 康友, 平山 高嗣, 井手 一郎, 出口 大輔, 村瀬 洋

    データ工学と情報マネジメントに関するフォーラム(DEIM)  2019.3.4 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:ホテルオークラJRハウステンボス  

    近年,投稿型料理レシピポータルサイトが普及している.ウェブ上には膨大な数の料理レシピが存在し,
    掲載されている料理の種類は多岐にわたる.しかし,それに伴い,サイト利用者が検索の際に目的とする料理レシピ
    件数を絞りこむことが難しくなりつつある.そこで本研究では,地域属性(スペイン料理,中華料理など)ごとに料
    理の味や見た目が大きく異なることに着目し,料理レシピがもつ多様な情報から,機械学習を用いて作成される料理
    の地域属性を推定する手法を提案する.学習には,料理の完成画像から得られた画像特徴,素材一覧から得られた素
    材特徴,調理手順文の動詞から得られた手順特徴の 3 つを組み合わせて用いる.結果として,これら 3 つの全特徴を
    用いた手法で 8 割近い推定精度が得られることを確認した.

  72. Hard Negative Mining from in-Vehicle Camera Images based on Multiple Observations of Background Patterns International conference

    Masashi Hontani, Haruya Kyutoku, David Robert Wong, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    International Conference on Computer Vision Theory and Applications (VISAPP) 2019  2019.2.26 

     More details

    Event date: 2019

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Vienna House Diplomat Prague, Prague, Czech Republic  

    In recent years, the demand for highly accurate pedestrian detectors has increased due to the development of advanced driving support systems.
    For the training of an accurate pedestrian detector, it is important to collect a large number of training samples.
    To support this, this paper proposes a ``hard negative'' mining method to automatically extract background images which tend to be erroneously detected as pedestrians.
    Negative samples are selected based on the assumption that frequent patterns observed multiple times in the same location are most likely parts of the background scene.
    As a result of an evaluation using in-vehicle camera images captured along the same route, we confirmed that the proposed method can automatically collect false positive samples accurately.
    We also confirmed that a highly accurate detector can be constructed using the additional negative samples.

  73. Next Viewpoint Recommendation by Pose Ambiguity Minimization for Accurate Object Pose Estimation International conference

    Nik Mohd Zarifie Hashim, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Ayako Amma, Norimasa Kobori

    International Conference on Computer Vision Theory and Applications (VISAPP) 2019  2019.2.25 

     More details

    Event date: 2019

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Vienna House Diplomat Prague, Prague, Czech Republic  

    3D object pose estimation by using a depth sensor is one of the important tasks in activities by robots. To reduce the pose ambiguity of an estimated object pose, several methods for multiple viewpoint pose estimation have been proposed. However, these methods need to select the viewpoints carefully to obtain better results. If the pose of the target object is ambiguous from the current observation, we could not decide where we should move the sensor to set as the next viewpoint. In this paper, we propose a best next viewpoint recommendation method by minimizing the pose ambiguity of the object by making use of the current pose estimation result as a latent variable. We evaluated viewpoints recommended by the proposed method and confirmed that it helps us to gain better pose estimation results than several comparative methods on a synthetic dataset.

  74. Pedestrian Intensive Scanning for Active-scan LIDAR International conference

    Taiki Yamamoto, Fumito Shinmura, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    International Conference on Computer Vision Theory and Applications (VISAPP) 2019  2019.2.25 

     More details

    Event date: 2019

    Language:English   Presentation type:Poster presentation  

    Venue:Vienna House Diplomat Prague, Prague, Czech Republic  

    In recent years, LIDAR is playing an important role as a sensor for understanding environments of a vehicle’s surroundings. Active-scan LIDAR is being actively developed as a LIDAR that can control the laser irradiation direction arbitrary and rapidly. In comparison with conventional uniform-scan LIDAR (e.g. Velodyne HDL-64e), Active-scan LIDAR enables us to densely scan even distant pedestrians. In addition, if appropriately controlled, this sensor has the potential to reduce unnecessary laser irradiations towards non-target objects. Although there are some preliminary studies on pedestrian scanning strategy for Active-scan LIDARs, in the best of our knowledge, an efficient method has not been realized yet. Therefore, this paper proposes a novel pedestrian scanning method based on orientation aware pedestrian likelihood estimation using the orientation-wise pedestrian’s shape models with local distribution of measured points. To evaluate the effectiveness of the proposed method, we conducted experiments by simulating Active-scan LIDAR using point-clouds from the KITTI dataset. Experimental results showed that the proposed method outperforms conventional methods.

  75. 電動車いす運転の熟達に伴う視行動変化の分析

    前川 大和, 赤井 直紀, モラレス ルイス 洋一, 平山 高嗣, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2019.8.1 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Poster presentation  

    Venue:グランキューブ大阪(大阪府立国際会議場)  

    近年,先進国を中心に高齢化が進んでおり,電動車いすの需要が高まっている.しかし,電動車いすの利便性は高い一方で,事故が多発している.自動車の事故は視覚的な認知ミスが原因であることが多く,電動車いすも自動車と同様に運転者の視覚的な認知を支援することが事故防止に有効であると考えられる.また,熟練運転者と非熟練運転者の視行動に差異があることが知られており,熟練者の視行動に基づいて,運転者の視覚的な認知の支援をすることができると考えられる.本研究では,電動車いす運転における熟練者の視行動のモデル化を目指し,リスクが複数存在する箇所である死角あり狭路で運転する場合を想定して,熟達に伴う視行動の変化を3次元空間上で分析した.その結果,熟達するほど複数のリスクに対してバランスよく注意を払うことを確認した.

  76. Class Augmentation For Semantic Segmentation by Integrating Multiple Methods

    Wang Qishen, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2019.12.12 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:広島県情報プラザ  

  77. 環境認識に関する基礎と最近の動向

    出口 大輔

    日本機械学会東海支部講習会  2019.12.5 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:名古屋大学  

  78. Scene-Adaptive Driving Area Prediction based on Automatic Label Acquisition from Driving Information International conference

    Takuya Migishima, Haruya Kyutoku, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    5th IAPR Asian Conference on Pattern Recognition (ACPR2019)  2019.11.28 

     More details

    Event date: 2019

    Language:English   Presentation type:Poster presentation  

    Venue:Aotea Centre (Auckland, New Zealand)  

  79. Semantic Segmentation of Railway Images Considering Temporal Continuity International conference

    Yuki Furitsu, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Hiroki Mukoujima, Nozomi Nagamine

    5th IAPR Asian Conference on Pattern Recognition (ACPR2019)  2019.11.27 

     More details

    Event date: 2019

    Language:English   Presentation type:Poster presentation  

    Venue:Aotea Centre (Auckland, New Zealand)  

  80. An Analysis of How Driver Experience Affects Eye-Gaze Behavior for Robotic Wheelchair Operation International conference

    Yamato Maekawa, Naoki Akai, Takatsugu Hirayama, Luis Yoichi Morales, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    2019 IEEE International Conference on Computer Vision (ICCV) Workshops  2019.11.2 

     More details

    Event date: 2019

    Language:English   Presentation type:Poster presentation  

    Venue:COEX Convention Center, Seoul, Korea  

    Drivers obtain information on surrounding environment using their eyesights. Experienced eye-gaze behavior is needed when driving at places where multiple risks exist to prepare for and avoid them. In this work, we analyze the change in eye-gaze behavior in such situations while a driver gains experience on the operation of a robotic wheelchair. Accurate distance information in the traffic environment is important to analyze the eye-gaze behavior. However, almost all previous works analyze eye-gaze behavior in a 2D environment, so they could not obtain accurate distance information. For this reason, we analyze eye-gaze behavior in 3D space. Concretely, we developed a novel eye-gaze behavior analysis platform based on a robotic wheelchair and estimated the driver's attention in 3D space. We try to analyze the eye-gaze behavior considering a useful field-of-view in 3D space based on the distance information instead of only the fixation point to investigate the objects that a driver implicitly pays attention to and from where s/he focuses on them. Results show that novice drivers pay attention to a single risk at a time. In contrast, they pay more attention to multiple risks simultaneously as they gain experience. Additionally, we discuss what features are effective to model the eye-gaze behavior based on the results.

    DOI: 10.1109/ICCVW.2019.00545

  81. Exemplar-based Pseudo-Viewpoint Rotation for White-Cane User Recognition from a 2D Human Pose Sequence International conference

    Naoki Nishida, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Jun Piao

    The 16-th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS)  2019.9.20 

     More details

    Event date: 2019

    Language:English   Presentation type:Poster presentation  

    Venue:University of Taipei  

  82. Similar Seasonal-Geo-Region Mining based on Visual Concepts in Social Media Photos International conference

    Yasutomo Kawanishi, Ichiro Ide, Chen Lu, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    5th IEEE Conference on Multimedia BigData  2019.9.11 

     More details

    Event date: 2019

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Kent Ridge Guild House, National University of Singapore  

  83. A Preliminary Study on Pedestrian Abnormal Behavior Recognition based on Pose Heatmap from Surveillance Camera Images

    Onur Temuroglu, Yasutomo Kawanishi, Daisuke Deguchi, Takatsugu Hirayama, Ichiro Ide, Hiroshi Murase, Mayuu Iwasaki, Atsushi Tsukada

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering  2019.9.10 

     More details

    Event date: 2019

    Language:English   Presentation type:Oral presentation (general)  

    Venue:大同大学  

  84. A Preliminary Study on Pseudo-Viewpoint Conversion for White-Cane User Recognition from Arbitrary Viewpoints

    Naoki Nishida, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Jun Piao

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering  2019.9.10 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大同大学  

  85. A Study on Human Skeleton Estimation from an Extremely Low-Resolution FIR Image Sequence for Monitoring Systems

    Saki Iwata, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering  2019.9.10 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大同大学  

  86. An Analysis of Simultaneous Image Matching on Various Datasets for Person Re-identification

    Nik Mohd Zarifie Hashim, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering  2019.9.10 

     More details

    Event date: 2019

    Language:English   Presentation type:Oral presentation (general)  

    Venue:大同大学  

    Person re-identification is becoming a focus topic in many discussions recently. It becomes a vital role in public surveillance for identifying people across the street, inside supermarkets, and airports. Person re-identification aims to match person images captured at several non-overlapping camera views. For this reason, many advanced types of research had been competing to cope with the best solution for identifying multiple persons. Due to the redundant and mismatching which occurred in the traditional individual image matching scheme, the simultaneous image matching [1, 2] provides a solution which could avoid this downside. In this study, we analyze the performance of the simultaneous image matching on various datasets. We also evaluate a new image mask for feature extraction of SDALF.

  87. Analysis of the Eye-gaze Behaviors of Robotic Wheelchair Drivers Considering the Geometric Relation with a Focused Object

    Yamato Maekawa, Naoki Akai, Takatsugu Hirayama, Luis Yoichi Morales, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering  2019.9.10 

     More details

    Event date: 2019

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大同大学  

  88. CityWalks: An Extended Dataset for Attribute-aware Semantic Segmentation

    Mahmud Dwi Sulistiyo, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Takatsugu Hirayama, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering  2019.9.9 

     More details

    Event date: 2019

    Language:English   Presentation type:Oral presentation (general)  

    Venue:大同大学  

  89. Hand Emergence Features in Ego-centric View for Analyzing Cooperative Group Work

    Kazuaki Kondo, Atsushi Shimada, Daisuke Deguchi

    HCG Symposium 2018  2018.12.13 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:シンフォニアテクノロジー響ホール伊勢  

  90. HOYO: A Gait Dataset Annotated with Mimetic Words

    Hirotaka Kato, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2018.9.7 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大阪工業大学  

  91. 地域・時期ごとのSNS投稿写真に基づく類似地域マイニング

    陳 璐, 川西 康友, 井手 一郎, 平山 高嗣, 道満 恵介, 出口 大輔, 村瀬 洋

    電子情報通信学会 魅力工学研究会シンポジウム 2018  2018.9.5 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Poster presentation  

    Venue:大阪工業大学 梅田キャンパス  

  92. 視線情報を利用した料理写真の魅力度推定手法

    佐藤 陽昇, 平山 高嗣, 道満 恵介, 川西 康友, 井手 一郎, 出口 大輔, 村瀬 洋

    電子情報通信学会 魅力工学研究会シンポジウム 2018  2018.9.5 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Poster presentation  

    Venue:大阪工業大学 梅田キャンパス  

  93. A Study on the Detection of Users of White Cane Users focusing on Human Pose

    Naoki Nishida, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Jun Piao

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2018  2018.9.4 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名城大学  

  94. A Study on the Construction of a Traffic Signal Detector by Automatic Accumulation of Training Data Leveraging Driving Behavior Information

    Takuya Migishima, Haruya Kyutoku, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2018  2018.9.3 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名城大学  

  95. オノマトペによる歩容の記述の高精度化に向けた データセットの構築

    加藤 大貴, 平山 高嗣, 道満 恵介, 川西 康友, 井手 一郎, 出口 大輔, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2018.8.8 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Poster presentation  

    Venue:札幌コンベンションセンター  

  96. 同一経路走行映像群からのネガティブサンプル自動抽出による人物検出器の高精度化

    本谷 真志, 久徳 遙矢, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2018.8.8 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Poster presentation  

    Venue:札幌コンベンションセンター  

  97. On Understanding Visual Relationships of Concepts by Visualizing Bag-of-Visual-Words Models

    Marc Aurel Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Hiroshi Murase

    Meeting on Image Recognition & Understanding  2018.8.8 

     More details

    Event date: 2018

    Language:English   Presentation type:Poster presentation  

    Venue:札幌コンベンションセンター  

    Recent applications in image processing often use a multimodal approach using both text and imagery. This is prone to semantic gap issues when converting between image and language. There has been few research quantifiying visual differences when assessing semantic relationships. In this research, we analyze datasets composed of logically related concepts. By visualizing a Bag-of-Visual-Words (BoVW) model spatially, visual semantics of logically related sub-concepts are shown. To find hidden semantics of related concepts, the most common visual words of an image in relation to its neighbors are highlighted. This provides additional semantic knowledge on how sub-ordinate concepts visually relate to another. It is thought to give an insight on the human perception of these concepts, and can be used in future research to estimate psycholinguistic ratings.

  98. Active Scan LIDARによる歩行者の向きを考慮した効率的な歩行者スキャン手法

    山本 大貴, 新村 文郷, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2018.8.7 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Poster presentation  

    Venue:札幌コンベンションセンター  

    近年,LASER 光の照射方向を瞬時かつ任意方向に制御可能な Active Scan LIDAR が開発中であり,局所的にスキャン密度を高めることにより遠距離の歩行者を検出可能になると期待されている.しかし,歩行者を効率的にスキャンする方法は実現されていない.そこで本発表では,歩行者の向き毎に構築した歩行者形状モデルと存在確率に基づいた歩行者尤度推定によるActive Scan LIDAR のための効率的な歩行者スキャン手法を提案する.

  99. Vehicle counting via car parts detection from an in-vehicle camera image International conference

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Workshop on Digital Signal Processing for In-Vehicle Systems  2018.10.8 

     More details

    Event date: 2018

    Language:English   Presentation type:Poster presentation  

    Venue:Nagoya University, Japan  

    This paper proposes a method to count vehicles from an in-vehicle camera image by regression based on car parts detection. In the case of an in-vehicle camera image, since vehicles are frequently occluded by other vehicles in traffic congestion, it is difficult to accurately count vehicles. Therefore, we propose a method to count vehicles by regression based on the number of visible car parts. For this, we make an estimator by learning the relation between the number of visible car parts and that of vehicles by Support Vector Regression. We evaluated our method using in-vehicle camera images recorded in an actual environment, where the proposed method performed better than counting detected vehicles.

  100. 姿勢を表現する多様体に基づくGANsを用いた特定クラス物体姿勢推定の検討

    川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2018.8.6 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Poster presentation  

    Venue:札幌コンベンションセンター  

    Generative Adversarial Nets(GANs)は,ある事前分布から画像などのデータを生成可能なネットワークであり,乱数から様々なデータを生成可能である.本研究では,物体の姿勢変化は潜在的には多様体で表現可能であることに着目し,多様体上に定義した確率分布から画像を生成するGANs の枠組みと,それを用いて学習画像を補間しつつ姿勢推定器を学習する手法を提案する.実験では,提案手法により,同一クラスに属する,学習データに含まれない物体の姿勢が補間できることを確認し,また,生成した画像を用いて姿勢推定器を学習することにより,高精度な姿勢推定ができることを示す.

  101. 車両周辺環境の違いに応じた歩行者検出信頼度の推定

    久徳 遙矢, 川西 康友, 出口 大輔, 井手 一郎, 加藤 一樹, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2018.8.6 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Poster presentation  

    Venue:札幌コンベンションセンター  

    車載カメラを用いた歩行者検出結果は,実環境下において依然として改善の余地がある.
    そこで我々はこれまでに,ある検出器の出力に未検出や誤検出が含まれない可能性を,検出器の出力とは独立に検出器の信頼度として出力するシステムを提案してきた.
    その中で,カメラから得た各画像の走行環境に応じた未検出と誤検出に関する信頼度について定義した.
    本稿では,これらを入力画像から直接推定する信頼度推定器を構築し,実走行データを用いて推定精度を評価した

  102. 車載カメラを用いた自己位置推定と地図構築

    出口 大輔

    第88回産研テクノサロン  2018.8.3 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大阪富国生命ビル  

    近年、自動運転車両や高度運転支援システムの研究開発が盛んであり、その中でも車載カメラを用いた周囲環境理解技術は大きな注目を集めている。自動運転等の応用を考えた場合、正確な自車位置の把握は欠くことのできない最も重要機能の一つである。本講演では、車載カメラを用いた自己位置推定に焦点を当て、車の特徴を活かした系列間照合によって位置推定を高精度に行う手法やそれらの地図構築への応用について紹介する。

  103. Visualization of Real World Activity on Group Work International conference

    Daisuke Deguchi, Kazuaki Kondo, Atsushi Shimada

    20th International Conference on HCI International 2018 (HCII2018)  2018.7.20 

     More details

    Event date: 2018

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Las Vegas, NV, USA  

    Group work is widely introduced and practiced as a method to achieve the learning goal efficiently by collaborating group members. However, since most types of group works are carried out in the real environment, it is very difficult to perform formative assessment and real time evaluation without students' feedbacks. Therefore, there is a strong demand to develop a method that supports evaluation of group work. To support evaluation of group work, this paper proposes a method to visualize the real world activity during group work by using first person view cameras and wearable sensors. Here, the proposed method visualizes three scores: (1) individual attention, (2) hand visibility, (3) individual activity. To evaluate the performance and analyze the relationships between scores, we conducted experiments of Marshmallow challenge" that is a collaborative work to construct a tower using marshmallow and spaghetti within a limit of time. Through the experiments, we confirmed that the proposed method has potential to become a evaluation tool for visualizing the activity of the group work."

    DOI: 10.1007/978-3-319-91131-1_2

  104. Estimating the attractiveness of a boxed lunch focusing on the attributes of side dishes

    Masamu Nakamura, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    2018.6.8 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:国民宿舎 ボルベリアダグリ  

  105. フロントガラスへの映り込みが発生した際の歩行者視認性推定

    森 優介, 平山 高嗣, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    パターン認識・メディア理解研究会(PRMU)  2018.5.18 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:岐阜大学サテライトキャンパス  

  106. Development of 'KamiRepo' System with Automatic Student Identification to Handle Handwritten Assignments on LMS International conference

    Shunya Seiya, Ryuya Ito, Kosuke Okamoto, Ukyo Tanikawa, Shigeki Ohira, Daisuke Deguchi, Tomoki Toda

    2018 the IEEE Global Engineering Education Conference (EDUCON2018)  2018.4.20 

     More details

    Event date: 2018

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Santa Cruz de Tenerife, Canary Islands, Spain  

    A Learning Management System (LMS) has become a fundamental tool for higher education, and a framework to leverage digital education data in the LMS has attracted attention. On the other hand, there is strong demand to deal with various education data provided not only from electronic media but also non-electronic media, such as a handwritten assignment. To solve this problem, this paper describes the development of 'KamiRepo' system to make it possible to automatically upload handwritten assignments to the LMS. In this system, optical character recognition (OCR) is performed to identify scanned handwritten assignments of individual students and read their scores. Then, their scanned files automatically separated from the entire file of the scanned handwritten assignments are returned to the individual students through LMS together with their corresponding scores. Compared with a conventional system using the dedicated multifunction printer, our developed system is capable of 1) using general-purpose scanners, 2) using a user interface on Web browser, and 3) achieving accurate student identification. We have launched this system in our university in April 2017 and have evaluated its effectiveness. The experimental results using real data collected for 6 months showed that our system achieved 99.7% of success rate in the automatic upload process.

  107. A Study on the Detection of Users of Whitecanes focusing on their Properties

    Naoki Nishida, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Shoji Yachida

    2018 IEICE General Conference  2018.3.22 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京電機大学 東京千住キャンパス  

  108. A study on the automatic acquisition of training data for traffic signal detection based on labeling referring to driving information

    Takuya Migishima, Haruya Kyutoku, Daisuke Deguchi, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Hiroshi Murase

    2018 IEICE General Conference  2018.3.22 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京電機大学 東京千住キャンパス  

  109. A Preliminary Study on Estimating the Difficulty of Pedestrian Detection Adaptive to Vehicle Surrounding Environments Measured by LiDAR

    Haruya Kyutoku, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Kazuki Kato, Hiroshi Murase

    IEICE Technical Report (PRMU)  2018.3.18 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:青山学院大学 青山キャンパス  

  110. Similar Geo-Region Mining based on Visual Concepts in Photos from Social Media

    Hiroki Takimoto, Yasutomo Kawanishi, Ichiro Ide, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2018.3.9 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:沖縄産業支援センター  

  111. ライトフィールド情報を活用した局所平面角度の推定とSIFT 特徴対応付けへの応用

    清水 政行, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    動的画像処理実利用化ワークショップ(DIA)  2018.3.8 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:中京大学  

    近年,ライトフィールドカメラが一般に市販されるようになり,ライトフィールド情報を容易に取得する
    ことが可能になった.ライトフィールド情報は空間中の光線情報を記録したものであり,撮影後の後処理によって任意の位置に合焦した画像を生成できるという特徴を有する.本発表では,このライトフィールド情報を活用することによって,画像中の任意の位置における最適な焦点距離と局所平面角度を同時に推定する手法を提案する.具体的には,ライトフィールドカメラの部分開口画像から算出されるSSD(Sum of Squared Difference)が合焦位置で最小になり,かつ,その隣接画素における最適な焦点距離が連続的に変化するというという2 つの性質に着目し,焦点距離と局所平面角度の同時推定手法を提案する.提案手法の有効性を確認するため,実環境において撮影した評価画像を用いて精度の検証を行った.その結果,テクスチャ情報が豊富な領域において良好な推定結果が得られることを確認した.

  112. Improvement of taste estimation from a cooking recipe with an image

    Yoichiro Ito, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2018.3.8 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:沖縄産業支援センター  

  113. Study on the Improvement of Visibility by Projecting Flickering Light from Headlights

    Takashi Maeda, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (MVE)  2018.3.8 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:沖縄産業支援センター  

  114. フロントガラスへの映り込みを考慮した歩行者視認性推定

    森 優介, 出口 大輔, 川西 康友, 平山 高嗣, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2018.3.2 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋工業大学  

    車載カメラなどを用いた歩行者検出によって歩行者の存在を運転者に警告することで,認知誤りによる事故を減らすことができると期待される.しかし,検出した歩行者全てを運転者に警告することは,運転者の集中力低下や苛立ちの原因になる.
    そのため,歩行者の視認性を推定し,視認が困難である歩行者のみを警告する方法が考えられる.
    歩行者の視認性を推定する研究の多くは,入力として鮮明な車載カメラ画像を前提としているが,例えばダッシュボード上の物体がフロントガラスに映り込むことにより視野が妨害されることがある.このような視野への妨害は歩行者の視認性に悪影響を与えると考えられる.
    そこで本研究では,フロントガラスへの映り込みを考慮した歩行者の視認性に着目し,その推定手法を提案する.

  115. 白杖固有の形状と存在範囲に着目した白杖利用者検出

    西田 尚樹, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2018.3.2 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋工業大学  

    駅などの危険な事故が起こりうる環境で白杖利用者を発見することは, 視覚障害者に対して人手の支援をするために重要である.
    しかし, 入力画像全体を探索して検出を行なうと, 背景から白杖以外を誤検出する可能性があり, 精度の高い白杖検出は困難となる.
    そこで我々は, 形状特徴を用いて白杖候補を検出した後,白杖が存在し得る範囲から白杖候補を絞り込むことで, 白杖を高精度に検出する手法を提案する.

  116. 運転者の運転行動情報を利用した信号機検出用学習データの収集

    右島 琢也, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2018.3.2 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋工業大学  

    交通死亡事故は交差点内で最も多く発生しており,交差点内の交通事故を防止するための有効な対策手段が求められている.
    交差点での事故を防止するため,信号機中で点灯している信号灯の色(以下現示色と呼ぶ)に応じ,運転者に詳細な指示を与える運転補助技術が開発されている.
    現示色までを含めて検出・認識する信号機検出器を構築する場合,色カテゴリ毎に位置ラベルを付与した多数の学習データを用意する必要がある.
    しかし,学習データの獲得を人手で行なう場合,大きな労力が必要となる.
    本研究では,信号機がある交差点を通過する際に,信号機の現示色によって運転挙動が異なることに着目することで,現示色を自動的に推定する手法を提案する.
    具体的には,物体検出・追跡の技術を利用して位置ラベルを付与するとともに,運転行動情報を利用して色カテゴリを付与することで,自動的にアノテーションする手法を提案する.

  117. Web画像の分布に基づく単語概念の視覚的な多様性の推定

    カストナー マークアウレル, 井手 一郎, 川西 康友, 平山 高嗣, 出口 大輔, 村瀬 洋

    コンピュータビジョンとイメージメディア研究会(CVIM)  2018.3.1 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:立命館大学  

    近年,画像処理の発展に伴い,自然言語と画像をつなぐ知識が必要になりつつある.概念辞書のようなデータベースは視覚性や画像特徴を考慮していないため,画像から自然な説明文を自動生成する際に障害になっている.そこで本発表では,単語概念の視覚的な多様性を推定する手法を提案する.提案手法では,まず,従来のデータセットに,Web画像の分布で測定した重みを使い,理想に近づくようにデータセットを再構成する.そしてMean-Shift法によって画像特徴のクラスタ数から視覚的な多様性を推定する.クラウドソーシングによる被験者実験を行い,決定した真値を用いた評価では,18語の名詞について従来のデータセットを用いた場合よりも正確に視覚性な多様性を推定できた.

  118. Development of Kamirepo system for connecting paper-based assignments with LMS

    Daisuke Deguchi

    2018.2.28 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  119. A Preliminary Study on Optimizing Person Re-identification using Stable Marriage Algorithm International conference

    Nik Mohd Zarifie Hashim, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    The International Workshop on Frontiers of Computer Vision (IW-FCV) 2018  2018.2.22 

     More details

    Event date: 2018

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Future University Hakodate  

    Person re-identification gains an increasing interest
    in the surveillance image processing field due to its’ importance
    for security. Most approaches to solve the person re-identification
    problem match persons one-by-one. However, redundant match-
    ing where one of the person is selected for the matching pair
    several times often occurs. It also degrades the overall image
    matching performance. To overcome the issue, in this paper,
    we propose a method which solves the person re-identification
    problem for multiple persons simultaneously. Instead of one-
    by-one matching, we consider person re-identification as an
    instance of the Stable Marriage Problem (SMP). The result of an
    experiment showed that the proposed method outperforms some
    of the existing state-of-the-art methods applied to the VIPeR
    dataset.

  120. A study on wheelchair-users detection in a crowded scene by integrating multiple frames

    Ukyo Tanikawa, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tatsuo Akiyama

    IEICE Technical Report (PRMU)  2018.1.18 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大阪府立大学  

  121. Efficient Pedestrian Scanning by Active Scan LIDAR International conference

    Taiki Yamamoto, Fumito Shinmura, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    International Workshop on Advanced Image Technology (IWAIT) 2018  2018.1.8 

     More details

    Event date: 2018

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Chiang Mai  

  122. Pedestrian Detection from Sparse Point-Cloud using 3DCNN International conference

    Yoshiki Tatebe, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Utsushi Sakai

    International Workshop on Advanced Image Technology (IWAIT) 2018  2018.1.8 

     More details

    Event date: 2018

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Chiang Mai  

  123. 地域・時期ごとのSNS投稿写真に基づく類似地域マイニング

    陳 璐, 川西 康友, 井手 一郎, 平山 高嗣, 道満 恵介, 出口 大輔, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2018.8.7 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Poster presentation  

    Venue:札幌コンベンションセンター  

    知らない土地に旅行する際,その土地での旅行計画を円滑に進めるためには,行き先の地域別の雰囲気を理解することが重要である.ある地域が,既に知っている地域の雰囲気と似ていることが分かれば,その地域の雰囲気を直感的に把握できる.従来研究は,地域ごとのSNS 投稿写真を用いて地域間の類似性を計算することにより,雰囲気が似ている場所をマイニングしている.我々はこの研究を発展させ,各写真の撮影時期を考慮し,時期毎の類似地域をマイニングする手法を提案する.

  124. Voting-based Hand-Waving Gesture Spotting from a Low-Resolution Far-Infrared Image Sequence International conference

    Yasutomo Kawanishi, Chisato Toriyama, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

    2018 IEEE International Conference on Visual Communications and Image Processing (VCIP2018)  2018.12.11 

     More details

    Event date: 2018

    Language:English   Presentation type:Oral presentation (general)  

    Venue:永豐棧酒店臺中(臺中,臺灣)  

    We propose a temporal spotting method of a hand gesture from a low-resolution far-infrared image sequence captured by a far-infrared sensor array. The sensor array captures the spatial distribution of far-infrared intensity as a thermal image by detecting far-infrared waves emitted from heat sources. It is difficult to spot a hand gesture from a sequence of thermal images captured by the sensor due to its low-resolution, heavy noise, and varying duration of the gesture. Therefore, we introduce a voting-based approach to spot the gesture with template matching-based gesture recognition. We confirm the effectiveness of the proposed temporal spotting method in several settings.

    DOI: 10.1109/VCIP.2018.8698650

  125. Gaze-inspired Learning for Estimating the Attractiveness of a Food Photo International conference

    Akinori Sato, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    20th IEEE Int. Symposium on Multimedia (ISM2018)  2018.12.10 

     More details

    Event date: 2018

    Language:English   Presentation type:Oral presentation (general)  

    Venue:臺中金典酒店(臺中,臺灣)  

    The number of food photos posted to the Web has been increasing. Most of the users prefer to post delicious-looking food photos. They, however, do not always look delicious. A previous work proposed a method for estimating the attractiveness of food photos, that is, the degree of how much a food photo looks delicious, as an assistive technology for taking a delicious-looking food photo. This method extracted image features from the entire food photo to evaluate the impression. In our work, we conduct a preference experiment where subjects are asked to compare a pair of food photos and measure their gaze. The proposed method extracts image features from local regions selected based on the gaze information and estimates the attractiveness of a food photo by learning regression parameters. Experimental results showed the effectiveness of extracting image features from outside the gaze regions rather than inside them.

    DOI: 10.1109/ISM.2018.00015

  126. Localizing the Gaze Target of a Crowd of People International conference

    Yuki Kodama, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hidehisa Nagano, Kunio Kashino

    International Workshop on Attention/Intention Understanding  2018.12.3 

     More details

    Event date: 2018

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Perth Convention and Exhibition Centre 21 Mounts Bay Rd Perth WA 6000 Australia  

    What target is focused on by many people?
    Analysis of the target is a crucial task, especially in a cinema, a stadium, and so on.
    However, it is very difficult to estimate the gaze of each person in a crowd accurately and simultaneously with existing image-based eye tracking methods, since the image resolution of each person becomes low when we capture the whole crowd with a distant camera.
    Therefore, we introduce a new approach for localizing the gaze target focused on by a crowd of people.
    The proposed framework aggregates the individually estimated results of each person's gaze.
    It enables us to localize the target being focused on by them even though each person's gaze localization from a low-resolution image is inaccurate.
    We analyze the effects of an aggregation method on the localization accuracy using images capturing a crowd of people in a tennis stadium under the assumption that all of the people are focusing on the same target, and also investigate the effect of the number of people involved in the aggregation on the localization accuracy.
    As a result, the proposed method showed the ability to improve the localization accuracy as it is applied to a larger crowd of people.

  127. Campus-wide Implementation of NU Kamirepo System for Handling Handwritten Assignments with an LMS

    Daisuke Deguchi, Shunya Seiya, Shigeki Ohira, Tomoki Toda

    2018.11.19 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

  128. Analyzing Headlight Flicker Patterns for Improving the Pedestrian Detectability from a Driver International conference

    Takashi Maeda, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2018 IEEE 21st International Conference on Intelligent Transportation Systems (ITSC2018)  2018.11.7 

     More details

    Event date: 2018

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Maui, Hawaii, USA  

    In this paper, we analyze headlight flicker patterns which improve the pedestrian detectability from a driver. Recently, headlights are becoming capable of selectively projecting light on a pedestrian in addition to the normal forward projection. However, it is still not clear how the light should be
    projected to effectively improve the visibility of the pedestrian. We actually analyze nine flicker patterns by controlling duty ratios and durations of lighting time, and conduct experiments in field and laboratory settings. As a result, we reveal that a specific fundamental frequency is effective for improving the pedestrian detectability from a driver. We also conclude that the difference between the two settings are not significant.

  129. Attribute-aware Semantic Segmentation of Road Scenes for Understanding Pedestrian Orientations International conference

    Mahmud Dwi Sulistiyo, Yasutomo Kawanishi, Daisuke Deguchi, Takatsugu Hirayama, Ichiro Ide, Jiang-Yu Zheng, Hiroshi Murase

    2018 IEEE 21th International Conference on Intelligent Transportation Systems (ITSC2018)  2018.11.7 

     More details

    Event date: 2018

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Maui, Hawaii, USA  

    Semantic segmentation is an interesting task for many deep learning researchers for scene understanding. However, recognizing details about objects’ attributes can be more informative and also helpful for a better scene understanding in intelligent vehicle use cases. This paper introduces a method for simultaneous semantic segmentation and pedestrian attributes recognition. A modified dataset built on top of the Cityscapes dataset is created by adding attribute classes corresponding to pedestrian orientation attributes. The proposed method extends the SegNet model and is trained by using both the original and the attribute-enriched datasets. Based on an experiment, the proposed attribute-aware semantic segmentation approach shows the ability to slightly improve the performance on the Cityscapes dataset, which is capable of expanding its classes in this case through additional data training.

  130. Estimating the Scene-wise Reliability of LiDAR Pedestrian Detectors International conference

    Haruya Kyutoku, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Kazuki Kato, Hiroshi Murase

    2018 IEEE 21th International Conference on Intelligent Transportation Systems (ITSC2018)  2018.11.7 

     More details

    Event date: 2018

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Maui, Hawaii, USA  

    Nowadays, development of driving support systems and autonomous driving systems have become active.
    Pedestrian detection from in-vehicle sensors is one of the most important technologies for these systems.
    However, outputs of pedestrian detectors can not be fully trusted in real environments.
    Therefore, we propose an estimation system of pedestrian detector's reliabilities for a given scene.
    This paper proposes a scene-wise reliability calculation method for LiDAR-based detectors, and a construction method for their estimators.
    Here, the problem is how we can define the reliability.
    The proposed method defines the reliability considering oversights as the strictest threshold without oversights.
    Meanwhile, it defines the reliability considering false detections as the loosest threshold without false detections.
    Experimental results showed that the proposed method could properly represent the reliability of a given scene, and estimate their reliability.

  131. Estimation of Driver's Insight for Safe Passing based on Pedestrian Attributes International conference

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Takatsugu Hirayama, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    2018 IEEE 21th International Conference on Intelligent Transportation Systems (ITSC2018)  2018.11.6 

     More details

    Event date: 2018

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Maui, Hawaii, USA  

    In order to reduce traffic accidents between a vehicle and a pedestrian, recognition of a pedestrian who has a possibility of collision with a vehicle should be helpful. However, since a pedestrian may suddenly change his/her direction and cross the road, it is difficult to predict his/her behavior directly. Here, we focus on the fact that experienced drivers usually pass by a pedestrian while preparing to step on the brake at any moment when they feel danger. If driver assistant systems can estimate such experienced driver’s decisions, they could early detect the pedestrian in danger of collision. Therefore, we classify the driver’s decisions into three types by referring to the accelerator operation of drivers, and propose a method to estimate the type of the driver’s decision. The drivers are considered to decide their actions focusing on various behaviors and states of a pedestrian, namely pedestrian’s attributes. Since the driver’s decisions change along the timeline, the use of a temporal context is considered to be effective. Thus, in this paper, we propose an estimation method using a recurrent neural network architecture with the pedestrian’s attributes as input. We constructed a dataset collected by experienced drivers in control of the vehicle and evaluated the performance, and then confirmed the effectiveness of the use of pedestrian’s attributes.

  132. 自動運転車両の実現に向けた車載カメラに よる環境理解

    出口 大輔

    日本光学会年次学術講演会  2018.11.2 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:筑波大学東京キャンパス文京校舎  

  133. A Study on Similar Geo-region Mining based on Spatio-temporal Clustering of Social Media Photos

    Chen Lu, Yasutomo Kawanishi, Ichiro Ide, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2018.10.26 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:北海道大学(札幌)  

  134. Estimation of Driver's Behavior based on Pedestrian's Attributes when Passing by a Pedestrian

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Takatsugu Hirayama, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    2018.10.17 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋国際会議場  

  135. Scene-wise Reliability Estimation of Pedestrian Detection using LiDAR

    Haruya Kyutoku, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Kazuki Kato, Hiroshi Murase

    2018.10.17 

     More details

    Event date: 2018

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋国際会議場  

  136. Epipolar geometry-based ego-localization using an in-vehicle monocular camera International conference

    Haruya Kyutoku, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Workshop on Digital Signal Processing for In-Vehicle Systems  2018.10.8 

     More details

    Event date: 2018

    Language:English   Presentation type:Poster presentation  

    Venue:Nagoya University, Japan  

    Nowadays, development of driving support systems and autonomous driving systems have become active.
    Vehicle ego-localization using in-vehicle sensors is one of the most important technologies for these systems.
    Accordingly, various attempts to localize own vehicle from in-vehicle sensors have been made.
    In general, the estimation accuracy of the traveling direction is lower than in the lateral direction.
    Therefore, we propose a highly accurate method for ego-localization of the traveling direction based on epipolar geometry using an in-vehicle monocular camera.
    The proposed method makes correspondences between in-vehicle camera images and database images with location information, and calculates the location using locations annotated to the corresponding database images.
    However, there are many gaps due to the difference of speed and trajectory of vehicles even if the images are obtained along the same road.
    To overcome this problem, the distance between the input image and the database image is calculated by the distance metric based on the epipolar geometry and the local feature method.
    An experiment was conducted using actual images with correct locations, and we confirmed the effectiveness of the proposed method from its results.

  137. Development of NU Server System to Link between Paper Report and LMS

    Shunya Seiya, Ryuya Ito, Kosuke Okamoto, Ukyo Tanikawa, Shigeki Ohira, Daisuke Deguchi, Tomoki Toda

    2017.12.15 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:広島国際会議場  

  138. Detection of Similar Geo-Regions based on Visual Concepts in Social Photos International conference

    Hiroki Takimoto, Magali Philippe, Yasutomo Kawanishi, Ichiro Ide, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    Pacific-Rim Conference on Multimedia (PCM)  2017.9.28 

     More details

    Event date: 2017

    Language:English   Presentation type:Oral presentation (general)  

    Travel destination recommendation is useful to support travel.Considering the recommendation of regions within the destination area to visit, it could be difficult for the users to explicitly indicate their preference.Therefore, we considered that it would be more intuitive to recommend regions in the destination area that are similar to a region already well-known to the user.Thus, in this paper, we propose a method for the detection of similar geo-regions based on Visual Concepts in social photos.We report experimental results and analyses by applying the proposed method to the YFCC100M dataset.

  139. 視点に応じた魅力度が付与された料理画像データセット

    井手 一郎, 髙橋 和馬, 道満 恵介, 川西 康友, 平山 高嗣, 出口 大輔, 村瀬 洋

    電子情報通信学会魅力工学研究会発足記念シンポジウム  2017.9.20 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Poster presentation  

    Venue:千葉大西千葉校舎  

  140. 名古屋大学の事例紹介

    出口 大輔, 宮島 千代美, 武田 一哉

    情報科学技術フォーラム(FIT)  2017.9.12 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京大学  

  141. A Preliminary Study on Construction of a Reliability Estimator Adaptive to Vehicle Environments for Pedestrian Detectors

    Haruya Kyutoku, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Kazuki Kato, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.8 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  142. A Preliminary Study on Impression Description using Bi-directional RNN

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.8 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  143. A Study on Pedestrian Detection using Deep Learning for Low-Resolution LIDAR

    Yoshiki Tatebe, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase, Utsushi Sakai

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.8 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  144. A study on pedestrian detection by ACF using channnel statistics

    Daisuke Deguchi, Haruya Kyutoku, Fumito Shinmura, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.8 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  145. A study on recognition of Texting-While-Walking using the pose and the face orientation

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.8 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  146. Negative samples extraction automatically from multiple image sequences captured on the same route for improving pedestrian detection

    Masashi Hontani, Haruya Kyutoku, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.8 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  147. Preliminary Study of Attribute-aware Semantic Segmentation for Pedestrian Understanding

    Mahmud Dwi Sulistiyo, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.8 

     More details

    Event date: 2017

    Language:English   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  148. A Preliminary Study on the Detection of Wheelchair Users using Faster R-CNN

    Ukyo Tanikawa, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.7 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  149. Analysis on the Relation between Pedestrian's Attributes and the Driver's Behavior when Passing by a Pedestrian

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    2017.10.11 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:グランキューブ大阪  

  150. Improvement of an attractiveness estimation method for food photos considering the appearance of main ingredients

    Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2017.3.6 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:九州大学 大橋キャンパス  

  151. Active Scan LIDARを用いた歩行者検出のための効率的スキャン法

    山本 大貴, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2017.3.3 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

    遠方の歩行者においても局所的にスキャンの密度を高めることが可能なActive Scan LIDARが開発中である.
    本研究では,歩行者の形状や存在確率を用いることで,Active Scan LIDARを用いた歩行者検出のための歩行者に対する効率的なスキャン法を提案する.

  152. インテリジェントヘッドライトのための点滅光照射法の検討

    前田 高志, 平山 高嗣, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2017.3.3 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

    運転者の歩行者視認を支援するために周辺の環境に応じて最適な光を照射する「インテリジェントヘッドライト」を提案する.その実現に向けて,点滅光照射法を検討し,有効な点滅パターンについて分析する.

  153. 人物検出器の高精度化に向けた走行映像群からのネガティブ学習サンプルの抽出手法

    本谷 真志, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2017.3.3 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

    歩行者検出器の高精度化において重要な要素である学習サンプルの質と量の改善に焦点を当て,
    同じ経路を走行した複数の走行映像から歩行者検出器の学習に必要となるネガティブサンプルを自動抽出する手法を提案する.

  154. 撮影支援に向けた料理写真の魅力度推定手法の改良

    佐藤 陽昇, 平山 高嗣, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2017.3.3 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

    本研究では,料理を魅力的に撮影するための支援を目的として,被験者に料理画像選好課題を課して視線情報を計測し,その分析に基づき設定した局所領域からの画像特徴抽出による料理写真の魅力度推定手法を提案した.

  155. Deep Manifold Embedding for 3D Object Pose Estimation International conference

    Hiroshi Ninomiya, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Norimasa Kobori, Yusuke Nakano

    International Conference on Computer Vision Theory and Applications (VISAPP) 2017  2017.3.1 

     More details

    Event date: 2017

    Language:English   Presentation type:Poster presentation  

    DOI: 10.5220/0006101201730178

  156. Can We Detect Pedestrians using Low-resolution LIDAR? International conference

    Yoshiki Tatebe, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Utsushi Sakai

    International Conference on Computer Vision Theory and Applications (VISAPP) 2017  2017.2.28 

     More details

    Event date: 2017

    Language:English   Presentation type:Poster presentation  

    Venue:Porto  

    DOI: 10.5220/0006100901570164

  157. Wheelchair-user Detection Combined with Parts-based Tracking International conference

    Ukyo Tanikawa, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Ryo Kawai

    International Conference on Computer Vision Theory and Applications (VISAPP) 2017  2017.2.28 

     More details

    Event date: 2017

    Language:English   Presentation type:Oral presentation (general)  

    DOI: 10.5220/0006101101650172

  158. Can a Driver Assistance System Determine if a Driver is Perceiving a Pedestrian? International conference

    Yuki Imaeda, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    International Conference on Computer Vision Theory and Applications (VISAPP) 2017  2017.2.27 

     More details

    Event date: 2017

    Language:English   Presentation type:Poster presentation  

    DOI: 10.5220/0006229306110616

  159. A Study on Effective Frequency of Superposed Flickering Headlight for Improving Pedestrian Visibility

    Takashi Maeda, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.7 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  160. Automatic selection of Web contents towards automatic authoring of a video biography International conference

    Ichiro Ide, Yasutomo Kawanishi, Kyoka Kunishiro, Frank Nack, Daisuke Deguchi, Hiroshi Murase

    19th IEEE Int. Symposium on Multimedia (ISM2017)  2017.12.13 

     More details

    Event date: 2017

    Language:English   Presentation type:Oral presentation (general)  

    Venue:臺中金典酒店(臺中,臺灣)  

    DOI: 10.1109/ISM.2017.54

  161. Migration of university-wide file sharing service using OSS

    Takashi Matsuoka, Hisanori Tajima, Nanami Seki, Daisuke Deguchi, Hirokazu Hasegawa

    2017.12.13 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:広島国際会議場  

  162. Survey on Attitudes towards Campus File Sharing Service

    Hisanori Tajima, Takashi Matsuoka, Nanami Seki, Daisuke Deguchi, Hirokazu Hasegawa

    2017.12.13 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:広島国際会議場  

  163. Summarization of news videos considering the consistency of auditory and visual contents International conference

    Ichiro Ide, Ye Zhang, Ryunosuke Tanishige, Keisuke Doman, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

    19th IEEE Int. Symposium on Multimedia (ISM2017)  2017.12.12 

     More details

    Event date: 2017

    Language:English   Presentation type:Oral presentation (general)  

    Venue:臺中金典酒店(臺中,臺灣)  

    DOI: 10.1109/ISM.2017.33

  164. A Collaborative Report on The Open Apereo 2017 Conference

    Yuji Tokiwa, Soichiro Fujii, Daisuke Deguchi, Shoji Kajita

    IPSJ SIG Technical Report (CLE)  2017.12.9 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:松山大学  

  165. A Study on Recognition of Pedestrian's Attribute using Pose Information

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    Vision Engineering Workshop (ViEW)  2017.12.8 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Poster presentation  

    Venue:パシフィコ横浜  

  166. 車載カメラを用いた環境理解

    出口 大輔

    経済情報学会主催セミナー  2017.12.6 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:岐阜聖徳学園大学  

    近年,自動運転に関するニュースを報道で目にする機会が増え,その実現に対する期待も日に日に高まってきている.自動運転の実現には,車が今どこを走行しているかを正確に把握する技術が非常に重要となる.しかしながら,現在広く用いられているGPSのみでは,都市部等で十分な精度での位置計測ができないという問題がある.この問題の解決手段の一つとして,車載カメラを用いた自車位置推定技術が注目を集めている.そこで本講演では,カメラを用いた自車位置推定に焦点を当てるとともに,その関連技術についても紹介する.

  167. Toward Describing Human Gaits by Onomatopoeias International conference

    Hirotaka Kato, Takatsugu Hirayama, Yasutomo Kawanishi, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    2017 IEEE International Conference on Computer Vision (ICCV2017) Workshops  2017.10.28 

     More details

    Event date: 2017

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Venice Convention Center, Venice, Italy  

  168. Estimating the attractiveness of a food photo using a Convolutional Neural Network

    Akinori Sato, Keisuke Doman, Takatsugu Hirayama, Ichiro Ide, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2017.10.20 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

  169. Driver's Decision Analysis in Terms of Pedestrian Attributes -A Case Study in Passing by a Pedestrian- International conference

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    Workshop on Human Factors in Intelligent Vehicles  2017.10.16 

     More details

    Event date: 2017

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Mielparque Yokohama, Kanagawa, Japan  

    In this paper, we report a case study on driver's decision in terms of pedestrian attributes. Among various traffic situations, the situation that a vehicle passes by a pedestrian is one of the major situations. To build a safety driving system that supports a non-experienced driver in such a situation, we analyzed how experienced drivers decide to handle the vehicle in such a situation. Since pedestrian’s behavior can be considered as a key factor for the decision, and also the behavior is different depending on their attributes," such as walking or stopping, noticing the vehicle or not, using a smartphone, etc., we analyzed what pedestrian's attributes affect the driver's decisions. For the analysis, we first built a large-scale dataset of driving data. Using the dataset, we clarified what attributes are dominant for the driver's decision."

  170. A Study on GANs based on Pose Manifold for Rigid Object Pose Estimation

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (PRMU)  2017.10.13 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:熊本大学  

  171. Study on Gaze Target Localization from Low-Resolution Faces of Group of People

    Yuki Kodama, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hidehisa Nagano, Kunio Kashino

    IEICE Technical Report (PRMU)  2017.10.13 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:熊本大学  

  172. A Preliminary Study on Reliability Estimation of Pedestrian Detectors

    Haruya Kyutoku, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Kazuki Kato, Hiroshi Murase

    2017.10.11 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:グランキューブ大阪  

  173. Automatic Selection of Web Contents Towards Automatic Authoring of a Video Biography

    Kyoka Kunishiro, Frank Nack, Ichiro Ide, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2017.3.6 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:九州大学 大橋キャンパス  

  174. Active Scan LIDARを用いた歩行者検出のための効率的スキャン手法

    山本 大貴, 新村 文郷, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    画像センシングシンポジウム(SSII)  2017.6.9 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Poster presentation  

    Venue:パシフィコ横浜アネックスホール  

    LIDAR は,対象までの距離や反射特性を測る環境認識センサであり,対象の 3 次元形状を分析できるため,これを用いた歩行者検出の研究が行われている.近年,LASER 光の照射方向を瞬時に制御可能な Active Scan LIDAR の開発が進められている.本研究では, Active Scan LIDAR を用いて歩行者から効率よく距離データを得るためのスキャン手法の開発を目的とする.
    Active Scan LIDAR を用いた歩行者検出の実現に向けて,歩行者の形状による歩行者尤度推定,及び歩行者存在確率に基づく効率的なスキャン手法を提案する.
    Active Scan LIDARを模擬した評価実験を行ったところ,全体を一定にスキャンする比較手法にくらべ,的中率,領域重なり率,歩行者抽出率すべての向上を確認でき,歩行者を効率的にスキャンできていることを確認した.

  175. Sharing i18n Practices and Issues

    Daisuke Deguchi, Soichiro Fujii, Shoji Kajita, Takahiro Sanada, Yuji Tokiwa

    Open Apereo 2017  2017.6.7 

     More details

    Event date: 2017

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Sheraton Society Hill Hotel in Philadelphia, PA  

    Apereo software are mostly developed in English-speaking countries. Therefore, users and developers rarely face issues caused by i18n and l10n. However, we, living in the non-English-speaking countries, are sometimes in trouble functionally caused by i18n and l10n. And we are continuously translating source code into our own language.

    In this session, three topics will be presented.

    At first, practices to apply IMS LTI and Caliper to existing tools on the Sakai based learning environment will be introduced. we are now encountering several issues caused by the lack of consideration of i18n in the specification. Points to solve these issues will be proposed.
    Next, short stories will be shared to customize and localize Apereo tools to fit a typical usage of Japanese universities. Ideas to eliminate issues in the source codes fundamentally will be described.
    Finally, a translation platform using a Web based translation support system such as Transifex will be explained in detail for those who will begin to translate Apereo software into your own language. In this platform, source code will be cloned from GitHub every night and one thing you should do is only to translate source code using Transifex.

  176. ヘッドライトを用いた歩行者視認性向上のための点滅光照射パターンの検討

    前田 高志, 平山 高嗣, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    コンピュータビジョンとイメージメディア研究会(CVIM)  2017.5.11 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Poster presentation  

    Venue:名古屋大学  

    薄暮時から夜間にかけての対歩行者死亡事故が多発しており,運転者の歩行者視認を支援するシステムへの需要が高まっている.我々はそのシステムとして,視認性が低い歩行者に周辺環境を考慮した最適な光を照射する「インテリジェントヘッドライト」を提案する.本研究ではその実現に向けて,点滅光照射法を検討した.具体的には,連続点灯時間およびデューティ比(1回の点滅における連続点灯時間の割合)を変化させたときの歩行者の視認性の違いを被験者実験により明らかにし,有効な点滅パターンについて分析した.その結果,瞬間的な照射かつ高速な点滅が効果的であり,2Hzの基本周波数を含む点滅において視認性が高くなる傾向が得られた.

  177. 料理写真の魅力度推定手法の改良

    佐藤 陽昇, 平山 高嗣, 髙橋 和馬, 道満 恵介, 川西 康友, 井手 一郎, 出口 大輔, 村瀬 洋

    コンピュータビジョンとイメージメディア研究会(CVIM)  2017.5.11 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Poster presentation  

    Venue:名古屋大学  

    近年,料理レシピサイトやSNSの普及によりWeb上への料理写真の投稿が増加している.Web上に投稿される料理写真は美味しそうに撮影されていることが望ましいが,その撮影は必ずしも容易ではない.従来研究では,料理を美味しそうに撮影するための支援技術として,料理写真の魅力度,つまり撮影された料理が美味しそうに見える度合いを推定する手法が提案されている.この手法では,魅力度付きの料理画像群から画像特徴を抽出し,回帰の枠組みにより任意の料理画像に対して魅力度を推定する.本研究では,閲覧者が一般的に注目する領域を分析し,それに基づいて画像特徴を抽出する領域を選択することにより,料理写真の魅力度推定手法を改良した.まず,画像の選好を評価する被験者実験を行い,魅力度を判断する際の視線情報を計測した.次に,視線の停留状態が続いた領域,すなわち注視領域を分析し,それに基づいて画像特徴の抽出領域を選択した.そして,画像全体から特徴抽出する従来手法と比較した結果から,注視領域外から特徴抽出することが有効であることが確認された.

  178. 人物検出器の高精度化に向けた走行映像群からのネガティブ学習サンプルの自動抽出に基づく人物検出器の追加学習

    本谷 真志, 久徳 遙矢, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    画像センシングシンポジウム(SSII)  2017.5.9 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Poster presentation  

    Venue:パシフィコ横浜アネックスホール  

    近年,運転支援を目的とした車載カメラ映像からの人物検出技術が広く研究されている.一般に,検出器が誤って人物と判定した背景画像(ネガティブ学習サンプル)を追加学習することで,検出器の精度を改善できることが知られている.そこで本発表では,人物検出器の追加学習を行なうために,検出器が誤って人物と判定した背景画像をネガティブ学習サンプルとして自動抽出する手法を提案する.提案手法では,同一地点を長時間観測しても背景領域は大きく変化しないという性質を利用し,同一経路を走行した映像群を比較することでネガティブ学習サンプルを抽出する.そして,抽出したネガティブ学習サンプルを追加学習することにより,検出器の精度向上を図る.提案手法の有効性を確認するため,同一経路を 4 回走行して撮影した映像を用いて提案手法の評価を行なった.その結果,誤って人物を抽出することなくネガティブ学習サンプルの自動収集が可能であり,また得られたサンプルを用いた追加学習により精度が高い検出器を再構築できることを確認した.

  179. A Preliminary Study on Gaze Target Localization from Low Resolution Faces of Group of People

    Yuki Kodama, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hidehisa Nagano, Kunio Kashino

    2017 IEICE General Conference  2017.3.23 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名城大学 天白キャンパス  

  180. A Preliminary Study on Projection of Flickering Light on Pedestrian for Improving Detectability

    Takashi Maeda, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2017 IEICE General Conference  2017.3.23 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名城大学 天白キャンパス  

  181. A Preliminary Study on an Efficient Scanning Method for Pedestrian Detection by Active Scan LIDAR

    Taiki Yamamoto, Fumito Shinmura, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    2017 IEICE General Conference  2017.3.23 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名城大学 天白キャンパス  

  182. A preliminarily study on negative samples extraction from multiple image sequences captured on the same route

    Masashi Hontani, Haruya Kyutoku, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    2017 IEICE General Conference  2017.3.23 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名城大学 天白キャンパス  

  183. 名古屋大学における紙レポートシステムの試験導入と課題

    戸田 智基, 田上 奈緒, 中務 孝広, 松岡 孝, 大平 茂輝, 後藤 明史, 出口 大輔

    Ja Sakai カンファレンス  2017.3.20 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:京都大学学術情報メディアセンター  

  184. Proposal of a spectral random dots marker using local feature for posture estimation International conference

    Norimasa Kobori, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEEE Virtual Reality 2017  2017.3.20 

     More details

    Event date: 2017

    Language:English   Presentation type:Poster presentation  

    Venue:Manhattan Beach Marriott Hotel, Manhattan Beach, CA, USA  

    DOI: 10.1109/VR.2017.7892257

  185. 傘による遮蔽に頑健なパーツ参照型歩行者検出

    新保 祐人, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    動的画像処理実利用化ワークショップ(DIA)  2017.3.9 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:島根県立産業交流会館  くにびきメッセ  

    近年,自動運転の実現に向けて自動車の周囲環境認識に関する研究が盛んに行なわれている.
    その中でも,見落としが重大な事故につながる歩行者の検出は重要な課題である.しかし,傘を差した
    歩行者は,傘によって頭部が遮蔽されるため検出が困難な対象として知られている.そこで本発表で
    は,傘差し歩行者検出の高精度化を目的とし,パーツ参照型歩行者検出手法であるParts Driven Faster
    RCNN を提案する.具体的には,Faster RCNN の候補領域抽出部において,傘と歩行者の関係性を学
    習して傘の候補領域から歩行者の候補領域を推定することにより,頭部が遮蔽された歩行者でも候補領
    域として抽出できるようにする.提案手法の有効性を確認するため,雨天時に撮影した車載カメラ画像
    系列を用いて評価実験を行ない,傘差し歩行者に対して検出精度が向上することを確認した.

  186. Monocular Localization within Sparse Voxel Maps International conference

    David Robert Wong, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2017 IEEE Intelligent Vehicles Symposium (IV2017)  2017.6.12 

     More details

    Event date: 2017

    Language:English   Presentation type:Poster presentation  

    Venue:Redondo Beach, California, USA  

    We introduce a method that uses a single camera to localize a vehicle within a pre-constructed map consisting of a voxel occupancy grid and road-line marker positions. Sophisticated mapping hardware is capable of creating high accuracy 3D maps of road environments, but localizing a vehicle within such maps is one of the challenges at the forefront of automated driving. A solution which is robust to dynamic environments, while using only inexpensive sensors, is a difficult problem. In addition, maps that enable precise localization consume a lot of data which is impractical for the expansive environments encountered in real-world road networks. We show how using the area of edge regions shared between rendered views of a compact voxel map and in-vehicle camera images can be coupled with non-linear optimization methods to determine the camera position and pose.

  187. チャンネル特徴量を用いた歩行者検出技術

    出口 大輔

    技術情報協会セミナー「歩行者検出における画像認識・LIDARの適用技術と自動運転への応用」  2017.1.11 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:日幸五反田ビル  

  188. A Study on an Efficient Pedestrian Scanning Method by Active Scan LIDAR

    Taiki Yamamoto, Fumito Shinmura, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.7 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  189. A food image dataset tagged with attractiveness scores according to view-points (in Japanese)

    Ichiro Ide, Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.7 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Poster presentation  

    Venue:名古屋大学  

  190. An analysis on deep learning based action recognition from extremely low-resolution thermal image sequence

    Takayuki Kawashima, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.7 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Poster presentation  

    Venue:名古屋大学  

  191. Improvement of an attractiveness estimation method of food photos by using gaze information during preference experiments

    Akinori Sato, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.7 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  192. Toward Zero-shot Gaits Translation by Onomatopoeia Based on the Relationship between Phoneme and Body-Parts Movement

    Hirotaka Kato, Takatsugu Hirayama, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017  2017.9.7 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

  193. Action Recognition from Extremely Low-Resolution Thermal Image Sequence International conference

    Takayuki Kawashima, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

    14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS2017)  2017.9.1 

     More details

    Event date: 2017

    Language:English   Presentation type:Poster presentation  

    Venue:Carlo V Castle, Lecce, Italy  

    This paper proposes a Deep Learning-based action recognition method from an extremely low-resolution thermal image sequence. The method recognizes daily actions by humans (e.g. walking, sitting down, standing up, etc.) and abnormal actions (e.g. falling down) without privacy concerns. While privacy concerns can be ignored, it is difficult to compute feature points and to obtain a clear edge of the human body from an extremely low-resolution thermal image. To address these problems, this paper proposes a Deep Learning-based action recognition method that combines convolution layers and an LSTM layer for learning spatio-temporal representation, whose inputs are the thermal images and their frame differences cropped by the gravity center of human regions. The effectiveness of the proposed method was confirmed through experiments.

    DOI: 10.1109/AVSS.2017.8078497

  194. Transifexを利用したコミュニティ翻訳

    出口 大輔

    JTF 翻訳支援ツール説明会  2017.8.21 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:セルリアンタワー  

  195. Estimation of the attractiveness of food photography focusing on main ingredients International conference

    Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    9th Workshop on Cooking and Eating Activities (CEA2017) in conjunction with IJCAI2017  2017.8.20 

     More details

    Event date: 2017

    Language:English   Presentation type:Oral presentation (general)  

    Venue:RMIT Univ. (Melbourne, VIC, Australia)  

    DOI: 10.1145/3106668.3106670

  196. Trajectory Ensemble: カメラネットワーク上での一時的な見えの変化に頑健な多人数追跡

    川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2017.8.10 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:広島国際会議場  

  197. 車両周辺環境の違いに対する歩行者検出器の信頼度推定に関する初期検討

    久徳 遙矢, 川西 康友, 出口 大輔, 井手 一郎, 加藤 一樹, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2017.8.10 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Poster presentation  

    Venue:広島国際会議場  

  198. 3DCNNを用いた低解像度点群からの歩行者検出

    建部 好輝, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋, 酒井 映

    画像の認識・理解シンポジウム(MIRU)  2017.8.9 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Poster presentation  

    Venue:広島国際会議場  

  199. 低解像度顔画像群からの集団の注目位置推定に向けて

    児玉 祐樹, 川西 康友, 平山 高嗣, 出口 大輔, 井手 一郎, 村瀬 洋, 永野 秀尚, 柏野 邦夫

    画像の認識・理解シンポジウム(MIRU)  2017.8.9 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Poster presentation  

    Venue:広島国際会議場  

  200. 超低解像度温度画像系列を用いた家庭内人物行動認識に関する検討

    川島 昂之, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 相澤 知禎, 川出 雅人

    画像の認識・理解シンポジウム(MIRU)  2017.8.9 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Poster presentation  

    Venue:広島国際会議場  

  201. 医用画像処理からの巣立ち

    出口 大輔

    第36回日本医用画像工学会大会(JAMIT2017)  2017.7.29 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    本講演では,医用画像処理に軸足を置いた研究から私自身経験の無いITS研究分野に挑戦したこれまでの経験を紹介するとともに,そこで感じた研究分野を変えることの難しさ,新しいことへの挑戦の楽しさ,人との繋がりの大切さ,などについてまとめる.私自身は,名古屋大学工学部の4年生として鳥脇研究室の門をくぐり,博士号取得まで一貫して医用画像処理,特に気管支内視鏡ナビゲーションシステムの開発と関連するセグメンテーション技術の開発に取り組んできた.その後,縁あってコンピュータービジョン・パターン認識などの研究に軸足を移し,現在ではITSに関連する研究にも取り組んでいる.その間,研究分野を変えることの難しさや,新しいことに挑戦する楽しさを再認識することができた.特に,新しい人との繋がりは自身を大きく成長させてくれたと考えている.このような私自身のこれまでの経験が,今後新しい研究分野に挑戦する研究者の皆様の助けになれば幸いである.

  202. Headgear Recognition by Decomposing Human Images in the Thermal Infrared Spectrum International conference

    Brahmastro Kresnaraman, Yasutomo Kawanishi, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    15th International Conference on Quality in Research (QiR2017)  2017.7.26 

     More details

    Event date: 2017

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Bali, Indonesia  

    Surveillance systems play a critical role in security and surveillance. A surveillance system with cameras that work in the visible spectrum is sufficient for most cases. However, problems may arise during the night, or in areas with less than ideal illumination conditions. Cameras with thermal infrared technology can be a better option in these situations since they do not rely on illumination to observe the environment. Furthermore, in our daily lives, it is common for humans to wear headgears such as glasses, masks, and hats. In surveillance, such headgears can be a hindrance to the identification of a person, and hence pose a certain degree of risk. This is not ideal in areas where the identity of a person is important, for example, in a bank. Therefore, in this paper we propose a headgear recognition method using an innovative decomposition approach on thermal infrared images. The decomposition method is based on Robust Principal Component Analysis, a modification of the popular Principal Component Analysis. The proposed method performs decomposition on a human image and isolates headgears in the image for recognition purposes. Experiments were conducted to evaluate the capability of the proposed method. The results show a positive outcome when compared with other methods.

    DOI: 10.1109/QIR.2017.8168475

  203. Trajectory Ensemble: Multiple Persons Consensus Tracking across Non-overlapping Multiple Cameras over Randomly Dropped Camera Networks International conference

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    1st Workshop on Target Re-Identification and Multi-Target Multi-Camera Tracking  2017.7.21 

     More details

    Event date: 2017

    Language:English   Presentation type:Poster presentation  

    Venue:Hawaii Convention Center  

    Multiple person tracking over a camera network is usually performed by matching person images between adjacent cameras. It easily fails by a temporal appearance change of the persons caused by environmental illumination and observation orientation of a camera. To solve this problem, matching person images across not only adjacent cameras but also cameras multiple hops away in the camera network is effective, but such relaxation of spatiotemporal cues also cause tracking failure due to the increase of matching candidates. To avoid the failure, we introduce Random Camera Drop" to generate different camera networks which relax the spatio-temporal cues partially and randomly. We then, integrate tracking results over the networks to a consensus tracking result by a novel concept "Trajectory Ensemble", an extension of unsupervised ensemble learning for the multiple person tracking over a camera network problem. We evaluated the framework on several virtual datasets generated from a public dataset, "Shinpuhkan 2014 dataset" and confirmed that the proposed method achieves the highest tracking results among several comparative methods."

  204. A study on keypoint matching with light field information

    Masayuki Shimizu, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (PRMU)  2017.6.23 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東北大学  

  205. Toward Description of Gaits by Onomatopoeia Based on the Relationship\\between Phoneme and Body-Parts Movement

    Hirotaka Kato, Takatsugu Hirayama, Yasutomo Kawanishi, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (PRMU)  2017.6.22 

     More details

    Event date: 2017

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東北大学  

  206. Questionnaire survey for utilization of e-textbook in higher education

    Daisuke Deguchi, Takaya Yamazato, Shigeki Ohira, Tomoki Toda, Hidehiro Nakajima, Katsusuke Shigeta, Yoshihiro Okada, Kazutsuna Yamaji

    2016.12.15 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Poster presentation  

    Venue:国立京都国際会館  

  207. A Study on the Detection of Wheelchair Users based on Parts Tracking

    Ukyo Tanikawa, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2016 IEICE General Conference  2016.3.15 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:九州大学 伊都キャンパス  

  208. A classification method of cooking operations based on eye movement patterns International conference

    Hiroya Inoue, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Ninth Biennial ACM Symposium on Eye Tracking Research and Applications (ETRA2016)  2016.3.15 

     More details

    Event date: 2016

    Language:English   Presentation type:Poster presentation  

    Venue:Francis Marion Hotel (Charleston, SC, USA)  

    DOI: 10.1145/2857491.2857500

  209. A study on pedestrian detection using multiple frames obtained from a low resolution LIDAR

    Yoshiki Tatebe, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Utsushi Sakai

    2016 IEICE General Conference  2016.3.15 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:九州大学 伊都キャンパス  

  210. 歩行者の姿勢に注目した「歩きスマホ」認識に関する検討

    新村 文郷, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 藤吉 弘亘

    動的画像処理実利用化ワークショップ(DIA)  2016.3.7 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Poster presentation  

    Venue:岩手大学  

    歩行者の「歩きスマホ」は周囲への注意が疎かになり,自動車の接近に気付きにくくなることから,交通事故に遭う危険性が高い.そのため,車載カメラを用いた歩行者の「歩きスマホ」の認識は,安全運転支援に有効だと考えられる.そこで本発表では,歩行者の「歩きスマホ」を認識する手法を提案する.具体的には,「歩きスマホ」中に見られる特徴的な歩行者の姿勢に注目し,腕と頭の位置の自演知識を用いることで腕と頭の姿勢の共起性を特徴として利用する認識手法を提案する.そして,実験を通して提案手法の有効性を示す.

  211. 誤検出マイニングに基づくシーン適応型歩行者検出の検討

    鈴木 悠暉, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    動的画像処理実利用化ワークショップ(DIA)  2016.3.7 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:岩手大学上田キャンパス  

    近年,車載カメラ画像を用いた安全支援技術に関する研究が盛んに行われている.その中でも歩行者検出は重要な課題であり,様々な手法が提案されている.一般に,走行環境の見えが多様に変化し,それが原因で過検出が増加する.単一の検出器では,全ての走行環境の多様な見えに対応することは困難である.そこで,異なる走行環境下においても似たような誤検出が現れるという性質に着目することで,誤検出の低減を目指す.具体的には,誤検出の種類毎に学習画像をクラスタリングし,各クラスタに対して検出器を構築する.これらの検出器を組み合わせて歩行者検出を行うことにより検出精度向上を図る.提案手法の有効性を確認するために,公開データセットを用いて評価実験を行った.その結果,従来の手法による歩行者検出手法と比べ,提案手法によって検出精度が向上することを確認した.

  212. 高感度・高階調車載カメラ映像を用いた夜間歩行者検出のための予備検討

    川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 藤吉 弘亘

    動的画像処理実利用化ワークショップ(DIA)  2016.3.7 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    自動運転や運転支援のために,車載カメラ映像からの歩行者検出技術の研究が盛んにおこなわれている.特に夜間は道路が暗いため,歩行者の検出が非常に困難である.本研究では,高感度・高階調カメラで観測した夜間の車載カメラ映像に対し,通常のカメラ向けに開発された歩行者検出法を適用するために,前処理としての輝度変換が有効であるかを検討した結果について報告する.

  213. Study on an image selection method towards automatic authoring of video obituary using Web contents

    Kyoka Kunishiro, Frank Nack, Ichiro Ide, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2016.3.7 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名桜大学  

  214. Summarization of news videos based on the consistency of news text and image contents

    Ye Zhang, Ryunosuke Tanishige, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2016.3.7 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名桜大学  

  215. Deformable Part Modelsとパーツ追跡の統合による車椅子利用者の検出に関する検討

    谷川 右京, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2016.3.4 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:愛知県立大学  

  216. オノマトペ表現に対応した歩容映像の識別に関する検討

    加藤 大貴, 平山 高嗣, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2016.3.4 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:愛知県立大学  

  217. 地域別SNS投稿写真の画像内容に基づく特徴が類似する地域の検出に関する検討

    滝本 広樹, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2016.3.4 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:愛知県立大学  

  218. 複数フレーム特徴量を用いた低解像度LIDARによる歩行者検出

    建部 好輝, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2016.3.4 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:愛知県立大学  

  219. 赤外線センサアレイを用いた人物行動認識に関する検討

    川島 昂之, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2016.3.4 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:愛知県立大学  

  220. 輝度明滅による歩行者の強調が見つけやすさに与える影響の分析

    日比 雅仁, 平山 高嗣, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2016.3.4 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

  221. 高階調カメラ画像からの特定物体検出に関する検討

    小松 美穂, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2016.3.4 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:愛知県立大学  

  222. HandWaving Gesture Detection Using a Far-Infrared Sensor Array with Thermo-Spatial Region of Interest International conference

    Chisato Toriyama, Yasutomo Kawanishi, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

    International Conference on Computer Vision Theory and Applications (VISAPP) 2016  2016.2.29 

     More details

    Event date: 2016

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Roma  

    DOI: 10.5220/0005718105450551

  223. Image transformation of eye areas for synthesizing eye-contacts in video conferencing International conference

    Takuya Inoue, Tomokazu Takahashi, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Takayuki Kurozumi, Kunio Kashino

    International Conference on Computer Vision Theory and Applications (VISAPP) 2016  2016.2.29 

     More details

    Event date: 2016

    Language:English   Presentation type:Poster presentation  

    Venue:Roma  

    DOI: 10.5220/0005668702730279

  224. Human Wearable Attribute Recognition using Decomposition of Thermal Infrared Images International conference

    Brahmastro Kresnaraman, Yasutomo Kawanishi, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    22th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2016)  2016.2.19 

     More details

    Event date: 2016

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Takayama, Gifu Prefecture  

    This paper addresses an attribute recognition problem in thermal images, specifically on worn objects such as hat and glasses. Although attribute recognition is a growing research field, there are not much work done in thermal infrared spectrum. In this spectrum, since illumination is not a problem, it could be a better option to be used in nighttime or poorly lit areas. The proposed method uses only the attribute information and excludes the unnecessary information for the recognition. To achieve this, we propose attribute recognition based on feature decomposition using Robust Principal Component Analysis (RPCA). An experiment to evaluate the capability of the proposed method was conducted on the dataset created for this research. The results show that the proposed method outperformed the method without decomposition by 14% in average with a maximum of 27% increase in a specific attribute.

  225. Human Body Segmentation Using Texture Aware Grab-cut and Statistical Shape Models International conference

    Esmaeil Pourjam, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    22th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2016)  2016.2.17 

     More details

    Event date: 2016

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Takayama, Gifu Prefecture  

    Segmentation is one of active areas in computer vision field with application in many areas from entertainment to intelligent vehicles (IVs). Among the objects, humans themselves have always been among the most interested subjects because of
    their special features. Since human body has an articulated structure, modeling and recognizing different variations in the body has proved to be very difficult. Wearing various kinds of clothes in different situations which can have a completely dissimilar appearance based on the clothing type, makes the modeling much more difficult. Add to this, the common problems of vision like illumination changes, blurring due to camera movements, etc. make the problem even more difficult. Thus having a system that can segment human subjects accurately can be useful in many applications. In this paper, we propose a system for segmenting human subjects using Statistical Shapes Models (SSM) feedback and a texture aware version of Grab-cut which incorporates texture feature for improving the segmentation accuracy. Our experiments show that the proposed system has an acceptable accuracy compared to the state-of-the art interactive methods and much better than the conventional ones.

  226. A study on detection of a pedestrian holding an umbrella with a selective DPM

    Yuto Shimbo, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (PRMU)  2016.1.22 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大阪大学 銀杏会館  

  227. A method for gaze correction between video conference participants that synthesizes eye areas image within the perceptual range of eye contact

    Takuya Inoue, Tomokazu Takahashi, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Takayuki Kurozumi, Kunio Kashino

    IEICE Technical Report (PRMU)  2016.1.21 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大阪大学 銀杏会館  

  228. Supervisory Driver Assistance System for Proactive Driving and Its Implementation

    Yoshiki Ninomiya, Eijiro Takeuchi, Yamaguchi Takuma, Fumito Shinmura, Yuki Yoshihara, Yasuhiro Akagi, Yasutomo Kawanishi, Daisuke Deguchi, Soichiro Hayakawa, Tatsuya Suzuki, Hiroshi Murase, Shota Matsubayashi, Kazuhisa Miwa

    2016.10.19 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

  229. ファイル共有サービスの運用状況

    松岡 孝, 田島 尚徳, 出口 大輔, 森 健策

    大学ICT推進協議会(AXIES)  2016.12.14 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:国立京都国際会館  

    近年,教育研究活動に関連する様々なデータを適切に管理することが強く求められている.この問題の解決を目指し,名古屋大学では教育研究に関わるデータの保存場所を組織的に整備する取り組みを行っている.平成27年4月より本運用を開始した本サービスの内容,システム構成,運用状況等について報告する.

  230. Webコンテンツを用いた人物紹介映像の自動編集に向けて

    國代 京花, ナックフランク, 井手 一郎, 川西 康友, 出口 大輔, 村瀬 洋

    HCGシンポジウム  2016.12.8 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:高知市文化プラザかるぽーと  

  231. Relationship between Phonetic-Space and Body-Parts Movement for Description of Gaits by Onomatopoeia

    Hirotaka Kato, Takatsugu Hirayama, Yasutomo Kawanishi, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    2016.12.7 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:高知市文化プラザかるぽーと  

  232. Misclassification Tolerable Learning for Robust Pedestrian Orientation Classification International conference

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    International Conference on Pattern Recognition (ICPR)  2016.12.5 

     More details

    Event date: 2016

    Language:English   Presentation type:Poster presentation  

    Venue:Cancun, Mexico  

    In this paper, we propose a multiclass classifier training method which reduces fatal" misclassifications by cost-relaxation of "tolerable" misclassifications in one-against-all classifiers training, named misclassification tolerable learning. In a binary classifier in the one-against-all classifiers, we introduce a new class group "conceptually similar classes," whose class labels are similar to the positive class. In the case of pedestrian orientation classification, the conceptually similar classes are defined as neighboring orientations to the positive orientation. We consider the misclassification of the conceptually similar classes to the positive class as tolerable misclassification. By relaxing the cost of the tolerable misclassifications, our proposed classification method reduces fatal misclassifications of non-similar classes. We evaluated the cost-relaxation effectiveness on several public datasets and confirmed that the proposed method outperforms the normal SVM on all of the datasets in the soft criterion by achieving 78.63% recognition rate on PDC Dataset."

  233. Recognition of Texting-While-Walking by Joint Features based on Arm and Head Poses International conference

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    2016.11.20 

     More details

    Event date: 2016

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Taipei, Taiwan  

    Pedestrians texting-while-walking" increase the risk of traffic accidents, since they are often not paying attention to their surrounding environments and fails to notice approaching vehicles. Thus, the recognition of texting-while-walking from an in-vehicle camera should be helpful for safety driving assistance. In this paper, we propose a method to recognize a pedestrian texting-while-walking from in-vehicle camera images. The proposed approach focuses on the characteristic relationship between the arm and the head poses observed during a texting-while-walking behavior. In this paper, Pose-Dependent Joint HOG feature is proposed as a novel feature, which uses parts locations as prior knowledge and describes the cooccurrence of the arm and the head poses. To show the effectiveness of the proposed method, we constructed a dataset and evaluated it."

  234. A Preliminarily Study on Pedestrian Detectability Estimation Considering Visual Adaptation to Lighting Changes

    Yuki Imaeda, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (PRMU)  2016.10.21 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:宮崎大学  

  235. Pedestrian Recognition for Proa ctive Driving Support System

    Fumito Shinmura, Haruya Kyutoku, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Fukui, Yuji Yamauchi, Takayoshi Yamashita, Hironobu Fujiyoshi, Hiroshi Murase

    2016.10.19 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:札幌コンベンションセンター  

  236. 輝度の明滅が歩行者の見つけやすさに与える影響の初期検討

    日比 雅仁, 平山 高嗣, 出口 大輔, 川西 康友, 井手 一郎, 村瀬 洋

    電子情報通信学会総合大会  2016.3.15 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:九州大学  

  237. Obstacle detection with train frontal view camera

    Hiroki Mukoujima, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Masato Ukai, Nozomi Nagamine, Ryuta Nakasone

    19th Meeting on Image Recognition & Understanding (MIRU2016)  2016.8.3 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Poster presentation  

    Venue:アクトシティ浜松  

  238. A study on detection of pedestrians using umbrellas from an in-vehicle camera

    Yuto Shimbo, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    19th Meeting on Image Recognition & Understanding (MIRU2016)  2016.8.2 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Poster presentation  

    Venue:アクトシティ浜松  

  239. A study on estimating the attractiveness of food images for photography assistance

    Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    19th Meeting on Image Recognition & Understanding (MIRU2016)  2016.8.2 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Poster presentation  

    Venue:アクトシティ浜松  

  240. Image Selection Method with Object Recognition towards Automatic Authoring Of Video Obituary using Web Contents

    Kyoka Kunishiro, Frank Nack, Ichiro Ide, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

    19th Meeting on Image Recognition & Understanding (MIRU2016)  2016.8.2 

     More details

    Event date: 2016

    Language:Japanese  

    Venue:アクトシティ浜松  

  241. Parts Selective DPM for detection of pedestrians possessing an umbrella International conference

    Yuto Shimbo, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2016 IEEE Intelligent Vehicles Symposium (IV2016)  2016.6.19 

     More details

    Event date: 2016

    Language:English   Presentation type:Poster presentation  

    Venue:Gothenburg, Sweden  

    In recent years, pedestrian detection from an invehicle camera has been attracting attention.However, in the case of a raining situation, the detection accuracy decreases because the head of a pedestrian tends to be occluded by an umbrella. In oder to handle such cases, in this paper, as a variation of the Deformable Part Model (DPM) which is widely used in the field of object recognition, we propose Parts Selective DPM (PS-DPM)" which selectively chooses the original part filters and additional part filters trained independently. In the detection of pedestrians possessing an umbrella, the selection of head and umbrella parts will make pedestrian detection more robust to the occlusion. We conducted experiments to evaluate the performance of the proposed method. As a result, pedestrian detection with the proposed PS-DPM achieved high detection accuracy in rainy weather, compared with the detection by the conventional DPM. Moreover, we confirmed that it did not decrease the pedestrian detection accuracy in fine weather."

  242. A Study on Activity Recognition based on Temporal Change of the Temperature Distribution obtained from a Far-Infrared Sensor Array

    Takayuki Kawashima, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

    IEICE Technical Report (PRMU)  2016.6.14 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:NTT武蔵野研究開発センタ  

  243. A Study on the Detection of Wheelchair Users Combined with Parts Tracking

    Ukyo Tanikawa, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Ryo Kawai, Toshikazu Sekiya

    IEICE Technical Report (PRMU)  2016.6.14 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:NTT武蔵野研究開発センタ  

  244. Preliminary study on deep manifold embedding for 3D object pose estimation

    Hiroshi Ninomiya, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Norimasa Kobori, Kunimatsu Hashimoto

    IEICE Technical Report (PRMU)  2016.6.13 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:NTT武蔵野研究開発センタ  

  245. A Study on the Calculation of Geo-Regional Similarity based on the Contents of Social Photos

    Hiroki Takimoto, Yasutomo Kawanishi, Ichiro Ide, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2016.6.2 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:岩手大学アイーナキャンパス  

  246. Ja Sakai Panel Session

    Daisuke Deguchi, Soichiro Fujii, Hisashi Hatakeyama, Shoji Kajita, Yuji Tokiwa

    Open Apereo 2016  2016.5.25 

     More details

    Event date: 2016

    Language:English   Presentation type:Oral presentation (general)  

    Venue:New York University (Kimmel Centre for University Life)  

    Ja Sakai is a regional community of Apereo Foundation in Japan and coordinating activities in Japanese universities and affiliates. In addition to i18n contribution, several unique projects are carried on. In this panel session we will talk about the following; (1) Community translation using Transifex (2) LTI based presentation evaluation tool (3) Showcase of Sakai in universities (4) Learning analysis using IMS Caliper

  247. 人体部位の相対的位置関係を利用したオノマトペ歩容映像の識別に関する検討

    加藤 大貴, 平山 高嗣, 川西 康友, 道満 恵介, 井手 一郎, 出口 大輔, 村瀬 洋

    コンピュータビジョンとイメージメディア研究会(CVIM)  2016.5.12 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Poster presentation  

    Venue:立命館大学  

  248. A study on estimating the attractiveness of food photography International conference

    Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    2016 IEEE Second International Conference on Multimedia Big Data  2016.4.22 

     More details

    Event date: 2016

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Taipei, Taiwan  

    This paper proposes a method for estimating the attractiveness of food photos in order to assist a user to shoot them attractively.
    The proposed method extracts both color and shape features from input food images, and then integrates them according to a regression scheme.
    By this way, the proposed method estimates the attractiveness of an unknown food photo.
    We also created a food image dataset taken from various 3D-angles for each food category, and set target values of their attractiveness through subjective experiments.
    Then, we evaluated the performance of the proposed method in two different ways of constructing the attractiveness estimator: One that constructs it for each food category, and the other that constructs a common attractiveness estimator for all food categories.
    Experimental results showed the effectiveness of the proposed method in addition to the necessity for adaptively selecting the estimator depending on the appearance of foods for further performance improvement.

  249. A Study on Activity Recognition based on Body Segmentation Using a Far-Infrared Sensor Array

    Takayuki Kawashima, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2016 IEICE General Conference  2016.3.17 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:九州大学 伊都キャンパス  

  250. A Study on Deep Manifold Embedding for 3D Object Pose Estimation

    Hiroshi Ninomiya, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Norimasa Kobori, Kunimatsu Hashimoto

    2016 IEICE General Conference  2016.3.16 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:九州大学 伊都キャンパス  

  251. A Study on Specific Object Detection under Extreme Lighting Conditions by HDR Camera

    Miho Komatsu, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2016 IEICE General Conference  2016.3.16 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:九州大学 伊都キャンパス  

  252. 致命的な誤認識を低減する多クラス分類器学習法による行動予測のための歩行者の向き認識

    川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 藤吉 弘亘

    画像の認識・理解シンポジウム(MIRU)  2016.8.3 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Poster presentation  

  253. エピポーラ幾何に基づく画像間距離と車載カメラ映像データベースを用いた詳細な自車位置推定

    久徳 遙矢, 川西 康友, 出口 大輔, 目加田 慶人, 井手 一郎, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2016.8.4 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Poster presentation  

    Venue:アクトシティ浜松  

    本発表では,正面向き車載カメラで撮影した画像を入力とし,位置情報付き車載カメラ映像データベースとの比較により詳細な自車位置を推定する手法について報告する.
    我々はこれまでに,フレーム対毎に算出するエピポーラ幾何に基づくフレーム間距離を用い,DPマッチングによりフレームの対応を求める手法を提案した.
    また,このDPマッチングのための端点を高精度に与えるため,フレーム間距離の性質を用いた距離尺度の拡張を行なった.
    これらの手法は,入力フレームと最も近い位置で撮影されたデータベース中のフレームを求めることを目的としている.
    すなわち,算出可能な位置情報の精度は,車載カメラ映像データベースの撮影間隔に強く依存する.
    そこでこれらの手法を拡張し,車載カメラ映像データベースの撮影間隔より詳細な位置情報を算出するための手法を提案する.
    提案手法では,エピポーラ幾何に基づくフレーム間距離とカメラ間の距離が比例関係を持つ性質から,線形関数フィッティングによって自車位置を推定する.
    実験から,データベースの撮影間隔の10倍詳細な位置情報を正解率80%で取得できることを確認した.

  254. 先読み運転支援のための車載カメラからの「歩きスマホ」認識に関する検討

    新村 文郷, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 藤吉 弘亘

    画像の認識・理解シンポジウム(MIRU)  2016.8.4 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Poster presentation  

    Venue:アクトシティ浜松(静岡県浜松市)  

  255. A study on deep manifold embedding for object pose estimation

    Hiroshi Ninomiya, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Norimasa Kobori, Kunimatsu Hashimoto

    19th Meeting on Image Recognition & Understanding (MIRU2016)  2016.8.4 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Poster presentation  

    Venue:アクトシティ浜松  

  256. A Preliminarily Study on Multi-Frames Features for LIDAR-Based Pedestrian Detection

    Yoshiki Tatebe, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Utsushi Sakai

    IEICE Technical Report (PRMU)  2016.9.5 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:富山大学  

  257. Subjective Sensing of Real World Activity on Group Study International conference

    Daisuke Deguchi, Kazuaki Kondo, Atsushi Shimada

    18th International Conference on Collaboration Technologies (CollabTech2016)  2016.9.16 

     More details

    Event date: 2016

    Language:English   Presentation type:Poster presentation  

    Venue:しいのき迎賓館, 金沢市  

    Collaborative learning is efficient teaching/learning method, and it is widely introduced and practiced in various situations. However, it has a difficulty to perform formative assessment and real time evaluation without students' feedbacks. Therefore, demand for technologies to support formative assessment in collaborative learning is increasing. To tackle this problem, we have started the research project for automatic sensing and visualization of real world activities in collaborative learning. In this paper, we will report details about preliminary group work experiments and its results with visualization tool.

  258. A Study for Applications of the Detection Method of Similar Geo-Regions based on Photographic Contents

    Hiroki Takimoto, Yasutomo Kawanishi, Ichiro Ide, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2016.10.13 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:支笏湖丸駒温泉  

  259. Accuracy improvement of food photo attractiveness estimation based on consideration of image features

    Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2016.10.13 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:支笏湖丸駒温泉  

  260. The proposal of encoding marker using local feature for posture estimation (in Japanese)

    Norimasa Kobori, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (IE)  2016.10.6 

     More details

    Event date: 2016

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:福岡大学  

  261. Moving camera background-subtraction for obstacle detection on railway tracks International conference

    Hiroki Mukoujima, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Masato Ukai, Nozomi Nagamine, Ryuta Nakasone

    2016 IEEE International Conference on Image Processing (ICIP2016)  2016.9.25 

     More details

    Event date: 2016

    Language:English   Presentation type:Poster presentation  

    Venue:Phoenix, Arizona, USA  

    This paper proposes a method for detecting obstacles using train frontal view videos.
    In recent years, obstacles detection using in-vehicle camera is actively developed for satisfying demands from various applications.
    In the field of obstacle detection, most methods employ machine learning approach, and they can detect only trained obstacles, such as pedestrian, bicycle, etc.
    Therefore, they cannot detect untrained general obstacles.
    To overcome this problem, this paper propose a background subtraction method using moving camera.
    The proposed method first computes frame-by-frame correspondences between the present and the database train frontal view image sequences, and detects obstacles by applying image subtraction to corresponding frames.
    To confirm the effectiveness of the proposed method, experiments were conducted by using several image sequences captured at the experimental railroad track.
    The experimental result showed that the proposed method could detect various obstacles accurately and effectively.

    DOI: 10.1109/ICIP.2016.7533104

  262. Pedestrian Attributes Recognition from an Image: A Survey

    Yasutomo Kawanishi, Fumito Shinmura, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (PRMU)  2015.12.22 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

  263. Taste and Texure Estimation of Food Based on Food Image and Ingredients List

    Hiroki Matsunaga, Keisuke Doman, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2015.3.3 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:成蹊大学  

  264. Toward understanding cooking activities based on gaze analysis

    Hiroya Inoue, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2015.3.3 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:成蹊大学  

  265. Typicality Analysis of the Combination of Ingredients in Cooking Recipes

    Satoshi Yokoi, Keisuke Doman, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2015.3.3 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:成蹊大学  

  266. A Study on Human Tracking using a Far-Infrared Sensor Array and a Thermo-Spatial Sensitive Histogram

    Takashi Hosono, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

    IEICE Technical Report (PRMU)  2015.1.23 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:奈良先端科学技術大学院大学  

  267. A study on detection of the type of a baggage utilizing multiple-viewpoints human images

    Yasuhiro Asai, Kento Nishibori, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (PRMU)  2015.1.23 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:奈良先端科学技術大学院大学  

  268. A study on hand waving gesture recognition by thermo-spatial restriction using a far-infrared sensor array

    Chisato Toriyama, Takashi Hosono, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (PRMU)  2015.1.22 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:奈良先端科学技術大学院大学  

  269. Cooking Operation Classification Based on Analysis of Eye Movement Patterns

    Hiroya Inoue, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    2015.12.16 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:富山国際会議場  

  270. Summarization of multiple news videos based on term scores using responses of SNS users

    Kosuke Kato, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2015.3.3 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:成蹊大学  

  271. Pedestrian's Inattention Estimation based on Recognition of Texting While Walking from In-Vehicle Camera Images

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    IEICE Technical Report (PRMU)  2015.6.18 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:新潟大学駅南キャンパス「ときめいと」  

  272. A study on analyzing the attractiveness of food photos using image features

    Kazuma Takahashi, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    2015.6.11 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:熊本  

  273. A study on selecting scenes that match the news contents for news video summarization

    Ye Zhang, Ryunosuke Tanishige, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2015.6.9 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:出雲科学館  

  274. Translating Apereo Software: A Case Study using Sakai and Transifex International conference

    Yuji Tokiwa, Daisuke Deguchi, Juan Jose Merono Sanchez, Jose Mariano Lujan Gonzalez, Diego del Blanco Orobitg

    Open Apereo 2015  2015.6.3 

     More details

    Event date: 2015

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Baltimore, Maryland, USA  

    Web based translation support systems such as Crowdin and Transifex make it easy for regional Sakai communities to collaborate globally in translation. In the fall and winter of 2014, Spanish Sakai community and Japanese Sakai community are collaborating in translation of Sakai 10 using Transifex as a common translation platform. This collaboration brought a lot of things to two communities. For instance, to develop a tool to import resource bundle files to Transifex in a specific manner, we can have an ease of use platform to translate modular designed software such as Sakai. And this platform will be extended for every regional community and for every project in Apereo community.
    During this session we will talk about followings;
    (1) Overview
    (2) Benefits for Apereo community
    (3) Context dependent translation by gettext Portable Object
    (4) Community translation strategy in Sakai Spanish Users (S2U)
    (5) Automatized process by Jenkins

  275. A Study on Removal of Temporal Objects from Image Sequences Based on Adaptive Background Selection

    Toru Kotsuka, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (PRMU)  2015.3.20 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:慶應義塾大学  

  276. A study on construction of pedestrian detectors adaptive to driving environment referring to false detection tendency

    Yuki Suzuki, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (PRMU)  2015.3.20 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:慶応大学矢上キャンパス  

  277. A study on the predicition of driver's pedestrian detectability considering characteristics of human fields-of-view while driving

    Ryunosuke Tanishige, Keisuke Doman, Daisuke Deguchi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (PRMU)  2015.3.20 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:慶応大学矢上キャンパス  

  278. Adaptive Reference Image Selection for Temporal Object Removal from Frontal In-vehicle Camera Image Sequences International conference

    Toru Kotsuka, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    International Conference on Computer Vision Theory and Applications (VISAPP) 2015  2015.3.14 

     More details

    Event date: 2015

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Berlin  

    In recent years, image inpainting is widely used to remove undesired objects from an image. Especially, the removal of temporal objects, such as pedestrians and vehicles, in street-view databases such as Google Street View has many applications in Intelligent Transportation Systems (ITS). To remove temporal objects, Uchiyama et al. proposed a method that combined multiple image sequences captured along the same route. However, when spatial alignment inside an image group does not work well, the quality of the output image of this method is often affected. For example, large temporal objects existing in only one image create regions that do not correspond to other images in the group, and the image created from aligned images becomes distorted. One solution to this problem is to select adaptively the reference image containing only small temporal objects for spatial alignment. Therefore, this paper proposes a method to remove temporal objects by integration of multiple image sequences with an adaptive reference image selection mechanism.

    DOI: 10.5220/0005357102330239

  279. A Preliminary Study on Human Attribute Classification in Thermal Image

    Brahmastro Kresnaraman, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

    2015 IEICE General Conference  2015.3.12 

     More details

    Event date: 2015

    Language:English   Presentation type:Oral presentation (general)  

    Venue:立命館大学 びわこ・くさつキャンパス  

  280. A Preliminary Study on the Construction of Pedestrian Detectors Referring to False Positive Tendency

    Yuki Suzuki, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2015 IEICE General Conference  2015.3.12 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:立命館大学 びわこ・くさつキャンパス  

  281. A Study on Frame Alignment between Present and Past Train Frontal View Videos

    Hiroki Mukoujima, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Masato Ukai, Nozomi Nagamine

    2015 IEICE General Conference  2015.3.12 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:立命館大学 びわこ・くさつキャンパス  

  282. A Study on the Detection of Pedestrians holding an Umbrella based on Generative Learning

    Yuto Shimbo, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2015 IEICE General Conference  2015.3.12 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:立命館大学 びわこ・くさつキャンパス  

  283. Estimation of Human Orientation using Coaxial RGB-Depth Images International conference

    Fumito Shinmura, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    International Conference on Computer Vision Theory and Applications (VISAPP) 2015  2015.3.12 

     More details

    Event date: 2015

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Berlin  

    Estimation of human orientation contributes to improving the accuracy of human behavior recognition. However,
    estimation of human orientation is a challenging task because of the variable appearance of the human
    body. The wide variety of poses, sizes and clothes combined with a complicated background degrades the
    estimation accuracy. Therefore, we propose a method for estimating human orientation using coaxial RGBDepth
    images. This paper proposes Depth Weighted Histogram of Oriented Gradients (DWHOG) feature
    calculated from RGB and depth images. By using a depth image, the outline of a human body and the texture
    of a background can be easily distinguished. In the proposed method, a region having a large depth gradient
    is given a large weight. Therefore, features at the outline of the human body are enhanced, allowing robust
    estimation even with complex backgrounds. In order to combine RGB and depth images, we utilize a newly
    available single-chip RGB-ToF camera, which can capture both RGB and depth images taken along the same
    optical axis. We experimentally confirmed that the proposed method can estimate human orientation robustly
    to complex backgrounds, compared to a method using conventional HOG features.

    DOI: 10.5220/0005305301130120

  284. A preliminary Study on the Effect of a Secondary Task while Driving on Pedestrian Detectability

    Yuki Imaeda, Ryunosuke Tanishige, Takatsugu Hirayama, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2015 IEICE General Conference  2015.3.11 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:立命館大学 びわこ・くさつキャンパス  

  285. 傘と歩行者の位置関係を考慮した生成型学習法による傘差し歩行者検出

    新保 祐人, 出口 大輔, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2015.3.9 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:豊橋技術科学大学  

  286. 撮影角度による見えの違いに注目した料理写真の魅力度分析

    髙橋 和馬, 村瀬 洋, 井手 一郎, 出口 大輔

    電子情報通信学会東海支部卒業研究発表会  2015.3.9 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:豊橋技術科学大学  

  287. 現在と過去の列車前方映像間のフレーム対応付けによる走行位置推定

    向嶋 宏記, 村瀬 洋, 井手 一郎, 出口 大輔

    電子情報通信学会東海支部卒業研究発表会  2015.3.9 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:豊橋技術科学大学  

  288. 運転時のサブタスクを考慮した歩行者の見落としやすさ推定

    今枝 祐綺, 平山 高嗣, 出口 大輔, 井手 一郎, 村瀬 洋

    電子情報通信学会東海支部卒業研究発表会  2015.3.9 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:豊橋技術科学大学  

  289. Introduction of video streaming service linked with Sakai at Nagoya University

    Akifumi Goto, Yoshihiro Ohta, Takahiro Nakatsukasa, Nao Tanoue, Shigeki Ohira, Daisuke Deguchi, Kensaku Mori

    Ja Sakai Annual Conference 2015  2015.3.9 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:法政大学  

  290. Pedestrian Orientation Classification Utilizing Single-Chip Coaxial RGB-ToF Camera International conference

    Fumito Shinmura, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    Workshop on Environment Perception for Automated On-road Vehicles in conjunction with 2015 IEEE Intelligent Vehicles Symposium (IV2015)  2015.6.28 

     More details

    Event date: 2015

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Seoul, Korea  

    This paper proposes a method for pedestrian orientation classification. In image recognition, the accuracy is often degraded by the influence of background. In addition, it is also difficult to remove the background and extract only the human body from an image. To overcome these problems, we utilize a single-chip RGB-ToF camera. This camera can acquire RGB and depth images along the same optical axis at the same moment, and thus segmentation of the RGB image becomes easier by using the coaxial depth image. Our proposed method segmented a human body from its background accurately, which lead to the improvement of the accuracy of pedestrian orientation classification.

  291. Position Interpolation using Feature Point Scale for Decimeter Visual Localization International conference

    David Robert Wong, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2015 IEEE International Conference on Computer Vision (ICCV2015) Workshops  2015.12.12 

     More details

    Event date: 2015

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Santiago, Chile  

    Vehicle ego-localization is a critical task not only for in-car navigation systems, but also for emerging intelligent and autonomous vehicle technologies. Visual localization methods that determine current location by performing image matching against a pre-constructed database have an accuracy limited by the spatial distance between database images. In this paper we propose a method that uses the scale of feature points to interpolate the position of the query image between two database images. We show how this simple contribution offers an appreciable improvement in localization accuracy with an extremely minimal increase in processing time, especially when used in conjunction with image matching methods that already monitor feature scale. Our experiments showed an increase of up to 33\% in average localization accuracy when compared to a method without any interpolation.

  292. A Collaborative Report on The Open Apereo 2015 Conference

    Soichiro Fujii, Yuji Tokiwa, Daisuke Deguchi, Shoji Kajita

    IPSJ SIG Technical Report (CLE)  2015.12.6 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

  293. 列車前方映像を用いた時空間差分による障害物検出に関する検討

    向嶋 宏記, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 鵜飼 正人, 長峯 望, 中曽根 隆太

    ビジョン技術の実利用ワークショップ(ViEW)  2015.12.3 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Poster presentation  

    Venue:パシフィコ横浜  

  294. 情報サービスの安定運用と迅速な障害対応を目的とした機器情報管理データベースの構築

    川田 良文, 出口 大輔, 渥美 紀寿, 加藤 芳秀, 嶋田 創, 荻野 正雄, 小川 泰弘, 大野 誠寛, 服部 昌祐, 山田 一成

    大学ICT推進協議会(AXIES)  2015.12.3 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Poster presentation  

    Venue:ウインクあいち  

    名古屋大学情報連携統括本部では、学内向けに種々の情報サービスを提供している。昨今、サービスの多様化に伴って発生するシステムのトラブルの複雑化が大きな問題となっている。そこで、情報サービスに必要なリソースを可視化し、サービスの安定運用と迅速な障害対応を行う取り組みを行っている。昨年度は、機器情報管理データベースの構築に加え、機器情報とサービスを関連付ける機能の実装を行った。本発表では、機器情報管理データベースの機能と運用方法について報告する。

  295. 赤外線センサアレイを用いた温度と空間の絞り込みによる手振り動作検出

    鳥山 千智, 川西 康友, 高橋 友和, 出口 大輔, 井手 一郎, 村瀬 洋, 相澤 知禎, 川出 雅人

    ビジョン技術の実利用ワークショップ(ViEW)  2015.12.3 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Poster presentation  

    Venue:パシフィコ横浜  

  296. Detector Ensemble based on False Positive Mining for Pedestrian Detection International conference

    Yuki Suzuki, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    3rd IAPR Asian Conference on Pattern Recognition (ACPR2015)  2015.11.6 

     More details

    Event date: 2015

    Language:English   Presentation type:Poster presentation  

    Venue:ALOFT KUALA LUMPUR SENTRAL (Kuala Lumpur, Malaysia)  

  297. Generation of a video summary on a news topic based on SNS responses to news stories International conference

    Kosuke Kato, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    Proc. 4th Int Workshop on Crowdsourcing for Multimedia (CrowdMM'15) in conjunction with ACMMM2015  2015.10.30 

     More details

    Event date: 2015

    Language:English   Presentation type:Poster presentation  

    Venue:Brisbane Convention and Exhibition Centre (Brisbane, QLD, Australia)  

    DOI: 10.1145/2810188.2810189

  298. A study on estimating the attractiveness of food photography composition

    Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2015.10.8 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:小樽  

  299. 終端フリーDPを用いた列車前方映像の照合による走行位置推定に関する検討

    向嶋 宏記, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 鵜飼 正人, 長峯 望, 中曽根 隆太

    電気・電子・情報関係学会東海支部連合大会  2015.9.29 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋工業大学  

  300. A study on pedestrian detection in raining condition considering the positional relationship of an umbrella and a pedestrian

    Yuto Shimbo, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2015  2015.9.29 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋工業大学  

  301. Distant Pedestrian Re-Detection from an in-Vehicle Camera based on Detections by Other Vehicles International conference

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    2015 IEEE Conference on Intelligent Transportation Systems (ITSC2015)  2015.9.16 

     More details

    Event date: 2015

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Las Plmas de Gran Canaria, Spain  

    In this paper, we propose the re-detection paradigm, which is a detection with prior knowledge of the detection targets, and we introduce an implementation of the re-detection for distant pedestrian detection from an in-vehicle camera. We focus on the fact that other vehicles including forward vehicles can observe and detect pedestrians before the own vehicle observes them. Since appearances of pedestrians do not significantly change even though their locations are different, sharing images of the detected pedestrians among the vehicles, the own vehicle can use them as prior knowledge for detecting them again. Results of applying the proposed method to a dataset obtained by an in-vehicle camera demonstrate that the accuracy of pedestrian detection results can be significantly increased if prior knowledge of the pedestrians could be obtained.

    DOI: 10.1109/ITSC.2015.200

  302. Tastes and textures estimation of foods based on the analysis of its ingredients list and image International conference

    Hiroki Matsunaga, Keisuke Doman, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    1st International Workshop on Multimedia Assisted Dietary Management  2015.9.8 

     More details

    Event date: 2015

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Genova, Italy  

    Recently, the number of cooking recipes on the Web is increasing.
    However, it is difficult to search them by tastes or textures although
    they are actually important considering the nature of the contents.
    Therefore, we propose a method for estimating the tastes and the
    textures of a cooking recipe by analyzing them.
    Concretely, the proposed method refers to an ingredients feature from
    the ``ingredients list'' and image features from the ``food image'' in
    a cooking recipe.
    We confirmed the effectiveness of the proposed method through an
    experiment.

  303. Road scene understanding by using in-vehicle camera

    Daisuke Deguchi

    2015.9.3 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋工業大学  

  304. Detectors ensemble based on false positive mining for pedestrian detection

    Yuki Suzuki, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

    18th Meeting on Image Recognition & Understanding (MIRU2015)  2015.7.30 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Poster presentation  

    Venue:ホテル阪急エキスポパーク  

  305. Distant Pedestrian Detection from an in-Vehicle Camera based on Observations of Forward Vehicles

    Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    18th Meeting on Image Recognition & Understanding (MIRU2015)  2015.7.30 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Poster presentation  

  306. 運転者から見た歩行者の危険度推定のための 「歩きスマホ」認識

    新村 文郷, 川西 康友, 出口 大輔, 井手 一郎, 村瀬 洋, 藤吉 弘亘

    画像の認識・理解シンポジウム(MIRU)  2015.7.29 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Poster presentation  

    Venue:ホテル阪急エキスポパーク  

  307. A study on analyzing eye movements toward understanding cooking activities

    Hiroya Inoue, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    18th Meeting on Image Recognition & Understanding (MIRU2015)  2015.7.29 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Poster presentation  

    Venue:ホテル阪急エキスポパーク  

  308. Hand waving gesture classification using a far-infrared sensor array with Thermo-Spatial Region of Interest

    Chisato Toriyama, Takashi Hosono, Yasutomo Kawanishi, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

    18th Meeting on Image Recognition & Understanding (MIRU2015)  2015.7.29 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Poster presentation  

    Venue:ホテル阪急エキスポパーク  

  309. Image transformation of eye area for synthesizing eye-contacts in video conferencing

    Takuya Inoue, Tomokazu Takahashi, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Takayuki Kurozumi, Kunio Kashino

    18th Meeting on Image Recognition & Understanding (MIRU2015)  2015.7.29 

     More details

    Event date: 2015

    Language:Japanese   Presentation type:Poster presentation  

    Venue:ホテル阪急エキスポパーク  

  310. Typicality analysis of the combination of ingredients in a cooking recipe for assisting the arrangement of ingredients International conference

    Satoshi Yokoi, Keisuke Doman, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    2015 IEEE International Conference on Multimedia and Expo (ICME2012)  2015.7.3 

     More details

    Event date: 2015

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Torino, Italy  

    As the number of cooking recipes posted on the Web increases, it becomes difficult to find a cooking recipe that a user needs. Moreover, even if it can be done, it is still difficult for users to arrange the cooking recipe, for example, by replacing ingredients with different ones. To deal with such problems, we propose a framework for typicality analysis of the combination of ngredients. The framework calculates a typicality value for each combination of ingredients. The list of ingredients can be arranged by adjusting the typicality value by adding or removing ingredients iteratively. The effectiveness of the proposed framework was confirmed through subjective experiments.

  311. ownCloudを用いた全教職員向けファイル共有サービスの構築

    松岡 孝, 田島 尚徳, 出口 大輔, 森 健策

    大学ICT推進協議会(AXIES)  2014.12.12 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:仙台市情報・産業プラザ TKPガーデンシティ仙台  

  312. Single Camera Vehicle Localization Using SURF Scale and Dynamic Time Warping International conference

    David Robert Wong, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2014 the IEEE Intelligent Vehicles Symposium (IV2014)  2014.6.10 

     More details

    Event date: 2014

    Language:English   Presentation type:Poster presentation  

    Venue:Dearborn, Michigan, USA  

    Vehicle ego-localization is an essential process for many driver assistance and autonomous driving systems. The traditional solution of GPS localization is often unreliable in urban environments where tall buildings can cause shadowing of the satellite signal and multipath propagation. Typical visual feature based localization methods rely on calculation of the fundamental matrix which can be unstable when the baseline is small.
    In this paper we propose a novel method which uses the scale of matched SURF image features and Dynamic Time Warping to perform stable localization. By comparing SURF feature scales between input images and a pre-constructed database, stable localization is achieved without the need to calculate the fundamental matrix. In addition, 3D information is added to the database feature points in order to perform lateral localization, and therefore lane recognition.
    From experimental data captured from real traffic environments, we show how the proposed system can provide high localization accuracy relative to an image database, and can also perform lateral localization to recognize the vehicle's current lane.

  313. Estimation of Traffic Sign Visibility Considering Local and Global Features in a Driving Environment International conference

    Keisuke Doman, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase, Utsushi Sakai

    2014 IEEE Intelligent Vehicles Symposium (IV2014)  2014.6.9 

     More details

    Event date: 2014

    Language:English   Presentation type:Poster presentation  

    Venue:Dearborn, Michigan, USA  

    This paper proposes a camera-based visibility estimation method for a traffic sign.
    The visibility here indicates how a visual target is easy to be detected and recognized by a human driver (not a machine).
    This research aims at realizing a nuisance-free driver assistance system which sorts out information depending on the visibility of a visual target, in order to prevent driver distraction.
    Our previous study on estimating the visibility of a traffic sign considered only the effect of the local region around a target, assuming the situation that a driver's gaze is around it.
    The proposed method integrates both the local features and global features in a driving environment without such an assumption.
    The global features evaluate the positional relationships between traffic signs and the appearance around the fixation point of a driver's gaze, which considers the effect of the driver's entire field of view.
    Experimental results showed the effectiveness of incorporating the global features for estimating the visibility of a traffic sign.

  314. Estimation of a politician's stance based on his/her posts to microblogs

    Hiromichi Iwai, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    2014.5.12 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

  315. Estimation of the Representative Story Transition in a Chronological Semantic Structure of News Topics International conference

    Kosuke Kato, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    4th International Conference on Multimedia Retrieval (ICMR2014)  2014.4.4 

     More details

    Event date: 2014

    Language:English   Presentation type:Poster presentation  

    Venue:Glasgow University  

    It is important to track the flow of topics to thoroughly understand the contents. Accordingly, a method that structures the chronological semantic relations between news stories, namely a 'topic thread structure' has been proposed.It allows the comprehensive understanding of a topic by chronologically tracking stories one by one from the initial story. However, this task imposes a user to watch many stories when it contains various sub-topics. Thus, we propose method that estimates the representative story transition in a topic thread structure. In the proposed method, features obtained from a story and those from the topic thread structure are used for the estimation. We confirmed the effectiveness of the proposed method by comparing the results obtained from the proposed method to the ground truth obtained from votes in a subjective experiment. However, this task imposes a user to watch many stories when it contains various sub-topics. Thus, we propose method that estimates the representative story transition in a topic thread structure. In the proposed method, features obtained from a story and those from the topic thread structure are used for the estimation. We confirmed the effectiveness of the proposed method by comparing the results obtained from the proposed method to the ground truth obtained from votes in a subjective experiment

  316. A Preliminary Study on the Removal of Moving Objects in a Frontal In-vehicle Camera Image Sequence

    Toru Kotsuka, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2014 IEICE General Conference  2014.3.20 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:新潟大学  

  317. A preliminary study on eye images synthesis for eye gaze correction for teleconferencing

    Takuya Inoue, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2014 IEICE General Conference  2014.3.20 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:新潟大学  

  318. A preliminary study on pedestrian detection using a low resolution LIDAR

    Yoshinori Ichikawa, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Utsushi Sakai, Hideaki Misawa

    2014 IEICE General Conference  2014.3.20 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:新潟大学  

  319. A study on gesture detection by an infrared sensor array considering active areas

    Chisato Toriyama, Takashi Hosono, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2014 IEICE General Conference  2014.3.20 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:新潟大学  

  320. Investigation on the Estimation of the Number of Vehicles in an In-Vehicle Camera Image based on Car Parts Detection

    Fumito Shinmura, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    2014 IEICE General Conference  2014.3.20 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:新潟大学  

  321. A Feasibility Study of Human Cloud Sensing

    Atsushi Shimada, Daisuke Deguchi, Kazuaki Kondo, Takuya Funatomi

    2014 IEICE General Conference  2014.3.18 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:新潟大学  

  322. Accuracy improvement of pedestrian detection from in-vehicle camera images based on environment adaptation using location information

    Daichi Suzuo, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hiroyuki Ishida, Yoshiko Kojima

    IEICE Technical Report (PRMU)  2014.3.13 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:早稲田大学  

  323. Proposal of the weighted voting type co-training method for the construction of an accurate traffic sign detector

    Yuji Kojima, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (PRMU)  2014.3.13 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:早稲田大学  

  324. 名古屋大学におけるSakaiの利用状況およびリーディング大学院の活用事例の紹介

    中務 孝広, 太田 芳博, 田上 奈緒, 大平 茂輝, 後藤 明史, 出口 大輔, 森 健策

    Ja Sakai カンファレンス  2014.3.10 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋大学  

    名古屋大学では,2010年度からSakaiによるNUCT(Nagoya University Collaboration and course Tools)を,講義における利用を主たる目的として全学向けに運用してきた.本稿では,Sakaiにおける利用状況等について報告するとともに,博士課程教育リーディングプログラムにおける教育学習支援システムとして,Sakaiを利活用した事例について紹介する.

  325. A method to relate news stories to Web news articles for video structuring using SNS

    Kosuke Kato, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2014.3.7 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:別府コンベンションセンタ  

  326. Scene Duplicate Detection from News Videos by Sub-Region-based Motion Matching of a Face

    Haruka Kumagai, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2014.3.7 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:別府国際コンベンションセンタ  

  327. A Study on the Estimation of Tastes of Cooking Recipes Based on Training Using Comments on Cooking Recipes as Supervisory Signals

    Hiroki Matsunaga, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    IEICE Technical Report (MVE)  2014.3.6 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:別府コンベンションセンタ  

  328. A study on memory-based regression for spatial people density estimation

    Yoshimune Tabuchi, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Takayuki Kurozumi, Kunio Kashino

    IEICE Technical Report (PRMU)  2014.2.13 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:福岡大学七隈キャンパス18号館  

  329. Proposal of Human Cloud Sensing

    Atsushi Shimada, Daisuke Deguchi, Kazuaki Kondo, Takuya Funatomi

    IEICE Technical Report (PRMU)  2014.2.13 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Poster presentation  

    Venue:福岡大学  

  330. The 1st Feasibility Study toward Human Cloud Sensing

    Daisuke Deguchi, Kazuaki Kondo, Takuya Funatomi, Atsushi Shimada

    IEICE Technical Report (PRMU)  2014.2.13 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Poster presentation  

    Venue:福岡大学  

  331. The 2nd Feasibility Study toward Human Cloud Sensing

    Kazuaki Kondo, Takuya Funatomi, Atsushi Shimada, Daisuke Deguchi

    IEICE Technical Report (PRMU)  2014.2.13 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Poster presentation  

    Venue:福岡大学  

  332. Can a Human be a Sensor? International conference

    Atsushi Shimada, Daisuke Deguchi, Kazuaki Kondo, Takuya Funatomi

    20th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2014)  2014.2.5 

     More details

    Event date: 2014

    Language:English   Presentation type:Poster presentation  

    Venue:Okinawa National College of Technology  

    This paper discusses a novel sensing strategy to retrieve real-world information. Instead of using sensor devices such as cameras, microphones and so on, the proposed approach involves people in real-world sensing to acquire requested information as accurately and quickly as possible. We call the proposed sensing strategy as Human Cloud Sensing (HCS)". In this paper, we introduce the concept of HCS and report some experimental results which were conducted to investigate the feasibility of "Can a human be a sensor?"."

  333. Environment adaptive pedestrian detection using in-vehicle camera and GPS International conference

    Daichi Suzuo, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hiroyuki Ishida, Yoshiko Kojima

    International Conference on Computer Vision Theory and Applications (VISAPP) 2014  2014.1.7 

     More details

    Event date: 2014

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Lisbon  

    In recent years, accurate pedestrian detection from in-vehicle camera images is focused to develop a safety driving assistance system. Currently, successful methods are based on statistical learning. However, in such methods, it is necessary to prepare a large amount of training images. Thus, the decrease in the number of training images degrades the detection accuracy. That is, in driving environments with few or no training images, it is difficult to detect pedestrians accurately. Therefore, we propose an approach that collects training images automatically to build classifiers for various driving environments. This is expected to realize highly accurate pedestrian detection by using an appropriate classifier corresponding to the current location. The proposed method consists of three steps; Classification of driving scenes, collection of non-pedestrian images and training of classifiers for each scene class, and associating a scene-class-specific classifier with GPS location information. Through experiments, we confirmed the effectiveness of the method compared to baseline methods.

    DOI: 10.5220/0004677003540361

  334. Exemplar-Based Human Body Super-Resolution for Surveillance Camera Systems International conference

    Kento Nishibori, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    International Conference on Computer Vision Theory and Applications (VISAPP) 2014  2014.1.6 

     More details

    Event date: 2014

    Language:English   Presentation type:Poster presentation  

    Venue:Lisbon  

    In this paper, we propose an exemplar-based super-resolution method applied to a human body in a surveillance video. Since persons are usually captured as low-resolution images by a video surveillance system, it is sometimes necessary to perform detection and identification of persons from not only a human face but also from the human body appearance. The super-resolution for a human body image is difficult because the appearances of person images vary according to the color of clothing and the posture of persons. Thus, we focus on the high-frequency components that could restore the lost high-frequency components of the low-resolution image regardless to the variation of the clothing. Therefore, the purpose of the work presented in this paper is to apply the exemplar-based super-resolution using high-frequency components for a low-resolution human body image to generate a high-resolution human body image so that both computer systems and humans can identify persons more accurately. As a result of experiments, we confirmed the effectiveness of the proposed super-resolution method.

    DOI: 10.5220/0004686101150121

  335. Sakaiにおけるi18nとl10n ~現状と課題~

    出口 大輔

    大学ICT推進協議会(AXIES)  2014.12.11 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:仙台市情報・産業プラザ TKPガーデンシティ仙台  

  336. 名古屋大学における情報サービスの運用改善を目的としたシステムトラブル対応DBの構築

    瀬川 午直, 出口 大輔, 渥美 紀寿, 加藤 芳秀, 嶋田 創, 荻野 正雄, 小川 泰弘, 大野 誠寛, 川田 良文, 山田 一成

    大学ICT推進協議会(AXIES)  2014.12.12 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:仙台市情報・産業プラザ TKPガーデンシティ仙台  

  337. 車両部位検出を利用した回帰による車両台数推定

    新村 文郷, 出口 大輔, 井手 一郎, 村瀬 洋

    画像センシングシンポジウム(SSII)  2014.6.13 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Poster presentation  

    Venue:パシフィコ横浜アネックスホール  

    安全運転支援において,周囲の道路状況を理解することは重要である.自車周囲を走行する他車両の台数の把握は,道路状況の理解に役立つ重要な情報と考えられる.本発表では,車載カメラ画像中から車両の台数を推定するため,車両部位検出を利用した回帰による車両台数推定手法を提案する.車両を検出して台数を数える手法では,車両のオクルージョンにより検出精度が低下する問題がある.この問題を回避するため,提案手法では車両部位を検出して台数を数えるアプローチを用いる.車両の部位数から台数を推定する場合,車両の台数と部位数の関係は複雑であり,部位数から車両台数を一意に求めることは難しい.そこで,回帰を導入することにより,推定誤差の低減を図る.提案手法の有効性を確認するため,実環境で撮影した車載カメラ画像に対して提案手法を適用して車両台数を推定し,推定精度を評価した.評価の結果,提案手法は平均絶対誤差1.11 台の精度で車両台数を推定可能なことを確認した.

  338. A study on an effective camera arrangement toward gaze awareness by eye images synthesis for teleconferencing

    Takuya Inoue, Tomokazu Takahashi, Takatsugu Hirayama, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2014  2014.9.8 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:中京大学 名古屋キャンパス  

  339. A study on effective features for pedestrian detection using a low resolution LIDAR

    Yoshinori Ichikawa, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hideaki Misawa, Utsushi Sakai

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2014  2014.9.8 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:中京大学  

  340. Vision-based Vehicle Localization using a Visual Street Map with Embedded SURF Scale International conference

    David Robert Wong, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Computer Vision in Vehicle Technology with Special Session on Micro Aerial Vehicles (CVVT2014)  2014.9.6 

     More details

    Event date: 2014

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Zurich, Switzerland  

    Accurate vehicle positioning is important not only for in-car navigation systems but is also a requirement for emerging autonomous driving methods. Consumer level GPS are inaccurate in a number of driving environments such as in tunnels or areas where tall buildings cause satellite shadowing. Current vision-based methods typically rely on the integration of multiple sensors or fundamental matrix calculation which can be unstable when the baseline is small.

    In this paper we present a novel visual localization method which uses a visual street map and extracted SURF image features. By monitoring the difference in scale of features matched between input images and the visual street map within a Dynamic Time Warping framework, stable localization in the direction of motion is achieved without calculation of the fundamental or essential matrices.

    We present the system performance in real traffic environments. By comparing localization results with a high accuracy GPS ground truth, we demonstrate that accurate vehicle positioning is achieved.

  341. TransifexによるSakai 翻訳環境の設定

    出口 大輔

    Ja Sakai アンカンファレンス  2014.9.4 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:京都大学吉田泉殿  

  342. A preliminary study on the estimation of human orientation using an integrated RGB-D sensor

    Fumito Shinmura, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hironobu Fujiyoshi

    IEICE Technical Report (PRMU)  2014.9.2 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:筑波大学  

  343. Spatial People Density Estimation from Multiple Viewpoints by Memory Based Regression International conference

    Yoshimune Tabuchi, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Takayuki Kurozumi, Kunio Kashino

    22nd IAPR International Conference on Pattern Recognition (ICPR2014)  2014.8.27 

     More details

    Event date: 2014

    Language:English   Presentation type:Poster presentation  

    Venue:Stockholm, Sweden  

    Crowd analysis using cameras has attracted much attention for public safety and marketing. Among techniques of the crowd analysis, we focus on spatial people density estimation which estimates the number of people for each small area in a floor region. However, spatial people density cannot be estimated accurately for an area far from the camera because of the occlusion by people in a closer area. Therefore, we propose a method using a memory based regression method with images captured from cameras from multiple viewpoints. This method is realized by looking up a table that consists of correspondences between people density maps and crowd appearances. Since the crowd appearances include situations where various occlusions occur, an estimation robust to occlusion should be realized. In an experiment, we examined the effectiveness of the proposed method.

  344. A Study on Prediction of Driver’s Overlooking Probability by Image Processing Adaptive to Visual Fields of View

    Ryunosuke Tanishige, Keisuke Doman, Daisuke Deguchi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    17th Meeting on Image Recognition & Understanding (MIRU2014)  2014.7.31 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Poster presentation  

    Venue:岡山コンベンションセンター  

  345. Baggage detection from multi-viewpoints human images

    Yasuhiro Asai, Kento Nishibori, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    17th Meeting on Image Recognition & Understanding (MIRU2014)  2014.7.30 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Poster presentation  

    Venue:岡山コンベンションセンター  

  346. 拡張Census Transformを用いた道路面経時差分による車載カメラ映像からの障害物検出

    久徳 遙矢, 出口 大輔, 高橋 友和, 目加田 慶人, 井手 一郎, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2014.7.29 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Poster presentation  

    Venue:岡山コンベンションセンター  

  347. 車両部位の検出数と検出信頼度を利用した回帰による車両台数推定

    新村 文郷, 出口 大輔, 井手 一郎, 村瀬 洋

    画像の認識・理解シンポジウム(MIRU)  2014.7.29 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Poster presentation  

    Venue:岡山コンベンションセンター  

  348. Human tracking via thermo-spatial sensitive histogram

    Takashi Hosono, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

    17th Meeting on Image Recognition & Understanding (MIRU2014)  2014.7.29 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Poster presentation  

    Venue:岡山コンベンションセンター  

  349. Removal of Moving Objects From Frontal In-vehicle Camera Videos Based on Adaptive Selection of Reference Image

    Toru Kotsuka, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    17th Meeting on Image Recognition & Understanding (MIRU2014)  2014.7.29 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Poster presentation  

    Venue:岡山コンベンションセンター  

  350. A Preliminary Study on Hand Waving Detection Using an Infrared Sensor Array

    Chisato Toriyama, Takashi Hosono, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

    Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2014  2014.9.8 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:中京大学 名古屋キャンパス  

  351. Scene duplicate detection from news videos using image-audio matching focusing on human faces International conference

    Haruka Kumagai, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    16th IEEE International Symposium on Multimedia (ISM2014)  2014.12.10 

     More details

    Event date: 2014

    Language:English   Presentation type:Oral presentation (general)  

    Venue:臺中金典酒店(臺中,臺灣)  

    DOI: 10.1109/ISM.2014.43

  352. A Proposal of Encoding Marker which is Robust against Blur and easy to Detect

    Norimasa Kobori, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

    IEICE Technical Report (IE)  2014.12.4 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大阪大学 中之島センター  

  353. Event detection based on twitter enthusiasm degree for generating a sports highlight video International conference

    Keisuke Doman, Taishi Tomita, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

    ACM International Multimedia Conference (ACM-MM)  2014.11.5 

     More details

    Event date: 2014

    Language:English   Presentation type:Poster presentation  

    Venue:Orlando, Florida, USA  

    This paper presents a Twitter-based event detection method based on Twitter Enthusiasm Degrees (TED)" toward generating a highlight video of a sports game. Existing methods not only depend on both languages and sports types but also often falsely detect non-target events. In contrast, the proposed method detects sports events using TEDs calculated from several kinds of string features independent of languages and sports. We applied the proposed method to actual sports games, and compared the detected events with the events present in broadcasted highlight videos, and confirmed the effectiveness and the language and sports type independencies of the proposed method."

  354. Human Tracking using a Far-Infrared Sensor Array and a Thermo-Spatial Sensitive Histogram International conference

    細野 峻司, 高橋 友和, 出口 大輔, 井手 一郎, 村瀬 洋, 相澤 知禎, 川出 雅人

    2nd Workshop on User-Centred Computer Vision  2014.11.1 

     More details

    Event date: 2014

    Language:English   Presentation type:Oral presentation (general)  

    Venue:National University of Singapore, Singapore  

  355. A Collaborative Report on The Open Apereo 2014 Conference

    Yuji Tokiwa, Soichiro Fujii, Makoto Miyazaki, Daisuke Deguchi, Naoshi Hiraoka, Shoji Kajita

    IPSJ SIG Technical Report (CLE)  2014.10.24 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東北大学川内キャンパス  

  356. A study on image transformation of eye areas for synthesizing eye-contacts in video conferencing

    Takuya Inoue, Tomokazu Takahashi, Takatsugu Hirayama, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Takayuki Kurozumi, Kunio Kashino

    IEICE Technical Report (PRMU)  2014.10.10 

     More details

    Event date: 2014

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:幕張メッセ国際会議場  

  357. Prediction of Driver's Pedestrian Detectability by Image Processing Adaptive to Visual Fields of View International conference

    Ryunosuke Tanishige, Daisuke Deguchi, Keisuke Doman, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

    2014 IEEE Conference on Intelligent Transportation Systems (ITSC2014)  2014.10.10 

     More details

    Event date: 2014

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Hyatt Regency Qingdao, Qingdao, China  

  358. A study on features for pedestrian detection using a low resolution LIDAR

    Yoshinori Ichikawa, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Hideaki Misawa, Utsushi Sakai

    IEICE Technical Report (PRMU)  2014.10.9 

     More details

    Event date: 2014

    Language:Japanese