Faculty Profiles - Deguchi Daisuke

Presentations -

Division display 301 - 320 of about 727 ／ All the affair displays >>

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

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.

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

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.

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

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

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

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

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．

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

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

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

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."

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

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."

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

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

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

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．

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

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

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

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

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.

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

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

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

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

　 PREV - NEXT 　

<Deguchi Daisuke>

Presentations -