Faculty Profiles - Deguchi Daisuke

Papers - Deguchi Daisuke

Division display 21 - 40 of about 244 ／ All the affair displays >>

Safety Margin Prediction for Pedestrians Using Risk Potential Function Considering Pedestrian Attributes and Driver Skill Reviewed

Yamato Maekawa, Takatsugu Hirayama, Yasutomo Kawanishi, Daisuke Deguchi, HaiLong Liu, Ichiro Ide, Hiroshi Murase

IEICE Transactions on Information and Systems Vol. J105-A ( 3 ) page： 38 - 42 2022.3

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

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

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

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

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

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

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

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

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

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

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

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

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.

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

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.

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

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.

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

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

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

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

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

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

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

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

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

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

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

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.

　 PREV - NEXT 　

<Deguchi Daisuke>

Papers - Deguchi Daisuke