The Experts below are selected from a list of 6414 Experts worldwide ranked by ideXlab platform
Yasushi Yagi - One of the best experts on this subject based on the ideXlab platform.
-
Directional characteristics evaluation of silhouette-based Gait Recognition
IPSJ Transactions on Computer Vision and Applications, 2018Co-Authors: Yui Shigeki, Fumio Okura, Ikuhisa Mitsugami, Kenichi Hayashi, Yasushi YagiAbstract:Gait is an important biometric trait for identifying individuals. The use of inputs from multiple or moving cameras offers a promising extension of Gait Recognition methods. Personal authentication systems at building entrances, for example, can utilize multiple cameras installed at appropriate positions to increase their authentication accuracy. In such cases, it is important to identify effective camera positions to maximize Gait Recognition performance, but it is not yet clear how different viewpoints affect Recognition performance. This study determines the relationship between viewpoint and Gait Recognition performance to construct standards for selecting an appropriate view for Gait Recognition using multiple or moving cameras. We evaluate the Gait features generated from 3D pedestrian shapes to visualize the directional characteristics of Recognition performance.
-
Gait Recognition by Deformable Registration
2018 IEEE CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018Co-Authors: Yasushi Makihara, Daisuke Adachi, Chi Xu, Yasushi YagiAbstract:This paper describes a method of Gait Recognition robust against intra-subject posture changes. A person sometimes walks with changing his/her posture when looking down at a smartphone or carrying a heavy object, which makes intra-subject variation large and consequently makes Gait Recognition difficult. We therefore introduce a deformable registration model to mitigate the intra-subject posture changes. More specifically, we represent a deformation field by a set of deformation vectors on lattice-type control points allocated on an image, i.e., by free-form deformation (FFD) framework. Given a pair of a probe and a gallery, we compute the deformation field so as to minimize the difference between a probe morphed by the deformation field and the gallery, as well as to ensure the spatial smoothness of the deformation field. We then learn the intra-subject eigen deformation modes from a training set of the same subjects' pairs (e.g., bending the upper body forward and swinging arms more), which are relatively different from inter-subject deformation modes (e.g., body shape spread and stride change). Moreover, because the deformable registration is responsible for a preprocessing part before matching, it can be combined with any types of matching algorithms for Gait Recognition. Experiments with 1,334 subjects show that the proposed method improves the Gait Recognition accuracy in both cases without and with a state-of-the-art deep learning-based matcher, respectively.
-
CVPR Workshops - Gait Recognition by Deformable Registration
2018 IEEE CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018Co-Authors: Yasushi Makihara, Daisuke Adachi, Chi Xu, Yasushi YagiAbstract:This paper describes a method of Gait Recognition robust against intra-subject posture changes. A person sometimes walks with changing his/her posture when looking down at a smartphone or carrying a heavy object, which makes intra-subject variation large and consequently makes Gait Recognition difficult. We therefore introduce a deformable registration model to mitigate the intra-subject posture changes. More specifically, we represent a deformation field by a set of deformation vectors on lattice-type control points allocated on an image, i.e., by free-form deformation (FFD) framework. Given a pair of a probe and a gallery, we compute the deformation field so as to minimize the difference between a probe morphed by the deformation field and the gallery, as well as to ensure the spatial smoothness of the deformation field. We then learn the intra-subject eigen deformation modes from a training set of the same subjects' pairs (e.g., bending the upper body forward and swinging arms more), which are relatively different from inter-subject deformation modes (e.g., body shape spread and stride change). Moreover, because the deformable registration is responsible for a preprocessing part before matching, it can be combined with any types of matching algorithms for Gait Recognition. Experiments with 1,334 subjects show that the proposed method improves the Gait Recognition accuracy in both cases without and with a state-of-the-art deep learning-based matcher, respectively.
-
Gait Recognition by fluctuations
Computer Vision and Image Understanding, 2014Co-Authors: Muhammad Rasyid Aqmar, Yasushi Makihara, Yusuke Fujihara, Yasushi YagiAbstract:This paper describes a method of Gait Recognition by suppressing and using Gait fluctuations. Inconsistent phasing between a matching pair of Gait image sequences because of temporal fluctuations degrades the performance of Gait Recognition. We remove the temporal fluctuations by generating a phase-normalized Gait image sequence with equal phase intervals. If inter-period Gait fluctuations within a Gait image sequence are repeatedly observed for the same subject, they can be regarded as a useful distinguishing Gait feature. We extract phase fluctuations as temporal fluctuations as well as Gait fluctuation image and trajectory fluctuations as spatial fluctuations. We combine them with the matching score using the phase-normalized image sequence as additional matching scores in the score-level fusion framework or as quality measures in the score-normalization framework. We evaluated the methods in experiments using large-scale publicly available databases and showed the effectiveness of the proposed methods.
-
Can Gait fluctuations improve Gait Recognition?
Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), 2012Co-Authors: Yasushi Makihara, Yusuke Fujihara, Yasushi YagiAbstract:Gait Recognition performance is often degraded by intra-subject Gait fluctuations such as temporal fluctuations due to non-uniform evolution of phase (Gait stance) and spatial fluctuations in arm swings or posture within the same phase. Therefore, we first propose a method for Gait Recognition using a phase-normalized image sequence to overcome the temporal fluctuations. However, it has been noticed that Gait fluctuations actually contain some useful individuality (e.g., degree of arm swing fluctuations). Hence, we propose a score-level fusion framework for Gait Recognition using the Gait fluctuation features as well as the phase-normalized image sequence. Experiments with a public Gait database of 100 subjects show the effectiveness of the proposed method.
Uday Pratap Singh - One of the best experts on this subject based on the ideXlab platform.
-
Vision-Based Gait Recognition: A Survey
IEEE Access, 2018Co-Authors: Jasvinder Pal Singh, Sanjeev Jain, Sakshi Arora, Uday Pratap SinghAbstract:In the digital world of today, global security issues have given rise to video surveillance devices. Gait-based human Recognition is an emerging behavioral biometric trait for intelligent surveillance monitoring because of its non-contact and non-cooperation with subjects. Other benefits of Gait Recognition in video surveillance are that it can be acquired at a distance and help to identify an object under low-resolution videos. This paper surveys extensively the current progress made towards vision-based human Gait Recognition. This paper discusses historical research that performs analysis of Gait locomotion and provides information on how Gait Recognition can be performed. This paper describes measuring metrics that can be used to measure the performance of Gait Recognition model under verification and identification mode. This paper also provides an up-to-date review of existing studies on Gait Recognition representations (model based and model free). We also provide an extensive survey of available Gait databases used in state-of-art Gait Recognition models, created since 1998. Furthermore, it offers insight into open research problems that help researchers to explore unripe areas in Gait analysis, such as occlusion, view variations, and appearance changes in Gait Recognition. This paper also identifies the future perspectives in Gait Recognition and also outlines the proposed work.
Mohammadreza Babaee - One of the best experts on this subject based on the ideXlab platform.
-
ICIP - Joint tracking and Gait Recognition of multiple people in video
2017 IEEE International Conference on Image Processing (ICIP), 2017Co-Authors: Maryam Babaee, Gerhard Rigoll, Mohammadreza BabaeeAbstract:We propose a novel approach to address the problem of jointly tracking and Gait Recognition of multiple people in a video sequence. The most state of the art algorithms for Gait Recognition consider the cases where there is only one person without any occlusion in a very constrained environment. However, in real scenarios such as in airports, train stations, etc, there are many people in the environment that make these algorithms inapplicable. Although first tracking of each person and then Gait Recognition could be a solution, we argue that the multi-people tracking and the Gait Recognition in a video are two sub-problems that can help each other. Hence, we propose a joint tracking and Gait Recognition of multiple people as one framework that can improve Gait Recognition accuracy and decrease the ID switching in tracking. Experimental results confirm the validity of proposed approach.
-
Joint tracking and Gait Recognition of multiple people in video
2017 IEEE International Conference on Image Processing (ICIP), 2017Co-Authors: Maryam Babaee, Gerhard Rigoll, Mohammadreza BabaeeAbstract:We propose a novel approach to address the problem of jointly tracking and Gait Recognition of multiple people in a video sequence. The most state of the art algorithms for Gait Recognition consider the cases where there is only one person without any occlusion in a very constrained environment. However, in real scenarios such as in airports, train stations, etc, there are many people in the environment that make these algorithms inapplicable. Although first tracking of each person and then Gait Recognition could be a solution, we argue that the multi-people tracking and the Gait Recognition in a video are two sub-problems that can help each other. Hence, we propose a joint tracking and Gait Recognition of multiple people as one framework that can improve Gait Recognition accuracy and decrease the ID switching in tracking. Experimental results confirm the validity of proposed approach.
Maryam Babaee - One of the best experts on this subject based on the ideXlab platform.
-
Gait Recognition from Incomplete Gait Cycle
2018 25th IEEE International Conference on Image Processing (ICIP), 2018Co-Authors: Maryam Babaee, Linwei Li, Gerhard RigollAbstract:In Gait Recognition, which has been recently regarded as a biometric Recognition tool, proposed approaches assume that an individual is observed for at least one Gait cycle. However, in reality, there might be available only a few frames of full Gait cycle of a subject due to occlusion. Therefore, Gait Recognition systems would fail in these scenarios. In this paper, we propose a method to tackle this problem by proposing a Gait Recognition algorithm from an incomplete Gait cycle information. We achieve this by 1) creating an incomplete Energy Image (GEI) from a few available silhouettes of a subject and 2) reconstructing the complete GEI from incomplete GEI using a deep auto-encoder. The experimental results on a public Gait dataset demonstrate the validity of the proposed method.
-
ICIP - Joint tracking and Gait Recognition of multiple people in video
2017 IEEE International Conference on Image Processing (ICIP), 2017Co-Authors: Maryam Babaee, Gerhard Rigoll, Mohammadreza BabaeeAbstract:We propose a novel approach to address the problem of jointly tracking and Gait Recognition of multiple people in a video sequence. The most state of the art algorithms for Gait Recognition consider the cases where there is only one person without any occlusion in a very constrained environment. However, in real scenarios such as in airports, train stations, etc, there are many people in the environment that make these algorithms inapplicable. Although first tracking of each person and then Gait Recognition could be a solution, we argue that the multi-people tracking and the Gait Recognition in a video are two sub-problems that can help each other. Hence, we propose a joint tracking and Gait Recognition of multiple people as one framework that can improve Gait Recognition accuracy and decrease the ID switching in tracking. Experimental results confirm the validity of proposed approach.
-
Joint tracking and Gait Recognition of multiple people in video
2017 IEEE International Conference on Image Processing (ICIP), 2017Co-Authors: Maryam Babaee, Gerhard Rigoll, Mohammadreza BabaeeAbstract:We propose a novel approach to address the problem of jointly tracking and Gait Recognition of multiple people in a video sequence. The most state of the art algorithms for Gait Recognition consider the cases where there is only one person without any occlusion in a very constrained environment. However, in real scenarios such as in airports, train stations, etc, there are many people in the environment that make these algorithms inapplicable. Although first tracking of each person and then Gait Recognition could be a solution, we argue that the multi-people tracking and the Gait Recognition in a video are two sub-problems that can help each other. Hence, we propose a joint tracking and Gait Recognition of multiple people as one framework that can improve Gait Recognition accuracy and decrease the ID switching in tracking. Experimental results confirm the validity of proposed approach.
Yasushi Makihara - One of the best experts on this subject based on the ideXlab platform.
-
Gait Recognition by Deformable Registration
2018 IEEE CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018Co-Authors: Yasushi Makihara, Daisuke Adachi, Chi Xu, Yasushi YagiAbstract:This paper describes a method of Gait Recognition robust against intra-subject posture changes. A person sometimes walks with changing his/her posture when looking down at a smartphone or carrying a heavy object, which makes intra-subject variation large and consequently makes Gait Recognition difficult. We therefore introduce a deformable registration model to mitigate the intra-subject posture changes. More specifically, we represent a deformation field by a set of deformation vectors on lattice-type control points allocated on an image, i.e., by free-form deformation (FFD) framework. Given a pair of a probe and a gallery, we compute the deformation field so as to minimize the difference between a probe morphed by the deformation field and the gallery, as well as to ensure the spatial smoothness of the deformation field. We then learn the intra-subject eigen deformation modes from a training set of the same subjects' pairs (e.g., bending the upper body forward and swinging arms more), which are relatively different from inter-subject deformation modes (e.g., body shape spread and stride change). Moreover, because the deformable registration is responsible for a preprocessing part before matching, it can be combined with any types of matching algorithms for Gait Recognition. Experiments with 1,334 subjects show that the proposed method improves the Gait Recognition accuracy in both cases without and with a state-of-the-art deep learning-based matcher, respectively.
-
CVPR Workshops - Gait Recognition by Deformable Registration
2018 IEEE CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018Co-Authors: Yasushi Makihara, Daisuke Adachi, Chi Xu, Yasushi YagiAbstract:This paper describes a method of Gait Recognition robust against intra-subject posture changes. A person sometimes walks with changing his/her posture when looking down at a smartphone or carrying a heavy object, which makes intra-subject variation large and consequently makes Gait Recognition difficult. We therefore introduce a deformable registration model to mitigate the intra-subject posture changes. More specifically, we represent a deformation field by a set of deformation vectors on lattice-type control points allocated on an image, i.e., by free-form deformation (FFD) framework. Given a pair of a probe and a gallery, we compute the deformation field so as to minimize the difference between a probe morphed by the deformation field and the gallery, as well as to ensure the spatial smoothness of the deformation field. We then learn the intra-subject eigen deformation modes from a training set of the same subjects' pairs (e.g., bending the upper body forward and swinging arms more), which are relatively different from inter-subject deformation modes (e.g., body shape spread and stride change). Moreover, because the deformable registration is responsible for a preprocessing part before matching, it can be combined with any types of matching algorithms for Gait Recognition. Experiments with 1,334 subjects show that the proposed method improves the Gait Recognition accuracy in both cases without and with a state-of-the-art deep learning-based matcher, respectively.
-
Gait Recognition by fluctuations
Computer Vision and Image Understanding, 2014Co-Authors: Muhammad Rasyid Aqmar, Yasushi Makihara, Yusuke Fujihara, Yasushi YagiAbstract:This paper describes a method of Gait Recognition by suppressing and using Gait fluctuations. Inconsistent phasing between a matching pair of Gait image sequences because of temporal fluctuations degrades the performance of Gait Recognition. We remove the temporal fluctuations by generating a phase-normalized Gait image sequence with equal phase intervals. If inter-period Gait fluctuations within a Gait image sequence are repeatedly observed for the same subject, they can be regarded as a useful distinguishing Gait feature. We extract phase fluctuations as temporal fluctuations as well as Gait fluctuation image and trajectory fluctuations as spatial fluctuations. We combine them with the matching score using the phase-normalized image sequence as additional matching scores in the score-level fusion framework or as quality measures in the score-normalization framework. We evaluated the methods in experiments using large-scale publicly available databases and showed the effectiveness of the proposed methods.
-
ACPR - Towards Robust Gait Recognition
2013 2nd IAPR Asian Conference on Pattern Recognition, 2013Co-Authors: Yasushi MakiharaAbstract:Gait Recognition is a method of biometric person authentication from his/her unconscious walking manner. Unlike the other biometrics such as DNA, fingerprint, vein, and iris, the Gait can be recognized even at a distance from a camera without subjects' cooperation, and hence it is expected to be applied to many fields: criminal investigation, forensic science, and surveillance. However, the absence of the subjects' cooperation may sometimes induces large intra-subject variations of the Gait due to the changes of viewpoints, walking directions, speeds, clothes, and shoes. We therefore develop methods of robust Gait Recognition with (1) an appearance-based view transformation model, (2) a kinematics-based speed transformation model. Moreover, CCTV footages are often stored as low frame-rate videos due to limitation of communication bandwidth and storage size, which makes it much more difficult to observe a continuous Gait motion and hence significantly degrades the Gait Recognition performance. We therefore solve this problem with (3) a technique of periodic temporal super resolution from a low frame-rate video. We show the efficiency of the proposed methods with our constructed Gait databases.
-
Can Gait fluctuations improve Gait Recognition?
Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), 2012Co-Authors: Yasushi Makihara, Yusuke Fujihara, Yasushi YagiAbstract:Gait Recognition performance is often degraded by intra-subject Gait fluctuations such as temporal fluctuations due to non-uniform evolution of phase (Gait stance) and spatial fluctuations in arm swings or posture within the same phase. Therefore, we first propose a method for Gait Recognition using a phase-normalized image sequence to overcome the temporal fluctuations. However, it has been noticed that Gait fluctuations actually contain some useful individuality (e.g., degree of arm swing fluctuations). Hence, we propose a score-level fusion framework for Gait Recognition using the Gait fluctuation features as well as the phase-normalized image sequence. Experiments with a public Gait database of 100 subjects show the effectiveness of the proposed method.
