Cargando…

Gait recognition using a few gait frames

Gait has been deemed as an alternative biometric in video-based surveillance applications, since it can be used to recognize individuals from a far distance without their interaction and cooperation. Recently, many gait recognition methods have been proposed, aiming at reducing the influence caused...

Descripción completa

Detalles Bibliográficos
Autores principales: Yao, Lingxiang, Kusakunniran, Worapan, Wu, Qiang, Zhang, Jian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7959613/
https://www.ncbi.nlm.nih.gov/pubmed/33817029
http://dx.doi.org/10.7717/peerj-cs.382
_version_ 1783664987475017728
author Yao, Lingxiang
Kusakunniran, Worapan
Wu, Qiang
Zhang, Jian
author_facet Yao, Lingxiang
Kusakunniran, Worapan
Wu, Qiang
Zhang, Jian
author_sort Yao, Lingxiang
collection PubMed
description Gait has been deemed as an alternative biometric in video-based surveillance applications, since it can be used to recognize individuals from a far distance without their interaction and cooperation. Recently, many gait recognition methods have been proposed, aiming at reducing the influence caused by exterior factors. However, most of these methods are developed based on sufficient input gait frames, and their recognition performance will sharply decrease if the frame number drops. In the real-world scenario, it is impossible to always obtain a sufficient number of gait frames for each subject due to many reasons, e.g., occlusion and illumination. Therefore, it is necessary to improve the gait recognition performance when the available gait frames are limited. This paper starts with three different strategies, aiming at producing more input frames and eliminating the generalization error cause by insufficient input data. Meanwhile, a two-branch network is also proposed in this paper to formulate robust gait representations from the original and new generated input gait frames. According to our experiments, under the limited gait frames being used, it was verified that the proposed method can achieve a reliable performance for gait recognition.
format Online
Article
Text
id pubmed-7959613
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-79596132021-04-02 Gait recognition using a few gait frames Yao, Lingxiang Kusakunniran, Worapan Wu, Qiang Zhang, Jian PeerJ Comput Sci Artificial Intelligence Gait has been deemed as an alternative biometric in video-based surveillance applications, since it can be used to recognize individuals from a far distance without their interaction and cooperation. Recently, many gait recognition methods have been proposed, aiming at reducing the influence caused by exterior factors. However, most of these methods are developed based on sufficient input gait frames, and their recognition performance will sharply decrease if the frame number drops. In the real-world scenario, it is impossible to always obtain a sufficient number of gait frames for each subject due to many reasons, e.g., occlusion and illumination. Therefore, it is necessary to improve the gait recognition performance when the available gait frames are limited. This paper starts with three different strategies, aiming at producing more input frames and eliminating the generalization error cause by insufficient input data. Meanwhile, a two-branch network is also proposed in this paper to formulate robust gait representations from the original and new generated input gait frames. According to our experiments, under the limited gait frames being used, it was verified that the proposed method can achieve a reliable performance for gait recognition. PeerJ Inc. 2021-03-01 /pmc/articles/PMC7959613/ /pubmed/33817029 http://dx.doi.org/10.7717/peerj-cs.382 Text en ©2021 Yao et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Artificial Intelligence
Yao, Lingxiang
Kusakunniran, Worapan
Wu, Qiang
Zhang, Jian
Gait recognition using a few gait frames
title Gait recognition using a few gait frames
title_full Gait recognition using a few gait frames
title_fullStr Gait recognition using a few gait frames
title_full_unstemmed Gait recognition using a few gait frames
title_short Gait recognition using a few gait frames
title_sort gait recognition using a few gait frames
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7959613/
https://www.ncbi.nlm.nih.gov/pubmed/33817029
http://dx.doi.org/10.7717/peerj-cs.382
work_keys_str_mv AT yaolingxiang gaitrecognitionusingafewgaitframes
AT kusakunniranworapan gaitrecognitionusingafewgaitframes
AT wuqiang gaitrecognitionusingafewgaitframes
AT zhangjian gaitrecognitionusingafewgaitframes