Cargando…

Robust clothing-independent gait recognition using hybrid part-based gait features

Recently, gait has been gathering extensive interest for the non-fungible position in applications. Although various methods have been proposed for gait recognition, most of them can only attain an excellent recognition performance when the probe and gallery gaits are in a similar condition. Once ex...

Descripción completa

Detalles Bibliográficos
Autores principales: Gao, Zhipeng, Wu, Junyi, Wu, Tingting, Huang, Renyu, Zhang, Anguo, Zhao, Jianqiang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9202625/
https://www.ncbi.nlm.nih.gov/pubmed/35721406
http://dx.doi.org/10.7717/peerj-cs.996
_version_ 1784728570094944256
author Gao, Zhipeng
Wu, Junyi
Wu, Tingting
Huang, Renyu
Zhang, Anguo
Zhao, Jianqiang
author_facet Gao, Zhipeng
Wu, Junyi
Wu, Tingting
Huang, Renyu
Zhang, Anguo
Zhao, Jianqiang
author_sort Gao, Zhipeng
collection PubMed
description Recently, gait has been gathering extensive interest for the non-fungible position in applications. Although various methods have been proposed for gait recognition, most of them can only attain an excellent recognition performance when the probe and gallery gaits are in a similar condition. Once external factors (e.g., clothing variations) influence people’s gaits and changes happen in human appearances, a significant performance degradation occurs. Hence, in our article, a robust hybrid part-based spatio-temporal feature learning method is proposed for gait recognition to handle this cloth-changing problem. First, human bodies are segmented into the affected and non/less unaffected parts based on the anatomical studies. Then, a well-designed network is proposed in our method to formulate our required hybrid features from the non/less unaffected body parts. This network contains three sub-networks, aiming to generate features independently. Each sub-network emphasizes individual aspects of gait, hence an effective hybrid gait feature can be created through their concatenation. In addition, temporal information can be used as complement to enhance the recognition performance, a sub-network is specifically proposed to establish the temporal relationship between consecutive short-range frames. Also, since local features are more discriminative than global features in gait recognition, in this network a sub-network is specifically proposed to generate features of local refined differences. The effectiveness of our proposed method has been evaluated by experiments on the CASIA Gait Dataset B and OU-ISIR Treadmill Gait Dataset B. Related experiments illustrate that compared with other gait recognition methods, our proposed method can achieve a prominent result when handling this cloth-changing gait recognition problem.
format Online
Article
Text
id pubmed-9202625
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-92026252022-06-17 Robust clothing-independent gait recognition using hybrid part-based gait features Gao, Zhipeng Wu, Junyi Wu, Tingting Huang, Renyu Zhang, Anguo Zhao, Jianqiang PeerJ Comput Sci Artificial Intelligence Recently, gait has been gathering extensive interest for the non-fungible position in applications. Although various methods have been proposed for gait recognition, most of them can only attain an excellent recognition performance when the probe and gallery gaits are in a similar condition. Once external factors (e.g., clothing variations) influence people’s gaits and changes happen in human appearances, a significant performance degradation occurs. Hence, in our article, a robust hybrid part-based spatio-temporal feature learning method is proposed for gait recognition to handle this cloth-changing problem. First, human bodies are segmented into the affected and non/less unaffected parts based on the anatomical studies. Then, a well-designed network is proposed in our method to formulate our required hybrid features from the non/less unaffected body parts. This network contains three sub-networks, aiming to generate features independently. Each sub-network emphasizes individual aspects of gait, hence an effective hybrid gait feature can be created through their concatenation. In addition, temporal information can be used as complement to enhance the recognition performance, a sub-network is specifically proposed to establish the temporal relationship between consecutive short-range frames. Also, since local features are more discriminative than global features in gait recognition, in this network a sub-network is specifically proposed to generate features of local refined differences. The effectiveness of our proposed method has been evaluated by experiments on the CASIA Gait Dataset B and OU-ISIR Treadmill Gait Dataset B. Related experiments illustrate that compared with other gait recognition methods, our proposed method can achieve a prominent result when handling this cloth-changing gait recognition problem. PeerJ Inc. 2022-05-31 /pmc/articles/PMC9202625/ /pubmed/35721406 http://dx.doi.org/10.7717/peerj-cs.996 Text en ©2022 Gao 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
Gao, Zhipeng
Wu, Junyi
Wu, Tingting
Huang, Renyu
Zhang, Anguo
Zhao, Jianqiang
Robust clothing-independent gait recognition using hybrid part-based gait features
title Robust clothing-independent gait recognition using hybrid part-based gait features
title_full Robust clothing-independent gait recognition using hybrid part-based gait features
title_fullStr Robust clothing-independent gait recognition using hybrid part-based gait features
title_full_unstemmed Robust clothing-independent gait recognition using hybrid part-based gait features
title_short Robust clothing-independent gait recognition using hybrid part-based gait features
title_sort robust clothing-independent gait recognition using hybrid part-based gait features
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9202625/
https://www.ncbi.nlm.nih.gov/pubmed/35721406
http://dx.doi.org/10.7717/peerj-cs.996
work_keys_str_mv AT gaozhipeng robustclothingindependentgaitrecognitionusinghybridpartbasedgaitfeatures
AT wujunyi robustclothingindependentgaitrecognitionusinghybridpartbasedgaitfeatures
AT wutingting robustclothingindependentgaitrecognitionusinghybridpartbasedgaitfeatures
AT huangrenyu robustclothingindependentgaitrecognitionusinghybridpartbasedgaitfeatures
AT zhanganguo robustclothingindependentgaitrecognitionusinghybridpartbasedgaitfeatures
AT zhaojianqiang robustclothingindependentgaitrecognitionusinghybridpartbasedgaitfeatures