Omni-Domain Feature Extraction Method for Gait Recognition

被引:1
作者
Wan, Jiwei [1 ]
Zhao, Huimin [1 ]
Li, Rui [1 ,2 ]
Chen, Rongjun [1 ]
Wei, Tuanjie [1 ]
机构
[1] Guangdong Polytech Normal Univ, Sch Comp Sci, Guangzhou 510665, Peoples R China
[2] Guangzhou Coll Commerce, Sch Art & Design, Guangzhou 511363, Peoples R China
基金
中国国家自然科学基金;
关键词
gait recognition; Omni-Domain Feature Extraction; temporal sensitive; dynamic motion;
D O I
10.3390/math11122612
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
As a biological feature with strong spatio-temporal correlation, the current difficulty of gait recognition lies in the interference of covariates (viewpoint, clothing, etc.) in feature extraction. In order to weaken the influence of extrinsic variable changes, we propose an interval frame sampling method to capture more information about joint dynamic changes, and an Omni-Domain Feature Extraction Network. The Omni-Domain Feature Extraction Network consists of three main modules: (1) Temporal-Sensitive Feature Extractor: injects key gait temporal information into shallow spatial features to improve spatio-temporal correlation. (2) Dynamic Motion Capture: extracts temporal features of different motion and assign weights adaptively. (3) Omni-Domain Feature Balance Module: balances fine-grained spatio-temporal features, highlight decisive spatio-temporal features. Extensive experiments were conducted on two commonly used public gait datasets, showing that our method has good performance and generalization ability. In CASIA-B, we achieved an average rank-1 accuracy of 94.2% under three walking conditions. In OU-MVLP, we achieved a rank-1 accuracy of 90.5%.
引用
收藏
页数:19
相关论文
共 49 条
  • [1] Mitigating human-induced emissions in Argentina: role of renewables, income, globalization, and financial development
    Adebayo, Tomiwa Sunday
    Akinsola, Gbenga Daniel
    Bekun, Festus Victor
    Osemeahon, Oseyenbhin Sunday
    Sarkodie, Samuel Asumadu
    [J]. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH, 2021, 28 (47) : 67764 - 67778
  • [2] [Anonymous], 2009, ENCLYCOPEDIA BIOMETR
  • [3] OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields
    Cao, Zhe
    Hidalgo, Gines
    Simon, Tomas
    Wei, Shih-En
    Sheikh, Yaser
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (01) : 172 - 186
  • [4] Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
    Cao, Zhe
    Simon, Tomas
    Wei, Shih-En
    Sheikh, Yaser
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 1302 - 1310
  • [5] Chao HQ, 2019, AAAI CONF ARTIF INTE, P8126
  • [6] GaitAMR: Cross-view gait recognition via aggregated multi-feature representation
    Chen, Jianyu
    Wang, Zhongyuan
    Zheng, Caixia
    Zeng, Kangli
    Zou, Qin
    Cui, Laizhong
    [J]. INFORMATION SCIENCES, 2023, 636
  • [7] Rapid Detection of Multi-QR Codes Based on Multistage Stepwise Discrimination and a Compressed MobileNet
    Chen, Rongjun
    Huang, Hongxing
    Yu, Yongxing
    Ren, Jinchang
    Wang, Peixian
    Zhao, Huimin
    Lu, Xu
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2023, 10 (18) : 15966 - 15979
  • [8] A Unified Local-Global Feature Extraction Network for Human Gait Recognition Using Smartphone Sensors
    Das, Sonia
    Meher, Sukadev
    Sahoo, Upendra Kumar
    [J]. SENSORS, 2022, 22 (11)
  • [9] Fan C, 2020, PROC CVPR IEEE, P14213, DOI 10.1109/CVPR42600.2020.01423
  • [10] Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images
    Fan, Deng-Ping
    Zhou, Tao
    Ji, Ge-Peng
    Zhou, Yi
    Chen, Geng
    Fu, Huazhu
    Shen, Jianbing
    Shao, Ling
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2020, 39 (08) : 2626 - 2637