Paper
9 October 2023 Gait recognition method in surveillance video based on two-branch network
Yueyu Huang, Hang Zhou, Yehong Chen, Xin Lu, Jia Yu, Ruiyu Han, Jiawei Chen
Author Affiliations +
Proceedings Volume 12791, Third International Conference on Advanced Algorithms and Neural Networks (AANN 2023); 1279112 (2023) https://doi.org/10.1117/12.3005013
Event: Third International Conference on Advanced Algorithms and Neural Networks (AANN 2023), 2023, Qingdao, SD, China
Abstract
In order to solve the problem of lack of temporal and multi-scale information in gait recognition tasks based on gait energy images. A gait recognition method based on two-branch network is proposed. In the convolutional network branch, the attention mechanism and residual connection are combined to design a multi-scale feature extraction module to obtain effective multi-scale features. A simple temporal image is constructed and input into the long short-term memory network to extract temporal features. More accurate gait classification can be achieved by combining the two types of features. Experimental results on open gait dataset CASIA-B show that the proposed method has good classification effect.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Yueyu Huang, Hang Zhou, Yehong Chen, Xin Lu, Jia Yu, Ruiyu Han, and Jiawei Chen "Gait recognition method in surveillance video based on two-branch network", Proc. SPIE 12791, Third International Conference on Advanced Algorithms and Neural Networks (AANN 2023), 1279112 (9 October 2023); https://doi.org/10.1117/12.3005013
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Gait analysis

Feature extraction

Video

Convolution

Video surveillance

Feature fusion

Reflection

Back to Top