Gait recognition with global–local feature fusion based on swin transformer-3DCNN
Signal, Image and Video Processing · 2025-01 · 19 (1)
DOI: 10.1007/s11760-024-03612-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Signal, Image and Video Processing, online erschienen am 03.12.2024. Verfasst von Ting Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: Chinese Customs.
Abstract (Originalsprache)
Gait recognition is a biometric technology that can be used for identification over long distances and has great application prospects in the field of public security. Currently, the majority of gait recognition approaches rely on either global or local information from gait features for the representation. However, representing global information frequently leads to the loss of intricate details of gait features, while local information may neglect the interrelations among different local features. Therefore, in this paper, a novel Swin Transformer-Conventional Neural Network Gait framework is proposed to effectively integrate both global and local information of gait features for the recognition. Within the framework, the Swin transformer module is incorporated to extract global information. The Swin transformer employs shift windows for hierarchical feature extraction, facilitating improved capture of global features and long-range dependencies in images. Within local branches, feature maps are segmented for feature extraction by using multiple 3D Convolutional Neural Networks to enhance the capture of local information. Furthermore, attention module is introduced to boost the locally extracted information from Convolutional Neural Network. Through results of experiments, our approach has substantially enhanced performance in gait recognition, achieving optimal recognition across most conditions.
Förderung
- Chinese Customs
Zitieren
APA
Wang, T., Zhou, G., Pu, Y., Moreno, R., & Yang, G. (2025). Gait recognition with global–local feature fusion based on swin transformer-3DCNN. Signal, Image and Video Processing, 19(1). https://doi.org/10.1007/s11760-024-03612-4
Vancouver
Wang T, Zhou G, Pu Y, Moreno R, Yang G. Gait recognition with global–local feature fusion based on swin transformer-3DCNN. Signal, Image and Video Processing. 2025;19(1). doi:10.1007/s11760-024-03612-4
BibTeX
@article{Wang2025,
author = {Wang, Ting and Zhou, Guanghang and Pu, Yanfeng and Moreno, Ramón and Yang, Guoping},
title = {Gait recognition with global–local feature fusion based on swin transformer-3DCNN},
journal = {Signal, Image and Video Processing},
year = {2025},
volume = {19},
number = {1},
doi = {10.1007/s11760-024-03612-4}
}
EUVIMED