Gait recognition using spatio-temporal representation fusion learning network with IMU-based skeleton graph and body partition strategy
PLOS One · 2025
DOI: 10.1371/journal.pone.0332947 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Fo Hu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Wenzhou, Zhejiang University, Wenzhou, People's Republic of China. Hauptthemen laut MEDLINE: Gait. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Project of Traditional Chinese Medicine in Zhejiang Province, Medical and Health Science and Technology Project of Zhejiang Province, Ningbo Science Innovation Yongjiang 2035 Key Technological Breakthrough Project.
Abstract (Originalsprache)
The precise recognition of human lower limb movements based on wearable sensors is very important for human-computer interaction. However, the existing methods tend to ignore the dynamic spatial information in the process of executing human lower limb movements, leading to challenges such as reduced decoding accuracy and limited robustness. In this paper, we construct skeleton graph data based on inertial measurement unit (IMU) sensors. Also, a two-branch deep learning model, termed TCNN-MGCHN, is proposed to mine meaningful spatial and temporal feature representations from IMU-based skeleton graph data. Firstly, a temporal convolutional module (consisting of a multi-scale convolutional sub-module and an attention sub-module) is developed to extract temporal feature information with highly discriminative power. Secondly, a multi-scale graph convolutional module and a spatial graph edges’ importance weight assignment method based on body partitioning strategy are proposed to obtain intrinsic spatial feature information between different skeleton nodes. Finally, the fused spatio-temporal features are passed into the classification module to obtain the predicted gait movements and sub-phases. Extensive comparison and ablation studies are conducted on our self-constructed human lower limb movement dataset. The results demonstrate that TCNN-MGCHN delivers superior classification performance compared to the mainstream methods. This study can provide a benchmark for IMU-based human lower limb movement recognition and related deep-learning modeling works.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Institute of Wenzhou, Zhejiang University, Wenzhou, People's Republic of China.
- Zhejiang University, Hangzhou, People's Republic of China.
- Zhejiang University of Technology, Hangzhou, People's Republic of China.
- The First Affiliated Hospital of Zhejiang Chinese Medical University (Zhejiang Provincial Hospital of Chinese Medicine), Hangzhou, People's Republic of China.
ORCID-Profile: Qinxu Zheng, Hongsheng Chang
Förderung
- Science and Technology Project of Traditional Chinese Medicine in Zhejiang Province
- Medical and Health Science and Technology Project of Zhejiang Province
- Ningbo Science Innovation Yongjiang 2035 Key Technological Breakthrough Project
- Natural Science Foundation of Zhejiang Province
- Key Laboratory of Intelligent Processing Technology for Digital Music (Zhejiang Conservatory of Music), Ministry of Culture and Tourism
- China Postdoctoral Science Foundation
Zitieren
APA
Hu, F., Zheng, Q., Ye, X., Qiao, Z., Xiong, J., & Chang, H. (2025). Gait recognition using spatio-temporal representation fusion learning network with IMU-based skeleton graph and body partition strategy. PLOS One. https://doi.org/10.1371/journal.pone.0332947
Vancouver
Hu F, Zheng Q, Ye X, Qiao Z, Xiong J, Chang H. Gait recognition using spatio-temporal representation fusion learning network with IMU-based skeleton graph and body partition strategy. PLOS One. 2025. doi:10.1371/journal.pone.0332947
BibTeX
@article{Hu2025,
author = {Hu, Fo and Zheng, Qinxu and Ye, Xuanjie and Qiao, Zukang and Xiong, Junlong and Chang, Hongsheng},
title = {Gait recognition using spatio-temporal representation fusion learning network with IMU-based skeleton graph and body partition strategy},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0332947}
}
EUVIMED