APSIPA Transactions on Signal and Information Processing > Vol 13 > Issue 4

CRNet: Robust Millimeter Wave Gait Recognition Method Based on Contrastive Learning

Zhen Meng, Beijing University of Posts and Telecommunications, China, Anfu Zhou, Beijing University of Posts and Telecommunications, China, Huadong Ma, Beijing University of Posts and Telecommunications, China, mhd@bupt.edu.cn , Qian Zhang, Hong Kong University of Science and Technology, China
 
Suggested Citation
Zhen Meng, Anfu Zhou, Huadong Ma and Qian Zhang (2024), "CRNet: Robust Millimeter Wave Gait Recognition Method Based on Contrastive Learning", APSIPA Transactions on Signal and Information Processing: Vol. 13: No. 4, e300. http://dx.doi.org/10.1561/116.00000067

Publication Date: 16 May 2024
© 2024 Z. Meng, A. Zhou, H. Ma and Q. Zhang
 
Subjects
 
Keywords
Gait RecognitionMillimeter Wave SensingContrastive Learning
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 394 times

In this article:
Introduction 
Related Work 
Motivation 
Method 
Experiment 
Conclusion and Future Work 
Acknowledgments 
References 

Abstract

Gait recognition based on millimeter waves (mmWave) has a wide range of applications, such as smart homes and health monitoring, and attracted extensive attention due to its non-contact, privacy protection, and light-independent characteristics. Existing gait recognition based on mmWave performs well on the datasets collected at a single time or environment. However, the recognition accuracy declines significantly with the time and environment domains shifting, which affects its practical applications. In this paper, we propose a novel mmWave gait recognition CRNet that is robust to both time and environment, which is realized through two-stage training. Specifically, the first stage designs a contrastive learning strategy to pre-train the encoder module, which aims at learning the general gait features across different seen time and environment domains. The second stage further trains the classification module based on specific recognition tasks. After the two-stage training, CRNet experiments on test sets with unseen time or environment domains. We collect a mmWave-based multiperson gait recognition dataset with multiple time and environment domains. Experiments show that CRNet still performs well in unfamiliar domains which increases the accuracy from 75.7% to 91.2% compared to the baseline.

DOI:10.1561/116.00000067

Companion

APSIPA Transactions on Signal and Information Processing Special Issue - Emerging Wireless Sensing Technologies for Smart Environments
See the other articles that are part of this special issue.