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

Cross-domain Behavior Recognition Based on Millimeter-wave Radar

Rendao Wang, Institute of Advanced Technology, University of Science and Technology of China, China, Binquan Wang, School of Cyber Science and Technology, University of Science and Technology of China, China, wbq0556@ustc.edu.cn
 
Suggested Citation
Rendao Wang and Binquan Wang (2024), "Cross-domain Behavior Recognition Based on Millimeter-wave Radar", APSIPA Transactions on Signal and Information Processing: Vol. 13: No. 4, e301. http://dx.doi.org/10.1561/116.00000262

Publication Date: 16 May 2024
© 2024 R. Wang and B. Wang
 
Subjects
 
Keywords
Human Activity RecognitionCross DomainUnsupervised Domain Adaptation
 

Share

Open Access

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

Downloaded: 425 times

In this article:
Introduction 
Related Work 
The Proposed Method 
Experiment 
Conclusion 

Abstract

Behavior recognition using millimeter wave (mmWave) signals has become a hot topic in recent years. However, existing works are mainly based on the premise that training samples and test samples have the same distribution, which leads to weak robustness of the network model to the environment during actual deployment. In this paper, we propose a domain adaptation framework for action recognition based on mmWave radar signals. Specifically, we use a convolutional neural network to construct our encoder to extract behavioral features in RF signals, use a semi-supervised learning method to pre-train the network, and finally we design a pseudo-label-based fine-grained domain adversarial network to further train the encoder. We conduct extensive experiments on our own collected behavioral data and two publicly available datasets. Experimental results demonstrate the superiority of our method.

DOI:10.1561/116.00000262

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.