TY - JOUR
T1 - A Lightweight Multiscale Neural Network for Indoor Human Activity Recognition Based on Macro and Micro-Doppler Features
AU - Yang, Xiaopeng
AU - Gao, Weicheng
AU - Qu, Xiaodong
AU - Yin, Peng
AU - Meng, Haoyu
AU - Fathy, Aly E.
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2023/12/15
Y1 - 2023/12/15
N2 - Through-the-wall radar (TWR) achieves indoor human activity recognition (HAR) by extracting Doppler and micro-Doppler features. However, the conventional deep learning-based HAR methods have the shortcomings of low accuracy and long inference time. To solve these problems, a lightweight multiscale neural network for indoor HAR based on macro and micro-Doppler features (TWR-FMSN) is proposed in this article. In the proposed method, the trajectories of macroscopic Doppler and microscopic Doppler features are defined first and the integrated models are applied to label the trajectories at both scales for recognition. An efficient attention-mechanism-based lightweight target detection neural network with the Lagrangian trajectory estimation is proposed to obtain macro-Doppler features of human motion. In addition, a kernel-distance-based micro-Doppler labeling method is utilized to obtain the micro-Doppler features of human motion. Finally, all the extracted macro-Doppler and micro-Doppler features are concatenated together for the decision of indoor HAR. The effectiveness of the proposed method is verified by experiments, and the results show that the proposed method can significantly reduce the inference time while retaining high recognition accuracy, which shows great potential in real-time deployment for the practical application.
AB - Through-the-wall radar (TWR) achieves indoor human activity recognition (HAR) by extracting Doppler and micro-Doppler features. However, the conventional deep learning-based HAR methods have the shortcomings of low accuracy and long inference time. To solve these problems, a lightweight multiscale neural network for indoor HAR based on macro and micro-Doppler features (TWR-FMSN) is proposed in this article. In the proposed method, the trajectories of macroscopic Doppler and microscopic Doppler features are defined first and the integrated models are applied to label the trajectories at both scales for recognition. An efficient attention-mechanism-based lightweight target detection neural network with the Lagrangian trajectory estimation is proposed to obtain macro-Doppler features of human motion. In addition, a kernel-distance-based micro-Doppler labeling method is utilized to obtain the micro-Doppler features of human motion. Finally, all the extracted macro-Doppler and micro-Doppler features are concatenated together for the decision of indoor HAR. The effectiveness of the proposed method is verified by experiments, and the results show that the proposed method can significantly reduce the inference time while retaining high recognition accuracy, which shows great potential in real-time deployment for the practical application.
KW - Deep learning
KW - human activity recognition (HAR)
KW - lightweight neural network
KW - micro-doppler
KW - through-the-wall radar (TWR)
UR - http://www.scopus.com/inward/record.url?scp=85166780161&partnerID=8YFLogxK
U2 - 10.1109/JIOT.2023.3301519
DO - 10.1109/JIOT.2023.3301519
M3 - Article
AN - SCOPUS:85166780161
SN - 2327-4662
VL - 10
SP - 21836
EP - 21854
JO - IEEE Internet of Things Journal
JF - IEEE Internet of Things Journal
IS - 24
ER -