Author:
Huan Sha,Wang Zhaoyue,Wang Xiaoqiang,Wu Limei,Yang Xiaoxuan,Huang Hongming,Dai Gan E.
Abstract
AbstractRadar-based human activity recognition (HAR) offers a non-contact technique with privacy protection and lighting robustness for many advanced applications. Complex deep neural networks demonstrate significant performance advantages when classifying the radar micro-Doppler signals that have unique correspondences with human behavior. However, in embedded applications, the demand for lightweight and low latency poses challenges to the radar-based HAR network construction. In this paper, an efficient network based on a lightweight hybrid Vision Transformer (LH-ViT) is proposed to address the HAR accuracy and network lightweight simultaneously. This network combines the efficient convolution operations with the strength of the self-attention mechanism in ViT. Feature Pyramid architecture is applied for the multi-scale feature extraction for the micro-Doppler map. Feature enhancement is executed by the stacked Radar-ViT subsequently, in which the fold and unfold operations are added to lower the computational load of the attention mechanism. The convolution operator in the LH-ViT is replaced by the RES-SE block, an efficient structure that combines the residual learning framework with the Squeeze-and-Excitation network. Experiments based on two human activity datasets indicate our method’s advantages in terms of expressiveness and computing efficiency over traditional methods.
Publisher
Springer Science and Business Media LLC
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献