Generalizable Indoor Human Activity Recognition Method Based on Micro-Doppler Corner Point Cloud and Dynamic Graph Learning

TL;DR

This paper introduces a novel indoor human activity recognition approach using micro-Doppler corner point clouds and dynamic graph learning, significantly improving model generalization across different testers in radar-based scenarios.

Contribution

The paper presents a new method combining micro-Doppler corner extraction and dynamic graph neural networks to enhance generalization in indoor activity recognition.

Findings

Strong generalization ability across different testers

Effective micro-Doppler corner feature extraction

Improved recognition accuracy demonstrated through experiments

Abstract

Through-the-wall radar (TWR) human activity recognition can be achieved by fusing micro-Doppler signature extraction and intelligent decision-making algorithms. However, limited by the insufficient priori of tester in practical indoor scenarios, the trained models on one tester are commonly difficult to inference well on other testers, which causes poor generalization ability. To solve this problem, this paper proposes a generalizable indoor human activity recognition method based on micro-Doppler corner point cloud and dynamic graph learning. In the proposed method, DoG-{\mu}D-CornerDet is used for micro-Doppler corner extraction on two types of radar profiles. Then, a micro-Doppler corner filtering method based on polynomial fitting smoothing is proposed to maximize the feature distance under the constraints of the kinematic model. The extracted corners from the two types of radar profiles are concatenated together into three-dimensional point cloud. Finally, the paper proposes a dynamic graph neural network (DGNN)-based recognition method for data-to-activity label mapping. Visualization, comparison and ablation experiments are carried out to verify the effectiveness of the proposed method. The results prove that the proposed method has strong generalization ability on radar data collected from different testers.