A Parameter Estimation and Deep Learning Hybrid Extraction Network for Multidirectional Human Activity Recognition Based on mmWave Radar

In the realm of human activity recognition (HAR) based on radar, the prevailing methods have been characterized by excessive complexity and a singular focus on a specific motion direction, posing challenges for practical deployment. This article introduces a lightweight parameter estimation and deep learning hybrid extraction network (PDHE-Net) for achieving multidirectional HAR based on mmWave radar. The network consists of a lightweight deep learning feature extraction (LDE) module, a parameter estimation module, and a classification module. Specifically, the LDE module consists of multiple layers of group convolution and Ghost module, aimed at extracting deep features from the time-Doppler (TD) maps. Parameter estimation module is employed to capture direction-independent features from the TD map. Ultimately, multidimensional features extracted by the LDE module and parameter estimation module are classified to realize multidirectional HAR. To verify the performance of the proposed method, experimental data was collected, comprising six categories of activities wherein targets moved in multidirections. The experimental results demonstrate that the proposed PDHE-Net achieved a recognition accuracy of 96.67% on the dataset, outperforming the state-of-the-art methods by 2.92%, while significantly reducing complexity.