A Meta-Learning-Based Approach for Hand Gesture Recognition Using FMCW Radar
Zhongyu Fan, Haifeng Zheng, Xinxin Feng · 2020
In recent years, the frequency modulated continuous wave (FMCW) radar have been widely applied for hand gesture detection and recognition. In this paper, we propose a Meta-Learning-based multi-branch network with Range-Doppler-Angle multi-dimensional parameters (ML-RDA-Net) for FMCW radar based hand gesture recognition. Furthermore, we construct the Range-Frame-Map, Doppler-Frame-Map, and Angle-Frame-Map datasets for the proposed model. Finally, we carry out extensive experiments to evaluate the performance of the proposed scheme. The experimental results show that the proposed model with multidimensional parameter dataset can achieve a 3%-7% accuracy improvement with much fewer samples comparing with some existing methods.