Multi-Hand Gesture Recognition Using Automotive FMCW Radar Sensor

With the development of human–computer interaction(s) (HCI), hand gestures are playing increasingly important roles in our daily lives. gesture recognition (HGR), users can play virtual games together, control smart equipment, etc. As a result, this paper presents multi-hand system using automotive frequency modulated continuous wave (FMCW) radar. Specifically, we first constructed range-Doppler map (RDM) and range-angle (RAM), then suppressed spectral leakage, dynamic static interferences. Since received echo signals with mixed propose spatiotemporal path selection algorithm to separate gestures. A dual 3D convolutional neural network-based feature fusion network is proposed for extraction classification. We developed FMCW radar-based platform evaluate performance method; experimental results show that method achieve an average accuracy 93.12% when eight two hands performed simultaneously.