Sensing, Tracking, and Recognition of Macro–Micro Hand Gestures Using Interferometric MIMO Radar
Xiangrong Wang, H. Liu, Xianghua Wang, Victor C. Chen, Moeness G. Amin, Kaiquan Cai
Abstract
In the past decades, radar-based hand gesture recognition (HGR) has gained increased attention in several applications involving contactless human-computer interaction (HCI). In this article, we propose both macro hand and micro finger gesture recognitions using an interferometric multi-input multi-output (MIMO) radar. The two principal signal processing modes of the radar are the conventional MIMO mode for initial positioning and the transmit interferometric mode for trajectory tracking. To achieve high precision sensing, a novel temporal and spatial interferometry is applied to acquire the subtle range and angular displacements of hand/finger motions, in lieu of the commonly used micro-Doppler (mD) spectrogram. Additionally, a ResNet50 convolution neural network (CNN) trained with 3-D space-time coordinates is used to provide HGR robustness against similar drawings. Simulation and experimental results show that the proposed interferometric MIMO radar performs rather well in sensing and tracking hand movements, achieving a recognition accuracy of 96.64%–96.33% for macro hand and micro finger gestures, respectively, and outperforming existing HGR methods.