Robust Doppler-Based Gesture Recognition With Incoherent Automotive Radar Sensor Networks

In this letter, the capabilities of an incoherent radar sensor network for robust Doppler-based gesture recognition are investigated, and a significant performance boost is demonstrated. A comprehensive dataset is recorded with an incoherent sensor network consisting of three time-synchronized 77GHz frequency-modulated continuous wave radars. Based on this dataset, we show that differential Doppler features obtained from the varying viewing angles result in a significant multistatic gain for classification, particularly for high intraclass variations and low Doppler frequencies. For the most complex dataset, cross-user validation accuracy of a convolutional neural network with optimized data fusion is improved by 7.4% to an overall value of 87.1%, which we regard to be high as gestures are not designed for distinguishability but reflect everyday control and communication signals.