TripleM:Multidimensional Feature Separation of Multiple Gestures in Multi-Person Scenarios Based on FMCW Radar

A remarkable process has been made in hand gesture recognition based on radar sensors, which has potential application in human-computer interaction. However, existing research is mostly conducted for only one hand gesture in the sensor's field of view, leading to limitations in some practical scenarios when multiple gestures exist simultaneously. In this paper, we propose a method to estimate the number of multiple gestures precisely in multi-person scenarios firstly, then separates the mixed blind source signals to acquire each motion signal. Finally, we extract multidimensional features for each separated gesture. Extensive experiments are carried out based on commer-cial frequency modulated continuous wave (FMCW) single-input multi-output (SIMO) millimeter-wave radar systems to verify the effectiveness of this approach.