Multiple Human Tracking and Fall Detection Real-Time System Using Millimeter-Wave Radar and Data Fusion

Abstract

This paper investigates an indoor multiple human tracking and fall detection system based on the usage of multiple Millimeter-Wave radars from Texas Instruments. We propose a real-time system framework to merge the signals received from radars and track the position and body status of human objects. In order to guarantee the overall accuracy of our system, we develop novel strategies such as dynamic DBSCAN clustering based on signal energy levels and a possibility matrix for multiple object tracking. Our prototype system, which employs three radars placed on x-y-z surfaces, demonstrates higher accuracy than the solution in [1] (90%), with 98.5% and 98.2% accuracy in multiple human tracking and fall detection respectively. The accuracy reaches 99.7% for single human tracking.