Research on elevator passenger fall detection based on machine vision

Abstract

Aiming at the problem that the current elevator monitoring system cannot detect the accidental fall of passengers, this paper proposes a fall detection method based on machine vision and multi-feature fusion. First, moving targets were extracted by ViBe algorithm, and then the human body was marked with an external rectangle. Three characteristic parameters, namely the aspect ratio, effective area ratio and centroid acceleration of the human body, were calculated. At last, thresholds were set and SVM classification training was conducted to judge whether there was a fall event. Experimental results show that the algorithm has high accuracy and good stability. It can effectively reduce the injury caused by the elderly falling down in the elevator.