Video Based Fall Detection using Features of Motion, Shape and Histogram

Abstract

Falls are one of the greatest risks for the older adults living alone at home. This paper presents a novel visual-based fall detection approach to support independent living for older adults. The proposed approach employs three unique features; motion information, human shape variation and projection histogram to detect a fall. Motion information of a segmented silhouette, which when extracted can provide a useful cue for classifying different behaviours. Also, the projection histogram and variation in human shape can be used to describe human body postures and subsequently fall events. The proposed approach presented here extracts motion information, using best-fit approximated ellipse around the human body and in addition projection histogram features to further improve the accuracy of fall detection. Experimental results are presented and show high fall detection rate of 99.81% with partially occluded video data.