A Novel Method Based on Optical Flow Combining with Wide Residual Network for Fall Detection

Abstract

Fall is an abnormal activity event in daily life, which is becoming a major cause of accidental death for the elderly. The purpose of fall detection is to minimize serious consequences and negative impacts after falling. Recently, most conventional vision-based fall detection methods mainly rely on hand-crafted features, which is inclined to be influenced by noises, etc. In this paper, a novel method is proposed to detect fall event during a video sequence by combining optical flow and wide residual network. The wide residual network contains fewer layers and achieves the same performance as residual network, which can make the neural network train faster. In addition, to model the video motion, we adopt optical flow images as input to the wide residual network. And finally, softmax classifier is utilized to distinguish fall event. The experimental results also confirm the fact that the proposed algorithm can achieve a reliable accuracy.