A novel method of background subtraction for indoor surveillance

Abstract

In this paper, a novel method of background subtraction and update is proposed for indoor surveillance. It is based on the hypothesis that the foreground pixel's luminance and chroma fluctuate due to the movement of object. Different from the previous algorithms, this method takes each pixel's time continuity in video sequence into consideration. It still works well even the background is visible for a short time. The experimental results show that the proposed method has good performance for indoor scenes.