Robust abnormity detecting and tracking using correlation coefficient

Jin Zheng, Bo Li, Chun-lian Yao

Abstract: Abnormity detection based on computer vision is the foundation of high-level automatic surveillance that includes objects recognition, tracking and alarm etc. In this paper, a robust abnormity detection algorithm using improved correlation coefficient is proposed. It assembles every pixel and its neighboring pixels to form a vector, and computes correlation coefficient to measure the similarity of corresponding window in the background image and current image. When the correlation coefficient is bigger than the adaptive threshold, the algorithm processes pixel level detection. Moreover, using k-means and correlation coefficient respectively, it realizes the clustering and tracking of the abnormity objects. The experimental results show the algorithm is robust against noise disturbance, illumination change, shadows and reflection effect. It can detect abnormity precisely, and improve the surveillance system's adaptability for the complicated environment greatly.