A novel algorithm of adaptive background estimation

We propose an adaptive background estimation algorithm for an outdoor video surveillance system. In order to enhance the ability of adaptation to illumination changes and variant noise in long-term running, an improved Kalman filtering model based on the local-region is discussed to dynamically estimate a background image, in which the parameters are predicted by a recursive-least-square adaptive filter. The experimental results on real-world video show that the algorithm can perform robustly and effectively.