Speeding uplow rank matrix recovery for foreground separation in surveillance videos

Video surveillance currently is one of the most active research topics in public safety and security, in which foreground extraction is important and fundamental for further processing, such as target tracking, activity recognition, and behavior prediction. In this paper, by assuming the background is highly correlated across different frames, we propose to separate foregrounds via speeded up low rank matrix recovery. The proposed method first shrinks the scale of data to roughly catch outliers (foregrounds) of the background. Based on the outliers, we design a sampling strategy that selects a number of frames to construct the low rank model of background. According to the constructed background model, our method further recovers both the background and the foreground for the rest frames in a reconstruction manner. Experimental results on both simulated and real data demonstrate the clear advantage of our approach compared to the state of the arts, in terms of accuracy and efficiency.