A Level-set Based Tracking Approach for Surveillance Video with Fusion and Occlusion

Traditional level-set-based methods of tracking contours suffered from occlusion and fusion. In this paper, the proposed method introduces dynamic incident detection to find and handle occlusion and fusion. Color histogram of the hue component in HSV color space is used to identify the objects re-entering after occlusion. On the other hand, object features including the size and the motion pattern are utilized to remove the fake regions that are fused with the object region. Besides, a comprehensive foreground extraction (CFE) method based on the combination of background subtraction and Local Binary Pattern (LBP) is proposed. It is fast and robust. Our method is Experiments show that the proposed approach outperforms previous methods on both speed and subjective quality.