Moving objects detection based on space vector difference

Based on the gray-level change characteristic between two successive video frames, gray information are broadly used for the detection of moving objects. However, the method will lose a lot of useful color information. In this paper, we propose a new approach to detect moving objects in the color space. The method utilizes the space vector difference to obtain a difference map between current video frame and background model. Then, by analyzing characteristic of the difference map histogram, an adaptive threshold is automatically calculated. The threshold can effectively separate moving objects and remove various significant noises in current video frame. The experimental results on several standard sequences demonstrate the efficiency and the high accuracy of the proposed method.