Moving objects detection by block comparison

Motion segmentation has been an important issue in computer vision. It is fundamental in motion understanding. Moving objects can be traced only after they are detected in the video sequence using motion segmentation methods. In this paper a new method is proposed to segment moving objects from the sequence. This method is based on the comparison of the block average gray level of two images instead of pixels gray level directly. It is robust. The location and the approximate shape of the moving objects are worked out based on the simple analysis of the difference curve. The effectiveness of the method is validated by some examples illustrated in the paper