Automatic extraction of moving object in video sequences

On the base of combining change-detection-based segmentation approach and spatial edge information by Canny edge detection, an algorithm is proposed that a local contrast enhancement is applied to improve the contrast between the foreground object and background in the pre-processing stage, so that the contrast between the foreground and background is enhanced, and the problem caused by low contrast is solved. A filter was designed to remove a modicum of noise caused by contrast enhancement processing. Then for the complex background, the algorithm utilizes probability-based classification to accumulate the background information, which is needed by the original segmentation algorithm, and consequently realizes the capturing of the background information automatically; Finally, the paper proposed that three situations should be discussed in the process of accumulating background information, and the problem of part loss of the segment due to the object being still for a long time. The proposed algorithm is evaluated on several MPEG-4 test sequences and produces promising results.