Real-Time and Automatic Segmentation Technique for Multiple Moving Objects in Video Sequence

This paper presents a real-time and automatic segmentation technique for moving objects in video sequence based on differences accumulation. Effective background is modeled by accumulative frame-to-frame differences, and moving objects in video sequence could be extracted using background subtraction method, which is different from conventional movement based detection methods. Enhanced Otsu segmentation method is presented, which thresholds the background difference image much more accurately, and overcomes conventional shortcomings of Otsu method. The boundary of moving objects is extracted after composite morphological operation. Improved localization method based on conventional region growing is presented, which shows effective and accurate results. Experiments are performed using different video sequence under different environment, which show that the proposed works well and shows satisfactory result.