A novel method for moving object detection in intelligent video surveillance systems

In this paper, the existing approaches to and open problems of extracting moving objects from a video sequence were reviewed briefly, and a novel method was proposed and verified. The method extracts contours of moving objects mainly by combining gradient information extracting with three-frame-differencing and connectivity-testing-based noise reduction. The results of theoretical analyses and computer simulation show that the method has some advantages over its competitors, e.g., having wider application ranges, less computation amount and better real-time performance, and being more robust in a noisy environment.