Moving target detection algorithm in image sequences based on edge detection and frame difference

In order to overcome the drawbacks of the traditional frame-difference method that is used in moving target detection, and to achieve both accurate and robust detection result, a novel approach for moving objects detection based on improved Canny edge detection and adaptive frame difference method is proposed in this paper. Firstly, select the threshold value of three-frame difference method adaptively by using Otsu algorithm, but the edge of target is not continuous enough. And then the boundary of current frame is obtained by using improved Canny operator, the edge information is more accurate, complete and continuous. Finally integrate the two results and use morphological approach to process the isolated noise spot and the hole in the target area, complete the moving target detection. Experimental results show that this algorithm can improve the moving target detection-rate in real-time.