The motion detection based on background difference method and active contour model

For the traditional moving target detection algorithm exists some problems such as determining threshold problems and more sensitive to noise, this paper presents a rapid extraction method based on variation level set of the edge blur moving objects. This method used the background difference method extract initial outline of moving target, and then used active contour model constraint edge detection; the final combined variation level set method with a second evolution to obtain accurate image segmentation. Experiments show that this method can rapidly and accurately segment moving object, for moving objects of different shapes and the rules of small-angle shot has a good adaptability and robustness.