A new method of moving object detection

This paper describes a method of moving object detection that integrates image gradient information with motion information. We use one multi-scale morphological gradient operator to detect gradient information. This operator has a very good effect to the detail of the edge location. The result is superior to the traditional method in edge continuity and isotropy. Past approaches have built detection based on motion information and edge information, but ours is the first to use multi-scale morphological gradient operator The implementation described can operates on lower resolution images under difficult conditions. Novel contributions of this paper include: 1) Based on multi-scale morphological gradient operator, this algorithm is robust to noise, objects shadow and illumination. 2) Using Inter-frame difference and only the first two frames, this detection has small computation, so it is suitable for real-time application. 3) This method can detect rigid-body or non rigid-body moving object among video sequence with complicated background.