Automatic Moving Object Segmentation Based on Edge Features
Zhang Xiao-yan①; Zhao Rong-chun①; Ma Zhi-qiang②; Qian Yuan②
①College of Computer, Northwestern Polytechnical University, Xi’an 710072, China;②The Telecommunication Engineering Institute, Air Force Engineering University, Xi’an 710077, China
Abstract：In order to segment the moving objects accurately, an edge based moving objects segmentation algorithm is proposed in this paper. First of all, the initial edge model of the moving object is obtained on the basis of the adaptive change detection method and Canny edge detection. Secondly, the binary edge model is tracked and updated to accommodate rotation and changes in shape of the tracked object. Finally, the outer contour of the moving object is determined based on the mathematical morphological operation and an improved active contour which uses the gradient vector as the external force guides the initial outer contour moving to the actual contour. The proposed algorithm is robust to the entire motion and local deformation of object, adaptable to the complex background and can obtain the accurate moving object contour.
2007, Vol. 29 
