论文部分内容阅读
MPEG-4 is a basic tool for interactivity and manipulation of video sequences. Video object segmentation is a key issue indefining the content of any video sequence, which is often divided into two steps: initial object segmentation and object tracking. Inthis paper, an initial object segmentation method for video object plane(VOP) generation using color information is proposed. Based on3 by 3 linear templates, a cellular neural network (CNN) is used to implemented object segmentation, The Experimental results arepresented to verify the efficiency and robustness of this approach.