Research on Video Frame and Image Segmentation

摘要：

A BS process involves building a model of the background and extracting regions of the foreground (moving objects) with the assumptions that the camera remains stationary and there exist no movements in the background. Video object extraction is a critical task in multimedia analysis and editing. Normally,the user provides some units of foreground and background,and then the target object is extracted from the video sequence. In this paper,we propose a object segmentation system that integrates a clustering model with Markov random field-based contour tracking and graph-cut image segmentation. The contour tracking propagates the shape of the target object,whereas the graph-cut refines the shape and improves the accuracy of video segmentation. Experimental results show that our segmentation system is efficient.

关键词： Video object extraction Markov random field Graph-cut

作者: Shilin Zhang Heping Li Shuwu Zhang

作者单位: Coputer Faculty,North China University of Technology,Beijing,China High Technology and Innovation Ce High Technology and Innovation Center,Institute of Automation,Chinese Academy of Sciences,Beijing,Ch

会议类型: 国际会议

会议名称: 2011 International Conference on Opto-Electronics Engineering and Information Science(2011光电电子工程与信息科学国际会议 ICOEIS 2011)

会议地点: 西安

会议语种:英文

页码: 1223-1225

在线出版日期: 2011-12-23（万方平台首次上网日期，不代表论文的发表时间）