视频对象分割及跟踪方法研究  

Video Objects Segmentation and Tracking in Video Sequences

作　　者：沈未名[1] 江柳[1] 种衍文[1] 

机构地区：[1]武汉大学多媒体网络通信工程湖北省重点实验室,武汉市珞喻路129号430079

出　　处：《武汉大学学报（信息科学版）》2004年第3期274-277,共4页Geomatics and Information Science of Wuhan University

基　　金：武汉大学科研启动基金资助项目 ( 5 0 2 2 73 0 10 )

摘　　要：讨论和分析了视频对象全自动提取及后续帧中的跟踪过程及采用的方法 ,对其算法、分割性能和结果进行了比较和评述。并结合Hausdorff和Snake跟踪器 ,对初始对象轮廓进行跟踪。结果证明 。The ISO MPEG4 has attracted much attention recently for providing a standard solution for object-based coding and multimedia data access and manipulation. So content-based representation and coding of the visual information is currently becoming an extremely active research field. Object-based video coding can provide greater compression ratio and better quality of reconstructed images. Video objects segmentation is a key technology in object-based video coding and multimedia data access etc. This paper depictes and analyzes and compares the video objects automatic segmentation and tracking processes and methods. Existing problems and development prospect in this field are described.

关 键 词：视频对象 对象分割 对象跟踪 聚类分析 光流 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]