首页 | 本学科首页   官方微博 | 高级检索  
     

时空结合的视频对象分割方法
引用本文:崔凤玉,赵彦玲.时空结合的视频对象分割方法[J].山东工业大学学报,2005,35(5):78-82.
作者姓名:崔凤玉  赵彦玲
作者单位:[1]山东大学齐鲁医院CT室,山东济南250012 [2]山东省计算中心多媒体实验审,山东济南250014
摘    要:视频对象分割是MPEG(Moving Picture Experts Group)-4视频编码的关键技术.针对常用方法的不足,提出了1种新的视频对象分割算法.形态学滤波后利用分水岭算法实现空域分割,时域分割采用二次帧差求交集的方法获取运动区域,然后时空结合.仿真结果表明该算法简单、快速、准确。

关 键 词:形态学滤波  分水岭  运动区域  二次帧差
文章编号:1672-3961(2005)05-0078-05
收稿时间:2005-01-18

Spatio-temporal segmentation method of moving objects
CUI Feng-yu, ZHAO Yan-ling.Spatio-temporal segmentation method of moving objects[J].Journal of Shandong University of Technology,2005,35(5):78-82.
Authors:CUI Feng-yu  ZHAO Yan-ling
Affiliation:1. Department of CT, Qilu Hospital of Shandong University, Jinan 250012, China; 2. Office for Multimedia, Shandong Computer Science Center, Jinan 250014, China
Abstract:Video object segmentation is a key technology in MPEG-4 video coding. A new method is proposed, in which, a spacial segmentation is made by the watershed method after morphological filtering, and the moving regions are obtained by the intersection of three twice-frame-diffemnce images. Then, the temporal information with spacial inforrnation is intcgrated. The proposed method proves to be simple, fast and accurate.
Keywords:morphological filter  watershed  moving regions  twice-frame-difference
本文献已被 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号