Video Object Segmentation of Still Background

摘要：

In this paper, according to statistical features of the foreground and the background, we propose a novel video object segmentation algorithm, this algorithm is a Bayes decision-making theory with least risk base on still background. Experiments on the platform of TMS320C6711 IDK(Imaging Developers Kit) of Texas Instruments proves that this algorithm can segment video object and meet needs of applications of MPEG-4.

关键词： video object segmentation still background Bayes decision-making theory

作者: Jianlin Zhao Zeju Wu Jundong Chen Jing Wang

作者单位: College of Communication and Electronic Engineering, Oing dao Technological University, Qingdao 2660 College of Communication and Electronic Engineering, Oing dao Technological University, Qingdao 2660 Louisiana Tech University in USA Radios and Television Bureau of Jiaozhou Qingdao 266300, China

会议类型: 国际会议

会议名称: 2009 International Workshop on Information Security and Application(2009 信息安全与应用国际研讨会)

会议地点: 青岛

会议语种:英文

页码: 605-608

在线出版日期: 2009-11-21（万方平台首次上网日期，不代表论文的发表时间）