一种新的基于时空信息的视频分割  

A New Region-labeling Algorithm and Its application to Segmentation of Video Sequences

作　　者：张庆利[1] 张兆扬[1] 

机构地区：[1]上海大学通信工程系,上海200030

出　　处：《电视技术》2004年第11期4-7,共4页Video Engineering

基　　金：国家自然科学基金项目(60172020)

摘　　要：提出了一种新的基于时空信息的视频分割算法,即先将原始图像标记成不同的区域,然后以帧间差分得到的对象运动信息作为评判准则,将这些区域分别归类于前景对象和背景,达到对象分割的目的。特别是在区域标记的过程中,采用了一种新的基于分水岭的区域标识技术。通过对标准图像序列的实验结果可以看到,利用该算法能够较精确地分割出视频对象。In this paper, we propose a new segmentation method to separate the moving objects from the background in a generic video sequence. It is to support the content-based functionalities focused by the MPEG-4. The proposed algorithm discriminates background from foreground by means of spatio-temporal information. First, the original image is labeled into different regions. Then, some regions are merged to form video object according to the inter-frame difference information as judgement criterion, and others are discarded. Experimental results obtained on some typical MPEG-4 sequences are shown in order to illustrate the segmentation algorithm performance.

关 键 词：视频对象分割 形态学 分水岭算法 帧间差分 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]