基于内容的多层次语义视频对象提取方法研究  

Algorithm of content-based multi-hierarchy semantic video object extraction

作　　者：李春燕[1] 杨树堂[1] 陆松年[1] 

机构地区：[1]上海交通大学现代通信所,上海200240

出　　处：《信息技术》2008年第9期31-34,共4页Information Technology

摘　　要：视频对象的提取在序列图像的分析中起着重要作用。提出一个基于内容的多层次视频的对象提取算法,利用高斯马尔可夫模型对其进行颜色和纹理的混合特征图像分割。利用Normalize-cut准则,对其运动信息进行分析,然后进行区域聚合,即得到具有语义的视频对象。对于背景运动信息较丰富的序列图像可以取得良好的提取效果。Extracting of semantic video object plays an important role in analysis of serial images. This paper proposes a new approach of content-based multi-hierarehy semantic video object extraction. It uses Gaussian- Markov random field model for image segmentation, which aims at combining color and texture features. The grouping process is based on the analysis of motion information of the different feature classes via normalize-cut mles. The semantic video objects are extracted by the proposed method. It has good results in videos of which background has rich motion information.

关 键 词：基于内容的分割和聚合 视频对象分割 高斯马尔可夫模型 Normalize—cut准则 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]