| 基于内容的多层次语义视频对象提取方法研究 |
| |
| 引用本文： | 李春燕,杨树堂,陆松年. 基于内容的多层次语义视频对象提取方法研究[J]. 信息技术, 2008, 32(9) |
| |
| 作者姓名： | 李春燕 杨树堂 陆松年 |
| |
| 作者单位： | 上海交通大学现代通信所,上海,200240 |
| |
| 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.
|
| 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 |
Algorithm of content-based multi-hierarchy semantic video object extraction |
| |
| LI Chun-yan,YANG Shu-tang,LU Song-nian. Algorithm of content-based multi-hierarchy semantic video object extraction[J]. Information Technology, 2008, 32(9) |
| |
| Authors: | LI Chun-yan YANG Shu-tang LU Song-nian |
| |
| Affiliation: | LI Chun-yan,YANG Shu-tang,LU Song-nian(Institute of Modern Communication,Shanghai Jiaotong University,Shanghai 200240,China) |
| |
| Abstract: | Extracting of semantic video object plays an important role in analysis of serial images.This paper proposes a new approach of content-based multi-hierarchy 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 rules.The semantic video objects are extracted by the proposed method.It has good resu... |
| |
| Keywords: | content-based segmentation and grouping semantic video object Gaussian-Markov random field model normalize-cut rule |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
