|
|||||
|
|
| 基于机器学习的压缩域镜头分割技术 | |
| 引用本文： | 刘生贵,聂幼三,路红,薛向阳.基于机器学习的压缩域镜头分割技术[J].电讯技术,2007,47(1):203-208. |
| 作者姓名： | 刘生贵 聂幼三 路红 薛向阳 |
| 作者单位： | 1. 四川大学,光电系,成都,610064 2. 西南电子电信技术研究所,成都,610041 3. 复旦大学,计算机科学与工程系,上海,200433 |
| 摘 要： | 为了进行视频结构化和视频内容分析,需要准确有效地提取视频镜头的边界信息.为此提出了一种利用支持向量机(SVM)学习压缩域特征的算法进行镜头边界检测,只需简单译码即可得到MPEG1/2等各类视频流压缩域的特征信息.经TRECVID2005镜头边界检测集的评测,该算法在保证查全率和检测精度的情况下获得了满意的效果. |
| 关 键 词： | 镜头分割 视频结构分析 MPEG压缩域 支持向量机(SVM) |
| 文章编号： | 1001-893X（2007）01-0203-06 |
| 收稿时间： | 2006/5/14 0:00:00 |
| 修稿时间： | 2006-05-142006-09-20 |
Shot Segmentation Technology by Using Machine Learning on Compressed Domain |
|
| LIU Sheng-gui,NIE You-san,LU Hong,XUE Xiang-yang.Shot Segmentation Technology by Using Machine Learning on Compressed Domain[J].Telecommunication Engineering,2007,47(1):203-208. | |
| Authors: | LIU Sheng-gui NIE You-san LU Hong XUE Xiang-yang |
| Affiliation: | 1. Department of Optoelectronics , Sichuan University, Chengdu 610064, China; 2. Southwest Electronic and Telecommunication Institute, Chengdu 610041, China; 3. Department of Computer Science and Engineering, Fudan University, Shanghai 200433, China |
| Abstract: | To analyze the video structure and content,shot boundary features should be extracted exactly and efficiently.In this paper,a novel approach is proposed to detect shot boundaries by using Support Vector Machine(SVM) on the compressed domain features,which can be extracted without fully decompressing MPEG-1/2 video.Experimental results on TRECVID2005 shot boundary evaluation demonstrate that the proposed approach can obtain promising performance under good recall and precision. |
| Keywords: | shot boundary detection video structure analysis MPEG compressed domain support vector machine(SVM) |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |
| 点击此处可从《电讯技术》浏览原始摘要信息 | |
| 点击此处可从《电讯技术》下载全文 | |
