北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2006, Vol. 29 ›› Issue (4): 94-98.doi: 10.13190/jbupt.200604.94.caojr

• 研究报告 • 上一篇    下一篇

基于支持向量机的语义视频摘要

曹建荣 ,蔡安妮   

  1. 1. 北京邮电大学 电信工程学院,北京 100876;2. 山东建筑大学 信息与电气工程学院,济南 250101
  • 收稿日期:2005-07-05 修回日期:1900-01-01 出版日期:2006-08-30 发布日期:2006-08-30
  • 通讯作者: 曹建荣

Semantic Video Summarization based on Support Vector Machine

C AO Jian-rong, CAI An-ni   

  1. 1. School of Telecommunication Engineering , Beijing University of Posts and Telecommunications, Beijing 100876,China;
    2. School of Information and Electrical Engineering , Shandong Jianzhu University , Jinan 250101, China
  • Received:2005-07-05 Revised:1900-01-01 Online:2006-08-30 Published:2006-08-30
  • Contact: C AO Jian-rong

摘要:

针对如何在语义层次上形成视频摘要问题,提出了一个基于支持向量机的风光记录片语义视频摘要算法。利用支持向量机对镜头关键帧进行语义分类,对每类镜头关键帧根据引入的镜头“重要性”函数提取构建视频摘要的帧。改变重要性函数阈值的大小,可以很方便的得到不同粒度的视频摘要。实验结果表明该算法形成的视频摘要较好地表达了视频的内容。

关键词: 支持向量机, 语义, 视频摘要

Abstract:

Constructing the video summarization in semantic level is very important. An algorithm of video summarization based on support vector machine (SVM) in semantic level for the natural scenery documentary is presented. The shot key frames are classified by SVM and the frames constructing the video summarization are selected from the shot key frames of every class by the importance function introduced. The scalable video summarization to fine level of detail can be achieved by changing the threshold of important function. Experiment results indicate that the proposed algorithm performs satisfactorily.

Key words: support vector machine, semantic;video summarization

中图分类号: