欢迎访问中国科学院大学学报,今天是

中国科学院大学学报 ›› 2010, Vol. 27 ›› Issue (3): 376-380.DOI: 10.7523/j.issn.2095-6134.2010.3.011

• 论文 • 上一篇    下一篇

一种快速有效的相似视频检索方法

曹政, 朱明   

  1. 中国科学技术大学自动化系 中国科学院网络传播系统与控制重点实验室 网络传播系统与控制安徽省重点实验室,合肥 230027
  • 收稿日期:2009-10-14 修回日期:2009-12-29 发布日期:2010-05-15
  • 通讯作者: 朱明
  • 基金资助:

    国家863计划项目(2008AA01Z408)和国家自然科学基金(60975045)资助 

A fast and effective similar video search method

CAO Zheng, ZHU Ming   

  1. Department of Automation, University of Science and Technology of China, The Key Lab of Network Communication System & Control, Chinese Academy of Sciences,The Key Lab of Network Communication System & Control, Anhui Province, Hefei 230027, China
  • Received:2009-10-14 Revised:2009-12-29 Published:2010-05-15

摘要:

提出了一种新的相似视频快速检索方法.根据视频的时空分布统计得到图像特征码和视频单元,通过统计视频单元数量度量视频相似性.为了适应可扩展计算的需要,提出了基于聚类索引表的检索方法.通过对大规模数据库的查询测试证明该相似性检索算法快速有效.

关键词: 相似视频检索, 图像特征码, 聚类索引表, 时空分布特征

Abstract:

A novel fast video similarity search approach was proposed. Image characteristic code and video component were computed based on the statistics of video spatial-temporal distribution. Video similarity was measured by computing the number of video components. An efficient search method based on clustering index table was proposed for the requirement of scalable computing. The query test results from large video database show that the proposed video similarity search algorithm is efficient and effective.

Key words: video similarity search, image characteristic code, clustering index table, spatial-temporal distribution

中图分类号: