欢迎访问中国科学院大学学报,今天是
论文

一种快速有效的相似视频检索方法

  • 曹政 ,
  • 朱明
展开
  • 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

  网络出版日期: 2010-05-15

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
Expand
  • 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 date: 2009-10-14

  Revised date: 2009-12-29

  Online 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.

本文引用格式

曹政 , 朱明 . 一种快速有效的相似视频检索方法[J]. 中国科学院大学学报, 2010 , 27(3) : 376 -380 . DOI: 10.7523/j.issn.2095-6134.2010.3.011

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.

参考文献


[1] Gao Y, Dai Q H. Clip based video summarization and Ranking //Pro of the intl conf on Content-based Image and Video Retrieval, 2008:135-140.

[2] Dong W, Wang Z, Charikar M, et al. Efficiently matching sets of features with random histograms //Pro of the 16th ACM intl conf on Multimedia 2008: 179-188.

[3] Yang X, Xue P, Tian Q. Automatically discovering unknown short video repeats //Pro of IEEE Intl Conf on Acoustics, Speech and Signal Processing, 2007, 1: I-1265-1268.

[4] Shen H T, Shao J, Huang Z, et al. Effective and efficient query processing for video subsequence identification
[J].IEEE Transactions on Knowledge and Data Engineering, 2009, 21(3):321-334.

[5] Deng Z P, Jia K B. A video similarity matching algorithm supporting for different time scales //Pro of Eighth Intl Conf on Intelligent Systems Design and Applications, 2008,3:570-574.

[6] Peng Y X, Ngo C W. Clip-based similarity measure for query-dependent clip retrieval and video summarization
[J]. IEEE Trans on Circuits and Systems for Video Technology, 2006, 16:612-627.

[7] Bayardo R J, Ma Y M, Srikant R. Scaling up all pairs similarity search //Pro of the 16th intl conf on World Wide Web, 2007:131-140.

[8] Lejsek H, Heiear F, Asmundsson, et al. NV-Tree: An efficient disk-based index for approximate search in very large high-dimensional collections
[J], IEEE Trans Pattern Analysis and Machine Intelligence, 2009, 31:869-883.

[9] Chiu C Y, Wang J H, Chang H C. Efficient histogram-based indexing for video copy detection //Pro of the Ninth IEEE Intl Symposium on Multimedia Workshops, 2007:265-270.

[10] Gao L, Li Z, Katsaggelos A. An efficient video indexing and retrieval algorithm using the luminance field trajectory modeling
[J]. IEEE Trans. Circuits and Systems on Video Technology, 2009, 19:1566-1571.

[11] Lv Q, Josephson W, Wang Z, et al. Multi-probe LSH efficient indexing for high-dimensional similarity search //Pro of the 33rd intl conf on Very Large Data Bases, 2007:950-961.

[12] Hoad T C, Zobel J. Detection of video sequences using compact signatures
[J]. ACM Trans on Information Systems, 2006, 24:1-50.

[13] Zenzo S D. A note on the gradient of a multi-image
[J]. Computer Vision, Graphics and Image Processing, 1986, 33: 116-125.

[14] Cheung S, Zakhor A. Fast similarity search and clustering of video sequences on the world-wide-web
[J]. IEEE Trans on Multimedia, 2005, 7:524-537.

文章导航

/