作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2011, Vol. 37 ›› Issue (6): 277-279. doi: 10.3969/j.issn.1000-3428.2011.06.096

• 开发研究与设计技术 • 上一篇    下一篇

基于视频指纹的快速视频拷贝检测方法

唐玉元 a,b,欧阳建权 a,b   

  1. (湘潭大学 a. 智能计算与信息处理教育部重点实验室;b. 信息工程学院,湖南 湘潭 411105)
  • 出版日期:2011-03-20 发布日期:2011-03-29
  • 作者简介:唐玉元(1984-),男,硕士研究生,主研方向:多媒体技术;欧阳建权,教授
  • 基金资助:
    国家科技支撑计划基金资助项目“面向全网运营的数字卡通工程化技术研究与应用”(2007BAH14B05)

Rapid Video Copy Detection Method Based on Video Fingerprint

Rapid Video Copy Detection Method Based on Video Fingerprint   

  1. (a. Key Laboratory of Intelligent Computing & Information Processing, Ministry of Education; b. College of Information Engineering, Xiangtan University, Xiangtan 411105, China)
  • Online:2011-03-20 Published:2011-03-29

摘要: 为满足视频拷贝检测的实时性要求,提出一种基于视频指纹的快速视频拷贝检测方法。基于DC图像序列提取改进的顺序度量特征和改进的运动特征,相结合生成视频指纹,通过视频指纹的相似性匹配对视频进行拷贝检测。实验结果证明,该方法能在保持准确性的同时快速地进行视频拷贝检测。

关键词: 版权保护, 视频指纹, 视频拷贝检测, 顺序度量, 运动特征

Abstract: In order to meet the requirements of real-time video copy detection, a method of rapid video fingerprint scheme is presented. The video fingerprint is generated by combining both the improved ordinal measure feature and the improved motion feature based on the DC image sequences. The query video streams can be identified by matching the candidate video. Experimental results show that the proposed video fingerprint has the advantage of higher discrimination and lower time complexity.

Key words: copyright protection, video fingerprint, video copy detection, Ordinal Measure(OM), motion feature

中图分类号: