计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (24): 186-190.

• 图形、图像、模式识别 • 上一篇    下一篇

一种鲁棒的视频指纹提取和匹配方法

段德友1,2,欧阳建权1,2   

  1. 1.湘潭大学 智能计算与信息处理教育部重点实验室,湖南 湘潭 411105
    2.湘潭大学 信息工程学院,湖南 湘潭 411105
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-08-21 发布日期:2011-08-21

Robust method for video fingerprint extracting and matching

DUAN Deyou1,2,OUYANG Jianquan1,2   

  1. 1.Key Lab of MoE of Intelligent Computing & Information Processing,Xiangtan University,Xiangtan,Hunan 411105,China
    2.College of Information Engineering,Xiangtan University,Xiangtan,Hunan 411105,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-08-21 Published:2011-08-21

摘要: 在视频广告监测的解决方案中,视频指纹日益受到重视。针对目前视频指纹鲁棒性不强、匹配方法效率不高或适用度不广的缺点,提出一种快速鲁棒的视频指纹算法:在视频指纹提取阶段,结合改进的Harris检测和改进的帧间差异法分别提取图像特征、运动特征以产生鲁棒的视频指纹;在指纹匹配阶段,设计了一种分层方案,该方案结合了典型匹配算法适用度广、位置敏感哈希(LSH)高效性的优点。实验表明,在亮度变换和尺寸变化以及常见的噪声攻击中,提取的视频指纹有较强的鲁棒性,提取、匹配的效率高。该方法满足视频监测准确性及实时性的要求。

关键词: 视频指纹, Harris检测, 运动特征, 位置敏感哈希, 视频监测

Abstract: Since existing some defects of the current video fingerprint approaches including weak robustness,ineffective matching scheme and limited adaptability,it presents a robust method for video fingerprint extracting and matching.The video fingerprint vector,which is combined the improved Harris descriptor with the improved inter-frame difference signature,is introduced.The hybrid video fingerprint matching scheme is designed for real-time working.The experimental results verify that comparing with the current method,the proposed video fingerprint is more robust to resist various geometric and signal based modification.

Key words: video fingerprint, Harris detection, motion feature, Location Sensitive Hash(LSH), video monitoring