首页 | 本学科首页   官方微博 | 高级检索  
     

视频相似度的衡量
引用本文:吴翌,庄越挺,潘云鹤.视频相似度的衡量[J].计算机辅助设计与图形学学报,2001,13(3):284-288.
作者姓名:吴翌  庄越挺  潘云鹤
作者单位:浙江大学人工智能研究所
基金项目:国家自然科学基金! ( 6 980 30 0 9)
摘    要:基于内容的视频检索系统中,最常用的检索方式是例子视频查询,即用户提交一部视频,系统返回相似的一系列视频,但是,怎样定义的两部视频是相似的,仍然是一个困难的问题。文中介绍了一种新的方法以解决这一难点。首先,提出了镜头质心特征向量的概念,减少了关键帧特征的存储量。其次,利用人类视觉判断中所潜在的因子,提出了视频在镜头间相似度的衡量,以及总体上相似度的衡量的方法,为不同粒度上的衡量提供了很大的灵活性,在现实意义上也是合理的。检索实验的结果证明了算法的有效性。

关 键 词:视频检索系统  视频相似度  图像处理  多媒体
修稿时间:1999年12月13

Video Similarity Measurement
WU Yi,ZHUANG Yue,Ting,PAN Yun,He.Video Similarity Measurement[J].Journal of Computer-Aided Design & Computer Graphics,2001,13(3):284-288.
Authors:WU Yi  ZHUANG Yue  Ting  PAN Yun  He
Abstract:The main retrieval method of content based video retrieval system is query by example. If user submits a video as example, system returns a set of similar videos. But how to define whether two videos are similar is still a great problem. This paper puts forward a video similarity model to solve the difficulty. First, it advances the centroid feature vector of shot in order to reduce the storage of video database. Second, considering the latent factors existing in human's vision perception, it introduces a new comparison algorithm based on multi level of video structure, such as from shot's view and from the overall view. This different granularity of measurement provides great flexibility, which is reasonable in real world. The final retrieval result demonstrates the validity of algorithm.
Keywords:content  based video retrieval system  query by example  centroid feature vector of shot
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号