全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

一种层次视频摘要生成方法

DOI: 10.11834/jig.20040119

Keywords: 视频摘要,视频总结,视频预览,关键帧,代表帧,视频检索,索引系统

Full-Text   Cite this paper   Add to My Lib

Abstract:

视频摘要是视频内容的一种压缩表示方式。为了能够更好地浏览视频,提出了一种根据浏览或检索的粒度不同来建立两种层次视频摘要(镜头级和场景级)的思想,并给出了一种视频摘要生成方法:首先用一种根据内容变化自动提取镜头内关键帧的方法来实现关键帧的提取;继而用一种改进的时间自适应算法通过镜头的组合来得到场景;最后在场景级用最小生成树方法提取代表帧。由于关键帧和代表帧分别代表了它们所在镜头和场景的主要内容,因此它们的序列就构成了视频总结。一些电影视频片段检验的实验结果表明,这种生成方法能够较好地提供粗细两种粒度的视频内容总结。

References

[1]  [3]Sun X D,Kankanhalli M S.Video summarization using R-sequence[J].Real-time Imaging,2000,6(6):449~459.
[2]  [5]Smith M A,Takeo Kanade.Video skimming and characterization through the combination of image and language understanding [A].In:Proceedings of the 1998 IEEE International Workshop on Content-Based Access of Image and Video Databases[C],Bombay,India,1998:61~70.
[3]  [7]Rui Y,Thomas S.Huang and Sharad Mehrotra.Exploring video structure beyond the shots [A].In:Proceedings of IEEE International Conference on Multimedia Computing and Systems [C],Austin,Texas,USA,1998:237~240.
[4]  [1]Li Y,Zhang T and Tretter D.An overview of video abstraction techniques [R].HP Laboratory Technical Report,HPL-2001-191,2001.
[5]  [2]Hanjalic A,Zhang H J.An integrated scheme for automated video abstraction based on unsupervised cluster-validity analysis [J].IEEE Transactions on Circuits and System for Video Technology,1999,9(8):1280~1289.
[6]  [4]Hanjalic A,Lagendijk R L,Biemond J.A new method for key frame based video content representation [A].In:Proceedings of 1st International Workshop on Image Database and Multimedia Search [C],Amsterdam,Holand,1997:67~74.
[7]  [6]Zhang H J,Kankamhalli A,Smoliar S.Automatic partitioning of full-motion video [J].Association for Computing Machinery Multimedia Systems,1993,1(1):10~28.
[8]  [8]沈清,汤霖.模式识别导论[M].长沙:国防科技大学出版社,1991:107~108.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133