跳到主要导航 跳到搜索 跳到主要内容

A novel shot boundary detection based on information theory using SVM

  • Beihang University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Shot boundary detection is the preliminary step for efficient video indexing and retrieval. To overcome the shortage of traditional threshold based method in shot detection, we proposed a novel cut detection method based on information theory using SVM. We first compute the dissimilarity using information theory and construct a discriminative feature vector based on mutual information. Then a support vector machine is trained to classify the frames as cut or none-cut frames. Experiment results demonstrate our proposed method is effective and outperforms state-of-art methods.

源语言英语
主期刊名Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011
512-516
页数5
DOI
出版状态已出版 - 2011
活动4th International Congress on Image and Signal Processing, CISP 2011 - Shanghai, 中国
期限: 15 10月 201117 10月 2011

出版系列

姓名Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011
1

会议

会议4th International Congress on Image and Signal Processing, CISP 2011
国家/地区中国
Shanghai
时期15/10/1117/10/11

指纹

探究 'A novel shot boundary detection based on information theory using SVM' 的科研主题。它们共同构成独一无二的指纹。

引用此