Skip to main navigation Skip to search Skip to main content

A novel shot boundary detection based on information theory using SVM

  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 4th International Congress on Image and Signal Processing, CISP 2011
Pages512-516
Number of pages5
DOIs
StatePublished - 2011
Event4th International Congress on Image and Signal Processing, CISP 2011 - Shanghai, China
Duration: 15 Oct 201117 Oct 2011

Publication series

NameProceedings - 4th International Congress on Image and Signal Processing, CISP 2011
Volume1

Conference

Conference4th International Congress on Image and Signal Processing, CISP 2011
Country/TerritoryChina
CityShanghai
Period15/10/1117/10/11

Keywords

  • information theory
  • mutual information
  • shot boundary detection
  • SVM

Fingerprint

Dive into the research topics of 'A novel shot boundary detection based on information theory using SVM'. Together they form a unique fingerprint.

Cite this