Within and between shot information utilisation in video key frame extraction

Dianting Liu, Mei-Ling Shyu, Chao Chen, Shu Ching Chen

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In consequence of the popularity of family video recorders and the surge of Web 2.0, increasing amounts of videos have made the management and integration of the information in videos an urgent and important issue in video retrieval. Key frames, as a high-quality summary of videos, play an important role in the areas of video browsing, searching, categorisation, and indexing. An effective set of key frames should include major objects and events of the video sequence, and should contain minimum content redundancies. In this paper, an innovative key frame extraction method is proposed to select representative key frames for a video. By analysing the differences between frames and utilising the clustering technique, a set of key frame candidates (KFCs) is first selected at the shot level, and then the information within a video shot and between video shots is used to filter the candidate set to generate the final set of key frames. Experimental results on the TRECVID 2007 video dataset have demonstrated the effectiveness of our proposed key frame extraction method in terms of the percentage of the extracted key frames and the retrieval precision.

Original languageEnglish
Pages (from-to)247-259
Number of pages13
JournalJournal of Information and Knowledge Management
Volume10
Issue number3
DOIs
StatePublished - Dec 1 2011

Fingerprint

information utilization
video
Redundancy
candidacy
redundancy
indexing
popularity

Keywords

  • clustering
  • information integration
  • Key frame extraction

ASJC Scopus subject areas

  • Library and Information Sciences
  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Within and between shot information utilisation in video key frame extraction. / Liu, Dianting; Shyu, Mei-Ling; Chen, Chao; Chen, Shu Ching.

In: Journal of Information and Knowledge Management, Vol. 10, No. 3, 01.12.2011, p. 247-259.

Research output: Contribution to journalArticle

@article{a04700fab7b64837844cd6f2b2555567,
title = "Within and between shot information utilisation in video key frame extraction",
abstract = "In consequence of the popularity of family video recorders and the surge of Web 2.0, increasing amounts of videos have made the management and integration of the information in videos an urgent and important issue in video retrieval. Key frames, as a high-quality summary of videos, play an important role in the areas of video browsing, searching, categorisation, and indexing. An effective set of key frames should include major objects and events of the video sequence, and should contain minimum content redundancies. In this paper, an innovative key frame extraction method is proposed to select representative key frames for a video. By analysing the differences between frames and utilising the clustering technique, a set of key frame candidates (KFCs) is first selected at the shot level, and then the information within a video shot and between video shots is used to filter the candidate set to generate the final set of key frames. Experimental results on the TRECVID 2007 video dataset have demonstrated the effectiveness of our proposed key frame extraction method in terms of the percentage of the extracted key frames and the retrieval precision.",
keywords = "clustering, information integration, Key frame extraction",
author = "Dianting Liu and Mei-Ling Shyu and Chao Chen and Chen, {Shu Ching}",
year = "2011",
month = "12",
day = "1",
doi = "10.1142/S0219649211002961",
language = "English",
volume = "10",
pages = "247--259",
journal = "Journal of Information and Knowledge Management",
issn = "0219-6492",
publisher = "World Scientific Publishing Co.",
number = "3",

}

TY - JOUR

T1 - Within and between shot information utilisation in video key frame extraction

AU - Liu, Dianting

AU - Shyu, Mei-Ling

AU - Chen, Chao

AU - Chen, Shu Ching

PY - 2011/12/1

Y1 - 2011/12/1

N2 - In consequence of the popularity of family video recorders and the surge of Web 2.0, increasing amounts of videos have made the management and integration of the information in videos an urgent and important issue in video retrieval. Key frames, as a high-quality summary of videos, play an important role in the areas of video browsing, searching, categorisation, and indexing. An effective set of key frames should include major objects and events of the video sequence, and should contain minimum content redundancies. In this paper, an innovative key frame extraction method is proposed to select representative key frames for a video. By analysing the differences between frames and utilising the clustering technique, a set of key frame candidates (KFCs) is first selected at the shot level, and then the information within a video shot and between video shots is used to filter the candidate set to generate the final set of key frames. Experimental results on the TRECVID 2007 video dataset have demonstrated the effectiveness of our proposed key frame extraction method in terms of the percentage of the extracted key frames and the retrieval precision.

AB - In consequence of the popularity of family video recorders and the surge of Web 2.0, increasing amounts of videos have made the management and integration of the information in videos an urgent and important issue in video retrieval. Key frames, as a high-quality summary of videos, play an important role in the areas of video browsing, searching, categorisation, and indexing. An effective set of key frames should include major objects and events of the video sequence, and should contain minimum content redundancies. In this paper, an innovative key frame extraction method is proposed to select representative key frames for a video. By analysing the differences between frames and utilising the clustering technique, a set of key frame candidates (KFCs) is first selected at the shot level, and then the information within a video shot and between video shots is used to filter the candidate set to generate the final set of key frames. Experimental results on the TRECVID 2007 video dataset have demonstrated the effectiveness of our proposed key frame extraction method in terms of the percentage of the extracted key frames and the retrieval precision.

KW - clustering

KW - information integration

KW - Key frame extraction

UR - http://www.scopus.com/inward/record.url?scp=84885395720&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885395720&partnerID=8YFLogxK

U2 - 10.1142/S0219649211002961

DO - 10.1142/S0219649211002961

M3 - Article

VL - 10

SP - 247

EP - 259

JO - Journal of Information and Knowledge Management

JF - Journal of Information and Knowledge Management

SN - 0219-6492

IS - 3

ER -