Efficient video indexing scheme for content-based retrieval

Hyun Sung Chang, Sanghoon Sull, Sang Uk Lee

Research output: Contribution to journalArticle

199 Citations (Scopus)

Abstract

Extracting a small number of key frames that can abstract the content of video is very important for efficient browsing and retrieval in video databases. In this paper, the key frame extraction problem is considered from a set-theoretic point of view, and systematic algorithms are derived to find a compact set of key frames that can represent a video segment for a given degree of fidelity. The proposed extraction algorithms can be hierarchically applied to obtain a tree-structured key frame hierarchy that is a multilevel abstract of the video. The key frame hierarchy enables an efficient content-based retrieval by using the depth-first search scheme with pruning. Intensive experiments on a variety of video sequences are presented to demonstrate the improved performance of the proposed algorithms over the existing approaches.

Original languageEnglish
Pages (from-to)1269-1279
Number of pages11
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume9
Issue number8
DOIs
Publication statusPublished - 1999 Dec 1

Fingerprint

Content based retrieval
Experiments

Keywords

  • Content-based retrieval
  • Key frame extraction
  • Key frame hierarchy
  • Video database
  • Video indexing

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Efficient video indexing scheme for content-based retrieval. / Chang, Hyun Sung; Sull, Sanghoon; Lee, Sang Uk.

In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 9, No. 8, 01.12.1999, p. 1269-1279.

Research output: Contribution to journalArticle

@article{ab82b78a8ef34310896e149ab24cfa72,
title = "Efficient video indexing scheme for content-based retrieval",
abstract = "Extracting a small number of key frames that can abstract the content of video is very important for efficient browsing and retrieval in video databases. In this paper, the key frame extraction problem is considered from a set-theoretic point of view, and systematic algorithms are derived to find a compact set of key frames that can represent a video segment for a given degree of fidelity. The proposed extraction algorithms can be hierarchically applied to obtain a tree-structured key frame hierarchy that is a multilevel abstract of the video. The key frame hierarchy enables an efficient content-based retrieval by using the depth-first search scheme with pruning. Intensive experiments on a variety of video sequences are presented to demonstrate the improved performance of the proposed algorithms over the existing approaches.",
keywords = "Content-based retrieval, Key frame extraction, Key frame hierarchy, Video database, Video indexing",
author = "Chang, {Hyun Sung} and Sanghoon Sull and Lee, {Sang Uk}",
year = "1999",
month = "12",
day = "1",
doi = "10.1109/76.809161",
language = "English",
volume = "9",
pages = "1269--1279",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "8",

}

TY - JOUR

T1 - Efficient video indexing scheme for content-based retrieval

AU - Chang, Hyun Sung

AU - Sull, Sanghoon

AU - Lee, Sang Uk

PY - 1999/12/1

Y1 - 1999/12/1

N2 - Extracting a small number of key frames that can abstract the content of video is very important for efficient browsing and retrieval in video databases. In this paper, the key frame extraction problem is considered from a set-theoretic point of view, and systematic algorithms are derived to find a compact set of key frames that can represent a video segment for a given degree of fidelity. The proposed extraction algorithms can be hierarchically applied to obtain a tree-structured key frame hierarchy that is a multilevel abstract of the video. The key frame hierarchy enables an efficient content-based retrieval by using the depth-first search scheme with pruning. Intensive experiments on a variety of video sequences are presented to demonstrate the improved performance of the proposed algorithms over the existing approaches.

AB - Extracting a small number of key frames that can abstract the content of video is very important for efficient browsing and retrieval in video databases. In this paper, the key frame extraction problem is considered from a set-theoretic point of view, and systematic algorithms are derived to find a compact set of key frames that can represent a video segment for a given degree of fidelity. The proposed extraction algorithms can be hierarchically applied to obtain a tree-structured key frame hierarchy that is a multilevel abstract of the video. The key frame hierarchy enables an efficient content-based retrieval by using the depth-first search scheme with pruning. Intensive experiments on a variety of video sequences are presented to demonstrate the improved performance of the proposed algorithms over the existing approaches.

KW - Content-based retrieval

KW - Key frame extraction

KW - Key frame hierarchy

KW - Video database

KW - Video indexing

UR - http://www.scopus.com/inward/record.url?scp=0033280146&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033280146&partnerID=8YFLogxK

U2 - 10.1109/76.809161

DO - 10.1109/76.809161

M3 - Article

VL - 9

SP - 1269

EP - 1279

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 8

ER -