Gradual shot boundary detection using localized edge blocks

Hun Woo Yoo, Han Jin Ryoo, Dong Sik Jang

Research output: Contribution to journalArticle

57 Citations (Scopus)

Abstract

A new algorithm for gradual shot boundary detection is proposed in this paper. The proposed algorithm is based on the fact that most of gradual curves can be characterized by variance distribution of edge information in the frame sequences. Average edge frame sequence is obtained by performing Sobel edge detection. Features are extracted by comparing variance with those of local blocks in the average edge frames. Those features are further processed by the opening operation to obtain smoothing variance curves. The lowest variance in the local frame sequence is chosen as a gradual detection point. Experimental results show that the proposed method provides 87.0% precision and 86.3% recall rates for six selected videos.

Original languageEnglish
Pages (from-to)283-300
Number of pages18
JournalMultimedia Tools and Applications
Volume28
Issue number3
DOIs
Publication statusPublished - 2006 Mar 1

Fingerprint

Boundary Detection
Edge detection
Curve
Edge Detection
Smoothing
Lowest
Experimental Results

Keywords

  • AGI (Average Gradient Image)
  • Gradual shot detection
  • Local blocks
  • Opening
  • Parabolic curve
  • Variance

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Information Systems
  • Computer Graphics and Computer-Aided Design
  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

Gradual shot boundary detection using localized edge blocks. / Yoo, Hun Woo; Ryoo, Han Jin; Jang, Dong Sik.

In: Multimedia Tools and Applications, Vol. 28, No. 3, 01.03.2006, p. 283-300.

Research output: Contribution to journalArticle

Yoo, Hun Woo ; Ryoo, Han Jin ; Jang, Dong Sik. / Gradual shot boundary detection using localized edge blocks. In: Multimedia Tools and Applications. 2006 ; Vol. 28, No. 3. pp. 283-300.
@article{d1e0a31ce79841c394e39c52dbf9b9bb,
title = "Gradual shot boundary detection using localized edge blocks",
abstract = "A new algorithm for gradual shot boundary detection is proposed in this paper. The proposed algorithm is based on the fact that most of gradual curves can be characterized by variance distribution of edge information in the frame sequences. Average edge frame sequence is obtained by performing Sobel edge detection. Features are extracted by comparing variance with those of local blocks in the average edge frames. Those features are further processed by the opening operation to obtain smoothing variance curves. The lowest variance in the local frame sequence is chosen as a gradual detection point. Experimental results show that the proposed method provides 87.0{\%} precision and 86.3{\%} recall rates for six selected videos.",
keywords = "AGI (Average Gradient Image), Gradual shot detection, Local blocks, Opening, Parabolic curve, Variance",
author = "Yoo, {Hun Woo} and Ryoo, {Han Jin} and Jang, {Dong Sik}",
year = "2006",
month = "3",
day = "1",
doi = "10.1007/s11042-006-7715-8",
language = "English",
volume = "28",
pages = "283--300",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - Gradual shot boundary detection using localized edge blocks

AU - Yoo, Hun Woo

AU - Ryoo, Han Jin

AU - Jang, Dong Sik

PY - 2006/3/1

Y1 - 2006/3/1

N2 - A new algorithm for gradual shot boundary detection is proposed in this paper. The proposed algorithm is based on the fact that most of gradual curves can be characterized by variance distribution of edge information in the frame sequences. Average edge frame sequence is obtained by performing Sobel edge detection. Features are extracted by comparing variance with those of local blocks in the average edge frames. Those features are further processed by the opening operation to obtain smoothing variance curves. The lowest variance in the local frame sequence is chosen as a gradual detection point. Experimental results show that the proposed method provides 87.0% precision and 86.3% recall rates for six selected videos.

AB - A new algorithm for gradual shot boundary detection is proposed in this paper. The proposed algorithm is based on the fact that most of gradual curves can be characterized by variance distribution of edge information in the frame sequences. Average edge frame sequence is obtained by performing Sobel edge detection. Features are extracted by comparing variance with those of local blocks in the average edge frames. Those features are further processed by the opening operation to obtain smoothing variance curves. The lowest variance in the local frame sequence is chosen as a gradual detection point. Experimental results show that the proposed method provides 87.0% precision and 86.3% recall rates for six selected videos.

KW - AGI (Average Gradient Image)

KW - Gradual shot detection

KW - Local blocks

KW - Opening

KW - Parabolic curve

KW - Variance

UR - http://www.scopus.com/inward/record.url?scp=33744537220&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33744537220&partnerID=8YFLogxK

U2 - 10.1007/s11042-006-7715-8

DO - 10.1007/s11042-006-7715-8

M3 - Article

AN - SCOPUS:33744537220

VL - 28

SP - 283

EP - 300

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 3

ER -