Morphological approach to scene change detection and digital video storage and retrieval

Woon Kyung Kim, S. Moon Ho Song, Hyeokman Kim, Cheeyang Song, Byung Woong Kwon, Sun Geun Kim

Research output: Chapter in Book/Report/Conference proceedingChapter

2 Citations (Scopus)

Abstract

With the abstraction of digital video as the corresponding binary video- a process which upon numerous subjective experimentation seems to preserve (most of the) intelligibility of video content- we can pursue a precise and analytic approach to (digital video storage and retrieval) algorithm design that are based upon geometrical (morphological) intuition. The foremost and tangible general benefit of such abstraction, however, is the immediate reductions of both data and computational complexities involved in implementing various algorithms and databases. The general paradigm presented may be utilized to address all issues pertaining to video library construction including visualization, optimum feedback query generation, object recognition, e.t.c., but the primary focus of attention in this paper are the ones pertaining to detection of fast (including presence of flashlights) and gradual scene changes (such as dissolves, fades, and various special effects such as wipes). Upon simulation we observed that we can achieve performances comparable to those of others with drastic reductions in both storage and computational complexities. Furthermore, since the conversion from grayscale to binary videos can be performed directly (with minimal additional computation) in the compressed domain by thresholding on the DCT DC coefficients themselves (or by using the contour information attached to MPEG4 formats), the algorithms presented herein are ideally suited for performing fast (on-the-fly) determinations of scene change, object recognition and/or tracking, and other more intelligent tasks traditionally requiring heavy demand on computational and/or storage complexities. The fast determinations may then be used on their own merits or can be used in conjunction or complementation with other higher-layer information in the future.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
PublisherSociety of Photo-Optical Instrumentation Engineers
Pages733-743
Number of pages11
Volume3656
Publication statusPublished - 1999
EventProceedings of the 1999 7th Conference of the Storage and Retrieval for Image and Video Databases VII - San Jose, Ca, USA
Duration: 1999 Jan 261999 Jan 29

Other

OtherProceedings of the 1999 7th Conference of the Storage and Retrieval for Image and Video Databases VII
CitySan Jose, Ca, USA
Period99/1/2699/1/29

Fingerprint

Flashlights
change detection
retrieval
Object recognition
Computational complexity
Special effects
conjunction
intelligibility
discrete cosine transform
experimentation
format
Visualization
direct current
Feedback
coefficients
simulation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Kim, W. K., Song, S. M. H., Kim, H., Song, C., Kwon, B. W., & Kim, S. G. (1999). Morphological approach to scene change detection and digital video storage and retrieval. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 3656, pp. 733-743). Society of Photo-Optical Instrumentation Engineers.

Morphological approach to scene change detection and digital video storage and retrieval. / Kim, Woon Kyung; Song, S. Moon Ho; Kim, Hyeokman; Song, Cheeyang; Kwon, Byung Woong; Kim, Sun Geun.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3656 Society of Photo-Optical Instrumentation Engineers, 1999. p. 733-743.

Research output: Chapter in Book/Report/Conference proceedingChapter

Kim, WK, Song, SMH, Kim, H, Song, C, Kwon, BW & Kim, SG 1999, Morphological approach to scene change detection and digital video storage and retrieval. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 3656, Society of Photo-Optical Instrumentation Engineers, pp. 733-743, Proceedings of the 1999 7th Conference of the Storage and Retrieval for Image and Video Databases VII, San Jose, Ca, USA, 99/1/26.
Kim WK, Song SMH, Kim H, Song C, Kwon BW, Kim SG. Morphological approach to scene change detection and digital video storage and retrieval. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3656. Society of Photo-Optical Instrumentation Engineers. 1999. p. 733-743
Kim, Woon Kyung ; Song, S. Moon Ho ; Kim, Hyeokman ; Song, Cheeyang ; Kwon, Byung Woong ; Kim, Sun Geun. / Morphological approach to scene change detection and digital video storage and retrieval. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3656 Society of Photo-Optical Instrumentation Engineers, 1999. pp. 733-743
@inbook{5a9d4a240baf4377913d287f8ef41772,
title = "Morphological approach to scene change detection and digital video storage and retrieval",
abstract = "With the abstraction of digital video as the corresponding binary video- a process which upon numerous subjective experimentation seems to preserve (most of the) intelligibility of video content- we can pursue a precise and analytic approach to (digital video storage and retrieval) algorithm design that are based upon geometrical (morphological) intuition. The foremost and tangible general benefit of such abstraction, however, is the immediate reductions of both data and computational complexities involved in implementing various algorithms and databases. The general paradigm presented may be utilized to address all issues pertaining to video library construction including visualization, optimum feedback query generation, object recognition, e.t.c., but the primary focus of attention in this paper are the ones pertaining to detection of fast (including presence of flashlights) and gradual scene changes (such as dissolves, fades, and various special effects such as wipes). Upon simulation we observed that we can achieve performances comparable to those of others with drastic reductions in both storage and computational complexities. Furthermore, since the conversion from grayscale to binary videos can be performed directly (with minimal additional computation) in the compressed domain by thresholding on the DCT DC coefficients themselves (or by using the contour information attached to MPEG4 formats), the algorithms presented herein are ideally suited for performing fast (on-the-fly) determinations of scene change, object recognition and/or tracking, and other more intelligent tasks traditionally requiring heavy demand on computational and/or storage complexities. The fast determinations may then be used on their own merits or can be used in conjunction or complementation with other higher-layer information in the future.",
author = "Kim, {Woon Kyung} and Song, {S. Moon Ho} and Hyeokman Kim and Cheeyang Song and Kwon, {Byung Woong} and Kim, {Sun Geun}",
year = "1999",
language = "English",
volume = "3656",
pages = "733--743",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "Society of Photo-Optical Instrumentation Engineers",

}

TY - CHAP

T1 - Morphological approach to scene change detection and digital video storage and retrieval

AU - Kim, Woon Kyung

AU - Song, S. Moon Ho

AU - Kim, Hyeokman

AU - Song, Cheeyang

AU - Kwon, Byung Woong

AU - Kim, Sun Geun

PY - 1999

Y1 - 1999

N2 - With the abstraction of digital video as the corresponding binary video- a process which upon numerous subjective experimentation seems to preserve (most of the) intelligibility of video content- we can pursue a precise and analytic approach to (digital video storage and retrieval) algorithm design that are based upon geometrical (morphological) intuition. The foremost and tangible general benefit of such abstraction, however, is the immediate reductions of both data and computational complexities involved in implementing various algorithms and databases. The general paradigm presented may be utilized to address all issues pertaining to video library construction including visualization, optimum feedback query generation, object recognition, e.t.c., but the primary focus of attention in this paper are the ones pertaining to detection of fast (including presence of flashlights) and gradual scene changes (such as dissolves, fades, and various special effects such as wipes). Upon simulation we observed that we can achieve performances comparable to those of others with drastic reductions in both storage and computational complexities. Furthermore, since the conversion from grayscale to binary videos can be performed directly (with minimal additional computation) in the compressed domain by thresholding on the DCT DC coefficients themselves (or by using the contour information attached to MPEG4 formats), the algorithms presented herein are ideally suited for performing fast (on-the-fly) determinations of scene change, object recognition and/or tracking, and other more intelligent tasks traditionally requiring heavy demand on computational and/or storage complexities. The fast determinations may then be used on their own merits or can be used in conjunction or complementation with other higher-layer information in the future.

AB - With the abstraction of digital video as the corresponding binary video- a process which upon numerous subjective experimentation seems to preserve (most of the) intelligibility of video content- we can pursue a precise and analytic approach to (digital video storage and retrieval) algorithm design that are based upon geometrical (morphological) intuition. The foremost and tangible general benefit of such abstraction, however, is the immediate reductions of both data and computational complexities involved in implementing various algorithms and databases. The general paradigm presented may be utilized to address all issues pertaining to video library construction including visualization, optimum feedback query generation, object recognition, e.t.c., but the primary focus of attention in this paper are the ones pertaining to detection of fast (including presence of flashlights) and gradual scene changes (such as dissolves, fades, and various special effects such as wipes). Upon simulation we observed that we can achieve performances comparable to those of others with drastic reductions in both storage and computational complexities. Furthermore, since the conversion from grayscale to binary videos can be performed directly (with minimal additional computation) in the compressed domain by thresholding on the DCT DC coefficients themselves (or by using the contour information attached to MPEG4 formats), the algorithms presented herein are ideally suited for performing fast (on-the-fly) determinations of scene change, object recognition and/or tracking, and other more intelligent tasks traditionally requiring heavy demand on computational and/or storage complexities. The fast determinations may then be used on their own merits or can be used in conjunction or complementation with other higher-layer information in the future.

UR - http://www.scopus.com/inward/record.url?scp=0032686995&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032686995&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0032686995

VL - 3656

SP - 733

EP - 743

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - Society of Photo-Optical Instrumentation Engineers

ER -