Adaptive selection of model histograms in block-based background subtraction

H. Kim, B. Ku, D. K. Han, S. Kang, Hanseok Ko

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

An adaptive block-based background modelling technique is proposed whereby the optimal number of model histograms is selected. The dynamic nature of a background tends to vary the pool of model histograms when capturing all possible scenes. Proposed is a novel method that recursively estimates the model weights, thereby continuously adjusting the number of histograms to robustly capture only the essence of intended objects. The proposed algorithm shows improved and reliable segmentation performance in various environments, including dynamic backgrounds with moving objects and repetitive variation of the pixel value.

Original languageEnglish
Pages (from-to)434-435
Number of pages2
JournalElectronics Letters
Volume48
Issue number8
DOIs
Publication statusPublished - 2012 Apr 12

Fingerprint

Pixels

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Adaptive selection of model histograms in block-based background subtraction. / Kim, H.; Ku, B.; Han, D. K.; Kang, S.; Ko, Hanseok.

In: Electronics Letters, Vol. 48, No. 8, 12.04.2012, p. 434-435.

Research output: Contribution to journalArticle

Kim, H. ; Ku, B. ; Han, D. K. ; Kang, S. ; Ko, Hanseok. / Adaptive selection of model histograms in block-based background subtraction. In: Electronics Letters. 2012 ; Vol. 48, No. 8. pp. 434-435.
@article{49d5557e7ef44537a6f5cc14287d2bfe,
title = "Adaptive selection of model histograms in block-based background subtraction",
abstract = "An adaptive block-based background modelling technique is proposed whereby the optimal number of model histograms is selected. The dynamic nature of a background tends to vary the pool of model histograms when capturing all possible scenes. Proposed is a novel method that recursively estimates the model weights, thereby continuously adjusting the number of histograms to robustly capture only the essence of intended objects. The proposed algorithm shows improved and reliable segmentation performance in various environments, including dynamic backgrounds with moving objects and repetitive variation of the pixel value.",
author = "H. Kim and B. Ku and Han, {D. K.} and S. Kang and Hanseok Ko",
year = "2012",
month = "4",
day = "12",
doi = "10.1049/el.2011.4068",
language = "English",
volume = "48",
pages = "434--435",
journal = "Electronics Letters",
issn = "0013-5194",
publisher = "Institution of Engineering and Technology",
number = "8",

}

TY - JOUR

T1 - Adaptive selection of model histograms in block-based background subtraction

AU - Kim, H.

AU - Ku, B.

AU - Han, D. K.

AU - Kang, S.

AU - Ko, Hanseok

PY - 2012/4/12

Y1 - 2012/4/12

N2 - An adaptive block-based background modelling technique is proposed whereby the optimal number of model histograms is selected. The dynamic nature of a background tends to vary the pool of model histograms when capturing all possible scenes. Proposed is a novel method that recursively estimates the model weights, thereby continuously adjusting the number of histograms to robustly capture only the essence of intended objects. The proposed algorithm shows improved and reliable segmentation performance in various environments, including dynamic backgrounds with moving objects and repetitive variation of the pixel value.

AB - An adaptive block-based background modelling technique is proposed whereby the optimal number of model histograms is selected. The dynamic nature of a background tends to vary the pool of model histograms when capturing all possible scenes. Proposed is a novel method that recursively estimates the model weights, thereby continuously adjusting the number of histograms to robustly capture only the essence of intended objects. The proposed algorithm shows improved and reliable segmentation performance in various environments, including dynamic backgrounds with moving objects and repetitive variation of the pixel value.

UR - http://www.scopus.com/inward/record.url?scp=84861587014&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861587014&partnerID=8YFLogxK

U2 - 10.1049/el.2011.4068

DO - 10.1049/el.2011.4068

M3 - Article

AN - SCOPUS:84861587014

VL - 48

SP - 434

EP - 435

JO - Electronics Letters

JF - Electronics Letters

SN - 0013-5194

IS - 8

ER -