Abstract

Background subtraction (BGS) is one of the important steps in many automatic video analysis applications. Several researchers have attempted to address the challenges due to illumination variation, shadow, camouflage, dynamic changes in the background and bootstrapping requirement. In this paper, a method to perform BGS using dynamic clustering is proposed. A background model is generated using the K'-means algorithm. The normalized γ corrected distance values and an automatic threshold value is used to perform the background subtraction. The background models are updated online to handle slow illumination changes. The experiment was conducted on CDNet2014 dataset. The experimental results show that the proposed method is fast and performs well for baseline, camera-jitter and dynamic background categories of video.

Original languageEnglish
Pages (from-to)689-696
Number of pages8
JournalInternational Journal of Advanced Computer Science and Applications
Volume10
Issue number12
Publication statusPublished - 01-01-2019

Fingerprint

Lighting
Camouflage
Jitter
Cameras
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

@article{452aec2fef324009981dfad0b709e6b6,
title = "Adaptive cluster based model for fast video background subtraction",
abstract = "Background subtraction (BGS) is one of the important steps in many automatic video analysis applications. Several researchers have attempted to address the challenges due to illumination variation, shadow, camouflage, dynamic changes in the background and bootstrapping requirement. In this paper, a method to perform BGS using dynamic clustering is proposed. A background model is generated using the K'-means algorithm. The normalized γ corrected distance values and an automatic threshold value is used to perform the background subtraction. The background models are updated online to handle slow illumination changes. The experiment was conducted on CDNet2014 dataset. The experimental results show that the proposed method is fast and performs well for baseline, camera-jitter and dynamic background categories of video.",
author = "Muralikrishna, {S. N.} and Balachandra Muniyal and {Dinesh Acharya}, U.",
year = "2019",
month = "1",
day = "1",
language = "English",
volume = "10",
pages = "689--696",
journal = "International Journal of Advanced Computer Science and Applications",
issn = "2158-107X",
publisher = "Science and Information Organization",
number = "12",

}

Adaptive cluster based model for fast video background subtraction. / Muralikrishna, S. N.; Muniyal, Balachandra; Dinesh Acharya, U.

In: International Journal of Advanced Computer Science and Applications, Vol. 10, No. 12, 01.01.2019, p. 689-696.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Adaptive cluster based model for fast video background subtraction

AU - Muralikrishna, S. N.

AU - Muniyal, Balachandra

AU - Dinesh Acharya, U.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Background subtraction (BGS) is one of the important steps in many automatic video analysis applications. Several researchers have attempted to address the challenges due to illumination variation, shadow, camouflage, dynamic changes in the background and bootstrapping requirement. In this paper, a method to perform BGS using dynamic clustering is proposed. A background model is generated using the K'-means algorithm. The normalized γ corrected distance values and an automatic threshold value is used to perform the background subtraction. The background models are updated online to handle slow illumination changes. The experiment was conducted on CDNet2014 dataset. The experimental results show that the proposed method is fast and performs well for baseline, camera-jitter and dynamic background categories of video.

AB - Background subtraction (BGS) is one of the important steps in many automatic video analysis applications. Several researchers have attempted to address the challenges due to illumination variation, shadow, camouflage, dynamic changes in the background and bootstrapping requirement. In this paper, a method to perform BGS using dynamic clustering is proposed. A background model is generated using the K'-means algorithm. The normalized γ corrected distance values and an automatic threshold value is used to perform the background subtraction. The background models are updated online to handle slow illumination changes. The experiment was conducted on CDNet2014 dataset. The experimental results show that the proposed method is fast and performs well for baseline, camera-jitter and dynamic background categories of video.

UR - http://www.scopus.com/inward/record.url?scp=85078420904&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85078420904&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85078420904

VL - 10

SP - 689

EP - 696

JO - International Journal of Advanced Computer Science and Applications

JF - International Journal of Advanced Computer Science and Applications

SN - 2158-107X

IS - 12

ER -