Improved background modeling through color de-correlation

Jong Geun Park, Chulhee Lee

Research output: Contribution to journalConference article

1 Citation (Scopus)

Abstract

Background modelling and foreground detection, which significantly affect the performance of intelligent visual surveillance systems, are challenging works due to dynamic background, illumination changes, image artefacts, etc. This paper describes an improved algorithm for background modelling. A pixel-wise non-parametric statistical model of the HSV colour components and gradients is used for background modelling. Since the non-parametric statistical model using the kernel density estimation is computationally complex, the probability density functions are estimated as a product of several one-dimensional histograms. Then, foreground regions are detected by using the Bayesian decision rule. The experimental results showed that the proposed algorithm produced more accurate and stable results than existing background modeling methods and the colour decorrelation procedure produced improvements.

Original languageEnglish
Pages (from-to)36-40
Number of pages5
JournalEuropean Signal Processing Conference
Publication statusPublished - 2011 Dec 1

Fingerprint

Color
Probability density function
Lighting
Pixels
Statistical Models

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

@article{bf43049263f54ea0b72030b44c9e4187,
title = "Improved background modeling through color de-correlation",
abstract = "Background modelling and foreground detection, which significantly affect the performance of intelligent visual surveillance systems, are challenging works due to dynamic background, illumination changes, image artefacts, etc. This paper describes an improved algorithm for background modelling. A pixel-wise non-parametric statistical model of the HSV colour components and gradients is used for background modelling. Since the non-parametric statistical model using the kernel density estimation is computationally complex, the probability density functions are estimated as a product of several one-dimensional histograms. Then, foreground regions are detected by using the Bayesian decision rule. The experimental results showed that the proposed algorithm produced more accurate and stable results than existing background modeling methods and the colour decorrelation procedure produced improvements.",
author = "Park, {Jong Geun} and Chulhee Lee",
year = "2011",
month = "12",
day = "1",
language = "English",
pages = "36--40",
journal = "European Signal Processing Conference",
issn = "2219-5491",

}

Improved background modeling through color de-correlation. / Park, Jong Geun; Lee, Chulhee.

In: European Signal Processing Conference, 01.12.2011, p. 36-40.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Improved background modeling through color de-correlation

AU - Park, Jong Geun

AU - Lee, Chulhee

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Background modelling and foreground detection, which significantly affect the performance of intelligent visual surveillance systems, are challenging works due to dynamic background, illumination changes, image artefacts, etc. This paper describes an improved algorithm for background modelling. A pixel-wise non-parametric statistical model of the HSV colour components and gradients is used for background modelling. Since the non-parametric statistical model using the kernel density estimation is computationally complex, the probability density functions are estimated as a product of several one-dimensional histograms. Then, foreground regions are detected by using the Bayesian decision rule. The experimental results showed that the proposed algorithm produced more accurate and stable results than existing background modeling methods and the colour decorrelation procedure produced improvements.

AB - Background modelling and foreground detection, which significantly affect the performance of intelligent visual surveillance systems, are challenging works due to dynamic background, illumination changes, image artefacts, etc. This paper describes an improved algorithm for background modelling. A pixel-wise non-parametric statistical model of the HSV colour components and gradients is used for background modelling. Since the non-parametric statistical model using the kernel density estimation is computationally complex, the probability density functions are estimated as a product of several one-dimensional histograms. Then, foreground regions are detected by using the Bayesian decision rule. The experimental results showed that the proposed algorithm produced more accurate and stable results than existing background modeling methods and the colour decorrelation procedure produced improvements.

UR - http://www.scopus.com/inward/record.url?scp=84863748199&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863748199&partnerID=8YFLogxK

M3 - Conference article

SP - 36

EP - 40

JO - European Signal Processing Conference

JF - European Signal Processing Conference

SN - 2219-5491

ER -