Mixture of gaussians-based background subtraction for bayer-pattern image sequences

Jae Kyu Suhr, Ho Gi Jung, Gen Li, Jaihie Kim

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

This letter proposes a background subtraction method for Bayer-pattern image sequences. The proposed method models the background in a Bayer-pattern domain using a mixture of Gaussians (MoG) and classifies the foreground in an interpolated red, green, and blue (RGB) domain. This method can achieve almost the same accuracy as MoG using RGB color images while maintaining computational resources (time and memory) similar to MoG using grayscale images. Experimental results show that the proposed method is a good solution to obtain high accuracy and low resource requirements simultaneously. This improvement is important for a low-level task like background subtraction since its accuracy affects the performance of high-level tasks, and is preferable for implementation in real-time embedded systems such as smart cameras.

Original languageEnglish
Article number5604673
Pages (from-to)365-370
Number of pages6
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume21
Issue number3
DOIs
Publication statusPublished - 2011 Mar 1

Fingerprint

Real time systems
Embedded systems
Cameras
Color
Data storage equipment

All Science Journal Classification (ASJC) codes

  • Media Technology
  • Electrical and Electronic Engineering

Cite this

@article{3ca5aa0c0c064e67a8e95f5e5ccc4f5e,
title = "Mixture of gaussians-based background subtraction for bayer-pattern image sequences",
abstract = "This letter proposes a background subtraction method for Bayer-pattern image sequences. The proposed method models the background in a Bayer-pattern domain using a mixture of Gaussians (MoG) and classifies the foreground in an interpolated red, green, and blue (RGB) domain. This method can achieve almost the same accuracy as MoG using RGB color images while maintaining computational resources (time and memory) similar to MoG using grayscale images. Experimental results show that the proposed method is a good solution to obtain high accuracy and low resource requirements simultaneously. This improvement is important for a low-level task like background subtraction since its accuracy affects the performance of high-level tasks, and is preferable for implementation in real-time embedded systems such as smart cameras.",
author = "Suhr, {Jae Kyu} and Jung, {Ho Gi} and Gen Li and Jaihie Kim",
year = "2011",
month = "3",
day = "1",
doi = "10.1109/TCSVT.2010.2087810",
language = "English",
volume = "21",
pages = "365--370",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

Mixture of gaussians-based background subtraction for bayer-pattern image sequences. / Suhr, Jae Kyu; Jung, Ho Gi; Li, Gen; Kim, Jaihie.

In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 21, No. 3, 5604673, 01.03.2011, p. 365-370.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Mixture of gaussians-based background subtraction for bayer-pattern image sequences

AU - Suhr, Jae Kyu

AU - Jung, Ho Gi

AU - Li, Gen

AU - Kim, Jaihie

PY - 2011/3/1

Y1 - 2011/3/1

N2 - This letter proposes a background subtraction method for Bayer-pattern image sequences. The proposed method models the background in a Bayer-pattern domain using a mixture of Gaussians (MoG) and classifies the foreground in an interpolated red, green, and blue (RGB) domain. This method can achieve almost the same accuracy as MoG using RGB color images while maintaining computational resources (time and memory) similar to MoG using grayscale images. Experimental results show that the proposed method is a good solution to obtain high accuracy and low resource requirements simultaneously. This improvement is important for a low-level task like background subtraction since its accuracy affects the performance of high-level tasks, and is preferable for implementation in real-time embedded systems such as smart cameras.

AB - This letter proposes a background subtraction method for Bayer-pattern image sequences. The proposed method models the background in a Bayer-pattern domain using a mixture of Gaussians (MoG) and classifies the foreground in an interpolated red, green, and blue (RGB) domain. This method can achieve almost the same accuracy as MoG using RGB color images while maintaining computational resources (time and memory) similar to MoG using grayscale images. Experimental results show that the proposed method is a good solution to obtain high accuracy and low resource requirements simultaneously. This improvement is important for a low-level task like background subtraction since its accuracy affects the performance of high-level tasks, and is preferable for implementation in real-time embedded systems such as smart cameras.

UR - http://www.scopus.com/inward/record.url?scp=79953050293&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79953050293&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2010.2087810

DO - 10.1109/TCSVT.2010.2087810

M3 - Article

AN - SCOPUS:79953050293

VL - 21

SP - 365

EP - 370

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 3

M1 - 5604673

ER -