Real-time robust background subtraction under rapidly changing illumination conditions.

L.P.J. Vosters, Caifeng Shan, T. Gritti

Research output: Contribution to journalArticleAcademicpeer-review

22 Citations (Scopus)
4 Downloads (Pure)

Abstract

Fast robust background subtraction under sudden lighting changes is a challenging problem in many applications. In this paper, we propose a real-time approach, which combines the Eigenbackground and Statistical Illumination method to address this issue. The first algorithm is used to reconstruct the background frame, while the latter improves the foreground segmentation. In addition, we introduce an online spatial likelihood model by detecting reliable background pixels. Extensive quantitative experiments illustrate our approach consistently achieves significantly higher precision at high recall rates, compared to several state-of-the-art illumination invariant background subtraction methods.
Original languageEnglish
Pages (from-to)1004-1015
Number of pages12
JournalImage and Vision Computing
Volume30
Issue number12
DOIs
Publication statusPublished - 2012

Fingerprint

Lighting
Pixels
Experiments

Cite this

@article{e73138a59a2a469fbd260edc63bd0b93,
title = "Real-time robust background subtraction under rapidly changing illumination conditions.",
abstract = "Fast robust background subtraction under sudden lighting changes is a challenging problem in many applications. In this paper, we propose a real-time approach, which combines the Eigenbackground and Statistical Illumination method to address this issue. The first algorithm is used to reconstruct the background frame, while the latter improves the foreground segmentation. In addition, we introduce an online spatial likelihood model by detecting reliable background pixels. Extensive quantitative experiments illustrate our approach consistently achieves significantly higher precision at high recall rates, compared to several state-of-the-art illumination invariant background subtraction methods.",
author = "L.P.J. Vosters and Caifeng Shan and T. Gritti",
year = "2012",
doi = "10.1016/j.imavis.2012.08.017",
language = "English",
volume = "30",
pages = "1004--1015",
journal = "Image and Vision Computing",
issn = "0262-8856",
publisher = "Elsevier",
number = "12",

}

Real-time robust background subtraction under rapidly changing illumination conditions. / Vosters, L.P.J.; Shan, Caifeng; Gritti, T.

In: Image and Vision Computing, Vol. 30, No. 12, 2012, p. 1004-1015.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Real-time robust background subtraction under rapidly changing illumination conditions.

AU - Vosters, L.P.J.

AU - Shan, Caifeng

AU - Gritti, T.

PY - 2012

Y1 - 2012

N2 - Fast robust background subtraction under sudden lighting changes is a challenging problem in many applications. In this paper, we propose a real-time approach, which combines the Eigenbackground and Statistical Illumination method to address this issue. The first algorithm is used to reconstruct the background frame, while the latter improves the foreground segmentation. In addition, we introduce an online spatial likelihood model by detecting reliable background pixels. Extensive quantitative experiments illustrate our approach consistently achieves significantly higher precision at high recall rates, compared to several state-of-the-art illumination invariant background subtraction methods.

AB - Fast robust background subtraction under sudden lighting changes is a challenging problem in many applications. In this paper, we propose a real-time approach, which combines the Eigenbackground and Statistical Illumination method to address this issue. The first algorithm is used to reconstruct the background frame, while the latter improves the foreground segmentation. In addition, we introduce an online spatial likelihood model by detecting reliable background pixels. Extensive quantitative experiments illustrate our approach consistently achieves significantly higher precision at high recall rates, compared to several state-of-the-art illumination invariant background subtraction methods.

U2 - 10.1016/j.imavis.2012.08.017

DO - 10.1016/j.imavis.2012.08.017

M3 - Article

VL - 30

SP - 1004

EP - 1015

JO - Image and Vision Computing

JF - Image and Vision Computing

SN - 0262-8856

IS - 12

ER -