Study on color space selection for detecting cast shadows in video surveillance

Csaba Benedek, T. Szirányi

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

In this article, the authors address the color modeling problem of cast shadows in video sequences. It is illustrated that the performance of shadow detection can be improved significantly through appropriate color space selection, if for practical purposes, the number of free parameters of the method should be kept low. Hence, the authors compare several well known color spaces with a six-parameter shadow model embedded into a globally optimal MRF framework. Experimental results are shown regarding the following questions: (1) What is the gain of using color images instead of grayscale ones? (2) What is the gain of using uncorrelated spaces instead of the standard RGB? (3) Chrominance (illumination invariant), luminance, or mixed spaces are more effective? (4) In which scenes are the differences significant? The authors qualified the metrics both in color based clustering of the individual pixels and in the case of Bayesian foreground-background-shadow segmentation. Experimental results on real-life videos show that CIE L*u*v* color space is the most efficient.

Original languageEnglish
Pages (from-to)190-201
Number of pages12
JournalInternational Journal of Imaging Systems and Technology
Volume17
Issue number3
DOIs
Publication statusPublished - 2007

Fingerprint

surveillance
casts
Color
color
luminance
Luminance
Lighting
Pixels
illumination
pixels

Keywords

  • Color spaces
  • MRF
  • Shadow detection
  • Video surveillance

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Atomic and Molecular Physics, and Optics
  • Computer Vision and Pattern Recognition

Cite this

Study on color space selection for detecting cast shadows in video surveillance. / Benedek, Csaba; Szirányi, T.

In: International Journal of Imaging Systems and Technology, Vol. 17, No. 3, 2007, p. 190-201.

Research output: Contribution to journalArticle

@article{a0ffd05f13af454a903be857966134ac,
title = "Study on color space selection for detecting cast shadows in video surveillance",
abstract = "In this article, the authors address the color modeling problem of cast shadows in video sequences. It is illustrated that the performance of shadow detection can be improved significantly through appropriate color space selection, if for practical purposes, the number of free parameters of the method should be kept low. Hence, the authors compare several well known color spaces with a six-parameter shadow model embedded into a globally optimal MRF framework. Experimental results are shown regarding the following questions: (1) What is the gain of using color images instead of grayscale ones? (2) What is the gain of using uncorrelated spaces instead of the standard RGB? (3) Chrominance (illumination invariant), luminance, or mixed spaces are more effective? (4) In which scenes are the differences significant? The authors qualified the metrics both in color based clustering of the individual pixels and in the case of Bayesian foreground-background-shadow segmentation. Experimental results on real-life videos show that CIE L*u*v* color space is the most efficient.",
keywords = "Color spaces, MRF, Shadow detection, Video surveillance",
author = "Csaba Benedek and T. Szir{\'a}nyi",
year = "2007",
doi = "10.1002/ima.20110",
language = "English",
volume = "17",
pages = "190--201",
journal = "International Journal of Imaging Systems and Technology",
issn = "0899-9457",
publisher = "John Wiley and Sons Inc.",
number = "3",

}

TY - JOUR

T1 - Study on color space selection for detecting cast shadows in video surveillance

AU - Benedek, Csaba

AU - Szirányi, T.

PY - 2007

Y1 - 2007

N2 - In this article, the authors address the color modeling problem of cast shadows in video sequences. It is illustrated that the performance of shadow detection can be improved significantly through appropriate color space selection, if for practical purposes, the number of free parameters of the method should be kept low. Hence, the authors compare several well known color spaces with a six-parameter shadow model embedded into a globally optimal MRF framework. Experimental results are shown regarding the following questions: (1) What is the gain of using color images instead of grayscale ones? (2) What is the gain of using uncorrelated spaces instead of the standard RGB? (3) Chrominance (illumination invariant), luminance, or mixed spaces are more effective? (4) In which scenes are the differences significant? The authors qualified the metrics both in color based clustering of the individual pixels and in the case of Bayesian foreground-background-shadow segmentation. Experimental results on real-life videos show that CIE L*u*v* color space is the most efficient.

AB - In this article, the authors address the color modeling problem of cast shadows in video sequences. It is illustrated that the performance of shadow detection can be improved significantly through appropriate color space selection, if for practical purposes, the number of free parameters of the method should be kept low. Hence, the authors compare several well known color spaces with a six-parameter shadow model embedded into a globally optimal MRF framework. Experimental results are shown regarding the following questions: (1) What is the gain of using color images instead of grayscale ones? (2) What is the gain of using uncorrelated spaces instead of the standard RGB? (3) Chrominance (illumination invariant), luminance, or mixed spaces are more effective? (4) In which scenes are the differences significant? The authors qualified the metrics both in color based clustering of the individual pixels and in the case of Bayesian foreground-background-shadow segmentation. Experimental results on real-life videos show that CIE L*u*v* color space is the most efficient.

KW - Color spaces

KW - MRF

KW - Shadow detection

KW - Video surveillance

UR - http://www.scopus.com/inward/record.url?scp=35848940086&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35848940086&partnerID=8YFLogxK

U2 - 10.1002/ima.20110

DO - 10.1002/ima.20110

M3 - Article

AN - SCOPUS:35848940086

VL - 17

SP - 190

EP - 201

JO - International Journal of Imaging Systems and Technology

JF - International Journal of Imaging Systems and Technology

SN - 0899-9457

IS - 3

ER -