Color models of shadow detection in video scenes

Csaba Benedek, T. Szirányi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper we address the problem of appropriate modelling of shadows in color images. While previous works compared the different approaches regarding their model structure, a comparative study of color models has still missed. This paper attacks a continuous need for defining the appropriate color space for this main surveillance problem. We introduce a statistical and parametric shadow model-framework, which can work with different color spaces, and perform a detailed comparision with it. We show experimental results 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? We 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
Title of host publicationVISAPP 2007 - 2nd International Conference on Computer Vision Theory and Applications, Proceedings
Pages225-232
Number of pages8
VolumeIFP
EditionIA/-
Publication statusPublished - 2007
Event2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007 - Barcelona, Spain
Duration: Mar 8 2007Mar 11 2007

Other

Other2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007
CountrySpain
CityBarcelona
Period3/8/073/11/07

Fingerprint

Color
Model structures
Luminance
Lighting
Pixels

Keywords

  • Color spaces
  • MRF
  • Shadow

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Benedek, C., & Szirányi, T. (2007). Color models of shadow detection in video scenes. In VISAPP 2007 - 2nd International Conference on Computer Vision Theory and Applications, Proceedings (IA/- ed., Vol. IFP, pp. 225-232)

Color models of shadow detection in video scenes. / Benedek, Csaba; Szirányi, T.

VISAPP 2007 - 2nd International Conference on Computer Vision Theory and Applications, Proceedings. Vol. IFP IA/-. ed. 2007. p. 225-232.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Benedek, C & Szirányi, T 2007, Color models of shadow detection in video scenes. in VISAPP 2007 - 2nd International Conference on Computer Vision Theory and Applications, Proceedings. IA/- edn, vol. IFP, pp. 225-232, 2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007, Barcelona, Spain, 3/8/07.
Benedek C, Szirányi T. Color models of shadow detection in video scenes. In VISAPP 2007 - 2nd International Conference on Computer Vision Theory and Applications, Proceedings. IA/- ed. Vol. IFP. 2007. p. 225-232
Benedek, Csaba ; Szirányi, T. / Color models of shadow detection in video scenes. VISAPP 2007 - 2nd International Conference on Computer Vision Theory and Applications, Proceedings. Vol. IFP IA/-. ed. 2007. pp. 225-232
@inproceedings{1c4c0254b4214750bdab5bc94726f91b,
title = "Color models of shadow detection in video scenes",
abstract = "In this paper we address the problem of appropriate modelling of shadows in color images. While previous works compared the different approaches regarding their model structure, a comparative study of color models has still missed. This paper attacks a continuous need for defining the appropriate color space for this main surveillance problem. We introduce a statistical and parametric shadow model-framework, which can work with different color spaces, and perform a detailed comparision with it. We show experimental results 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? We 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",
author = "Csaba Benedek and T. Szir{\'a}nyi",
year = "2007",
language = "English",
volume = "IFP",
pages = "225--232",
booktitle = "VISAPP 2007 - 2nd International Conference on Computer Vision Theory and Applications, Proceedings",
edition = "IA/-",

}

TY - GEN

T1 - Color models of shadow detection in video scenes

AU - Benedek, Csaba

AU - Szirányi, T.

PY - 2007

Y1 - 2007

N2 - In this paper we address the problem of appropriate modelling of shadows in color images. While previous works compared the different approaches regarding their model structure, a comparative study of color models has still missed. This paper attacks a continuous need for defining the appropriate color space for this main surveillance problem. We introduce a statistical and parametric shadow model-framework, which can work with different color spaces, and perform a detailed comparision with it. We show experimental results 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? We 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 paper we address the problem of appropriate modelling of shadows in color images. While previous works compared the different approaches regarding their model structure, a comparative study of color models has still missed. This paper attacks a continuous need for defining the appropriate color space for this main surveillance problem. We introduce a statistical and parametric shadow model-framework, which can work with different color spaces, and perform a detailed comparision with it. We show experimental results 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? We 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

UR - http://www.scopus.com/inward/record.url?scp=67650230378&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650230378&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:67650230378

VL - IFP

SP - 225

EP - 232

BT - VISAPP 2007 - 2nd International Conference on Computer Vision Theory and Applications, Proceedings

ER -