Illumination-invariant motion detection using colour mixture models

Ming Xu; Tim Ellis

doi:10.5244/C.15.18

Illumination-invariant motion detection using colour mixture models

Ming Xu
, Tim Ellis

City, University of London
City, University of London

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

Abstract

This paper tackles the problem of robust change detection in image sequences from static cameras. Motion cues are detected using frame differencing with an adaptive background estimation modelled by a mixture of Gaussians. Illumination invariance and elimination or detection of shadows is achieved by using a colour chromaticity representation of the image data. The combination of the colour-and intensity-based models results in some promising applications.

Original language	English
Title of host publication	Proceedings - British Machine Vision Conference, BMVC 2001
Editors	Tim Cootes, Chris Taylor
Place of Publication	Manchester
Publisher	British Machine Vision Association
Pages	163-172
Number of pages	10
ISBN (Electronic)	1 901725 17 0
ISBN (Print)	1 901725 16 2
DOIs	https://doi.org/10.5244/C.15.18
Publication status	Published - 2001
Externally published	Yes

Access to Document

10.5244/C.15.18

https://bmva-archive.org.uk/bmvc/2001/papers/74/accepted_74.pdf

Cite this

@inproceedings{da975b57ebe04282b5642d068be15be9,

title = "Illumination-invariant motion detection using colour mixture models",

abstract = "This paper tackles the problem of robust change detection in image sequences from static cameras. Motion cues are detected using frame differencing with an adaptive background estimation modelled by a mixture of Gaussians. Illumination invariance and elimination or detection of shadows is achieved by using a colour chromaticity representation of the image data. The combination of the colour-and intensity-based models results in some promising applications.",

author = "Ming Xu and Tim Ellis",

year = "2001",

doi = "10.5244/C.15.18",

language = "English",

isbn = " 1 901725 16 2",

pages = "163--172",

editor = "Tim Cootes and Chris Taylor",

booktitle = "Proceedings - British Machine Vision Conference, BMVC 2001",

publisher = "British Machine Vision Association",

}

TY - GEN

T1 - Illumination-invariant motion detection using colour mixture models

AU - Xu, Ming

AU - Ellis, Tim

PY - 2001

Y1 - 2001

N2 - This paper tackles the problem of robust change detection in image sequences from static cameras. Motion cues are detected using frame differencing with an adaptive background estimation modelled by a mixture of Gaussians. Illumination invariance and elimination or detection of shadows is achieved by using a colour chromaticity representation of the image data. The combination of the colour-and intensity-based models results in some promising applications.

AB - This paper tackles the problem of robust change detection in image sequences from static cameras. Motion cues are detected using frame differencing with an adaptive background estimation modelled by a mixture of Gaussians. Illumination invariance and elimination or detection of shadows is achieved by using a colour chromaticity representation of the image data. The combination of the colour-and intensity-based models results in some promising applications.

U2 - 10.5244/C.15.18

DO - 10.5244/C.15.18

M3 - Conference Proceeding

SN - 1 901725 16 2

SP - 163

EP - 172

BT - Proceedings - British Machine Vision Conference, BMVC 2001

A2 - Cootes, Tim

A2 - Taylor, Chris

PB - British Machine Vision Association

CY - Manchester

ER -

Illumination-invariant motion detection using colour mixture models

Abstract

Access to Document

Fingerprint

Cite this