Tracking and segmenting people in varying lighting conditions using colour

Yogesh  Raja; Stephen J. McKenna; Shaogang Gong

doi:10.1109/AFGR.1998.670953

Tracking and segmenting people in varying lighting conditions using colour

Yogesh Raja (Lead / Corresponding author), Stephen J. McKenna (Lead / Corresponding author), Shaogang Gong (Lead / Corresponding author)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

144 Citations (Scopus)

Abstract

Colour cues were used to obtain robust detection and tracking of people in relatively unconstrained dynamic scenes. Gaussian mixture models were used to estimate probability densities of colour for skin, clothing and background. These models were used to detect, track and segment people, faces and hands. A technique for dynamically updating the models to accommodate changes in apparent colour due to varying lighting conditions was used. Two applications are highlighted: (1) actor segmentation for virtual studios, and (2) focus of attention for face and gesture recognition systems. A system implemented on a 200 MHz PC tracks multiple objects in real time

Original language	English
Title of host publication	Third IEEE International Conference on Automatic Face and Gesture Recognition
Subtitle of host publication	Proceedings
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	228-233
Number of pages	6
ISBN (Print)	0818683449
DOIs	https://doi.org/10.1109/AFGR.1998.670953
Publication status	Published - 1998
Event	3rd IEEE International Conference on Automatic Face and Gesture Recognition - New Public Hall, Nara, Japan Duration: 14 Apr 1998 → 16 Apr 1998

Conference

Conference	3rd IEEE International Conference on Automatic Face and Gesture Recognition
Abbreviated title	FG'98
Country/Territory	Japan
City	Nara
Period	14/04/98 → 16/04/98

Access to Document

10.1109/AFGR.1998.670953

Cite this

@inproceedings{a56b6577e55741f2bbeafa4189053c17,

title = "Tracking and segmenting people in varying lighting conditions using colour",

abstract = "Colour cues were used to obtain robust detection and tracking of people in relatively unconstrained dynamic scenes. Gaussian mixture models were used to estimate probability densities of colour for skin, clothing and background. These models were used to detect, track and segment people, faces and hands. A technique for dynamically updating the models to accommodate changes in apparent colour due to varying lighting conditions was used. Two applications are highlighted: (1) actor segmentation for virtual studios, and (2) focus of attention for face and gesture recognition systems. A system implemented on a 200 MHz PC tracks multiple objects in real time",

author = "Yogesh Raja and McKenna, {Stephen J.} and Shaogang Gong",

year = "1998",

doi = "10.1109/AFGR.1998.670953",

language = "English",

isbn = "0818683449 ",

pages = "228--233 ",

booktitle = "Third IEEE International Conference on Automatic Face and Gesture Recognition",

publisher = "IEEE",

note = "3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG'98 ; Conference date: 14-04-1998 Through 16-04-1998",

}

Raja, Y, McKenna, SJ & Gong, S 1998, Tracking and segmenting people in varying lighting conditions using colour. in Third IEEE International Conference on Automatic Face and Gesture Recognition: Proceedings. IEEE, Piscataway, NJ, pp. 228-233 , 3rd IEEE International Conference on Automatic Face and Gesture Recognition, Nara, Japan, 14/04/98. https://doi.org/10.1109/AFGR.1998.670953

Tracking and segmenting people in varying lighting conditions using colour. / Raja, Yogesh (Lead / Corresponding author); McKenna, Stephen J. (Lead / Corresponding author); Gong, Shaogang (Lead / Corresponding author).
Third IEEE International Conference on Automatic Face and Gesture Recognition: Proceedings. Piscataway, NJ: IEEE, 1998. p. 228-233 .

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Tracking and segmenting people in varying lighting conditions using colour

AU - Raja, Yogesh

AU - McKenna, Stephen J.

AU - Gong, Shaogang

PY - 1998

Y1 - 1998

N2 - Colour cues were used to obtain robust detection and tracking of people in relatively unconstrained dynamic scenes. Gaussian mixture models were used to estimate probability densities of colour for skin, clothing and background. These models were used to detect, track and segment people, faces and hands. A technique for dynamically updating the models to accommodate changes in apparent colour due to varying lighting conditions was used. Two applications are highlighted: (1) actor segmentation for virtual studios, and (2) focus of attention for face and gesture recognition systems. A system implemented on a 200 MHz PC tracks multiple objects in real time

AB - Colour cues were used to obtain robust detection and tracking of people in relatively unconstrained dynamic scenes. Gaussian mixture models were used to estimate probability densities of colour for skin, clothing and background. These models were used to detect, track and segment people, faces and hands. A technique for dynamically updating the models to accommodate changes in apparent colour due to varying lighting conditions was used. Two applications are highlighted: (1) actor segmentation for virtual studios, and (2) focus of attention for face and gesture recognition systems. A system implemented on a 200 MHz PC tracks multiple objects in real time

U2 - 10.1109/AFGR.1998.670953

DO - 10.1109/AFGR.1998.670953

M3 - Conference contribution

SN - 0818683449

SP - 228

EP - 233

BT - Third IEEE International Conference on Automatic Face and Gesture Recognition

PB - IEEE

CY - Piscataway, NJ

T2 - 3rd IEEE International Conference on Automatic Face and Gesture Recognition

Y2 - 14 April 1998 through 16 April 1998

ER -

Tracking and segmenting people in varying lighting conditions using colour

Abstract

Conference

Access to Document

Fingerprint

Cite this