Bayesian Pixel Classification for Human Tracking

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Daniel Roth Articles by Petr Doubek Articles by Luc Van Gool

IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2

Breckenridge, Colorado

January 05-January 07

ISBN: 0-7695-2271-8

	ASCII Text	x
	Daniel Roth, Petr Doubek, Luc Van Gool, "Bayesian Pixel Classification for Human Tracking," Applications of Computer Vision and the IEEE Workshop on Motion and Video Computing, IEEE Workshop on, vol. 2, pp. 78-83, IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2, 2005.

	BibTex	x
	@article{ 10.1109/ACVMOT.2005.34, author = {Daniel Roth and Petr Doubek and Luc Van Gool}, title = {Bayesian Pixel Classification for Human Tracking}, journal ={Applications of Computer Vision and the IEEE Workshop on Motion and Video Computing, IEEE Workshop on}, volume = {2}, year = {2005}, isbn = {0-7695-2271-8}, pages = {78-83}, doi = {http://doi.ieeecomputersociety.org/10.1109/ACVMOT.2005.34}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Applications of Computer Vision and the IEEE Workshop on Motion and Video Computing, IEEE Workshop on TI - Bayesian Pixel Classification for Human Tracking SN - 0-7695-2271-8 SP78 EP83 A1 - Daniel Roth, A1 - Petr Doubek, A1 - Luc Van Gool, PY - 2005 KW - null VL - 2 JA - Applications of Computer Vision and the IEEE Workshop on Motion and Video Computing, IEEE Workshop on ER -

Daniel Roth, ETH Z?rich, Switzerland

Petr Doubek, ETH Z?rich, Switzerland

Luc Van Gool, ETH Z?rich, Switzerland

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ACVMOT.2005.34

We present a monocular object tracker, able to detect and track multiple objects in non-controlled environments. Bayesian per-pixel classification is used to build a tracking framework that segments an image into foreground and background objects, based on observations of object appearances and motions. Gaussian mixtures are used to build the color appearance models. The system adapts to changing lighting conditions, handles occlusions, and works in real-time.

Citation:

Daniel Roth, Petr Doubek, Luc Van Gool, "Bayesian Pixel Classification for Human Tracking," wacv-motion, vol. 2, pp.78-83, IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2, 2005

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.