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.
Bayesian Pixel Classification for Human Tracking
2005-01-01
464978 byte
Conference paper
Electronic Resource
English
Sub-Pixel Bayesian Estimation of Albedo and Height
British Library Online Contents | 1996
|Bayesian Classification Scheme
NTRS | 1992
|Gibbs likelihoods for Bayesian tracking
IEEE | 2004
|Multistatic Bayesian extended target tracking
IEEE | 2016
|