BMVC 2004, Kingston, 7th-9th Sept, 2004

Markov-based Silhouette Extraction for Three--Dimensional Body Tracking in Presence of Cluttered Background
A. Shahrokni, V. Lepetit (EPFL, Switzerland), T. Drummond (University of
Cambridge) and P. Fua (EPFL, Switzerland)

We propose a novel method to detect human body contours in presence of
clutter and complex texture. Contours are extracted using a novel Markovbased
approach which learns a texture along a given scanline in order to
detect texture crossings. In contrast to conventional silhouette detection algorithms
based on gradient, our texture boundary detection method allows
extraction of silhouettes of textured and non-textured objects under dif-
cult conditions such as having a cluttered/moving background. We demonstrate
on demanding examples of monocular body tracking that our proposed
method yields better results than gradient-based techniques.
(pdf article)