Motion capture based on color error maps in a distributed collaborative environment

In this paper a composite framework for collaborative working is presented. The framework includes real-time motion tracking based on computer vision from standard Web-cams situated at different locations, data transmission and real-time animation of 3D avatars in a virtual world. Motion tracking is obtained without using markers, with weak constraints on users' clothes and environment lighting, ft is based on a model fitting process that compares the 2D processed images supplied by cameras with a set of artificially generated views of a human model.