Non-linear statistical models for the 3D reconstruction of human pose and motion from monocular image sequences

This paper presents a model based approach to human body tracking in which the 2D silhouette of a moving human and the corresponding 3D skeletal struc ture are encapsulated within a non-linear point distribution model. This st atistical model allows a direct mapping to be achieved between the external boundary of a human and the anatomical position. It is shown how this info rmation, along with the position of landmark features such as the hands and head can be used to reconstruct information about the pose and structure o f the human body from a monocular view of a scene. (C) 2000 Elsevier Scienc e B.V. All rights reserved.