This chapter presents a novel approach to markerless real-time 3D pose estimation in a multi camera setup. We explain how foreground-background segmentation and 3D reconstruction are used to extract a 3D hull of the user. This is done in real-time using voxel carving and a fixed lookup table. The body pose is then retrieved using an example-based classifierr which uses 3D Haar-like wavelet features to allow for real-time classification. Average Neighborhood Margin Maximization (ANMM) is introduced as a powerful approach to train these Haar-like features.
© Copyright 2009 Multi-Camera Networks: Concepts and Applications. Veröffentlicht von Elsevier. Alle Rechte vorbehalten.