Cooperative background modelling using multiple cameras towards human detection in smart-rooms

In multi-camera systems for human detection and analysis, Shape-from-Silhouette (SfS) is a common approach taken to reconstruct the Visual Hull, i.e. the 3D-Shape, of the bodies. The reconstructed 3D-Shape is later used in 3D-trackers and body fitting techniques. The Visual Hull is formally defined as the intersection of the visual cones formed by the back-projection of several 2D binary silhouettes into the 3D space. Silhouettes are usually extracted using a foreground classification process, which is performed independently in each camera view. In this paper we present a novel approach in which 2D-foreground classification is achieved in 3D accordance in a Bayesian framework. In our approach, instead of classifying images and reconstructing the volume later, we simultaneously reconstruct and classify in the 3D space. Furthermore, the classification of the 3D space is used to obtain a more accurate model of the 2D-background.