Using computer vision for 3D probabilistic reconstruction and motion tracking

Abstract

This paper presents an approach to the 3D visual tracking problem into multi-camera environments. This proposal executes the markerless visual tracking observing the environment through a model based in a volumetric reconstruction technique, called 3D Probabilistic Occupancy Grid, which is still seldom used for this purpose. The target is tracked by the use of Expectation-Maximization algorithm with an object representation model constructed with Gaussians blobs representing the object body parts.