Méthodes de reconstruction denses pour la vision active

This paper aims to analyse how to introduce 3D information into an active vision system . In order to do so, we propose to realiz e a dense reconstruction from a monocular sequence in an active vision application . We first present existing algorithms for dens e reconstruction . After having compared their drawbacks and advantages, we describe the chosen algorithm . Finally, we show th e results obtained from synthetic images and images acquired when using an artificial robotic head .