Construction précise de bases d’amers géo-référencés pour la localisation d’un véhicule en milieu urbain

To provide high quality Augmented Reality AR service, accurate 6DoF localization is required. To ensure such accuracy, most of current vision-based solutions rely on an offline large scale modeling of the environment. While existing solutions require expensive equipments and/or a prohibitive computation time, we propose in this paper a complete framework that automatically builds an accurate city scale database of landmarks using only a standard camera, a GPS and GIS Geographic Information System.