This paper describes a new vision based method for the Simultaneous Localization and Mapping of mobile robots. The only data used is a video input from a moving calibrated monocular camera. From the detection and matching of interest points in images at video rate, robust estimates of the camera poses are computed in real-time and a 3D map of the environment is reconstructed. The computed
E. Mouragnon, Fabien Dekeyser, Maxime Lhuillier, M