Authors: Francesco Callari, Gilbert Soucy and Frank Ferrie
Download (1416 KB)
Abstract: This paper introduces a novel model-based technique to determine the pose of complex, non-cooperatrice 3-D objects from laser rangefinder images. Geometrical models of object parts are probabilistically matched against a model database, and various sources of uncertainty are carried through the process, yielding local, point-by-point estimates of position and predicted error. Promising experimental results are presented and discussed.