Most cornputcr vision systems perform object recognition on the basis of the fwturcs extracted from a single image of the object. The problem with this approach is that it implicitly assumes that the availiblc fcaturcs are sufficient to determine the identity and pose of the object uniquely. If this assumption is not met, then the fcawe set is insufficient, and ambiguity results. Consequently. much rcscarch in cornputcr vision has gone towards finding sets of features that are sufficient for spccific tasks, with the result that each system has its own associated set of features. A single, general feature set would be desirable.However, research in automatic generation of object recognition programs has demonstrated that pre-dctcrmined, fixed feature sets are often incapable of providing enough information to unambiguously determine object identity and pose. One approach to overcoming the inadequacy of any feature sct is to utilize multiple sensor observations obtained from different viewpoints, and combine them with knowledge of the 3D structure of the object to perform unambiguous object recognition. This paper prcscnts initial results towards performing object recognition using multiple observations to rcsolve arnbigui tics.Starting from the premise that sensor motions should be planned out in advance, the difiicultics involved in planning with ambiguous information are discussed. A reprcscntation lor pl'anning h a t combincs geometric information with viewpoint uncertainty is presented. A sensor planner utilizing thc rcprcscntation was implemented, and the results of object recognition experimcnts pcrformcd with thc planncr are discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.