Recognizing and locating a known object from multiple images

An approach to recognizing and locating a partially visible object from multiple images for a pile of parts is proposed. The image-to-model correspondence is established through an examination of the consistency between the surface patches extracted from the images and the patches described in an object model. To obtain the scene description, which is composed of parameterized surface patches, the scene´s needle map is derived by a modified photometric stereo method. The needle map is then segmented into primitive surfaces, and the resultant patches are identified and described by using a modified Hough transformation based on the Gaussian spherical maps of the patches. To interpret the scene description, the object model is built with a frame structure to describe geometric features of the model patches. By a search process guided by some heuristic planning strategies based on the fuzzy-set concept, sets of patches considered to be possibly on the surface of the model object are extracted from the scene description. The candidate sets are tested and the locations and orientations of the corresponding object instances are computed. Results of two experiments are reported