Recognition of 3-D objects in range images using a butterfly multiprocessor

The recent advent of Multiple Instruction Multiple Data (MIMD) architectures together with the potentially attractive application of range images for object recognition, motivated the development of a successful goal-directed 3-D object recognition system on a 18 node Butterfly multiprocessor. This system, which combines the use of range images, multiprocessing, and rule-based control in a unique manner, provides several new insights and data points into these research areas. Several topics pertinent to current research were explored. First, a new method of surface characterization using a curvature graph was proposed and tested. It was determined that by jointly using information provided by the principal curvatures, the potential exists for uniquely identifying a larger variety of surfaces than has heretofore been accomplished. Second, a 3-D surface-type data representation, coupled with the depth information available in range images, was used to correctly recognize and interpret occluded scenes. Finally, it was determined that both multiprocessing and a rule-guided/goal-directed search can be successfully combined in an object recognition system. Multiprocessing was employed both at the object level and within objects. This enabled the achievement of near linear speedups for scenes containing fewer objects than the number of available processors. 3-D object recognition Surface characterization Butterfly multiprocessor Range images Curvature graphs