Recognition of 2-D occluded objects and their manipulation by PUMA 560 robot

A new method based on a cluster-structure paradigm is presented for the recognition of 2-D partially occluded objects. This method uses the line segments which comprise the boundary of an object in the recognition process. The length of each of these segments as well as the angle between successive segments comprise the only information needed by the program to find an object's position. The technique is applied in several steps which include segment clustering, finding all sequences in one pass over the data, and final clustering of sequences so as to obtain the desired rotational and translational information. The amount of computational effort decreases as the recognition algorithm progresses. As compared to earlier methods, which identify an object based on only one sequence of matched segments, the new technique allows the identification of all parts of the model which match with the apparent image. These parts need not be adjacent to each other. Also the method is able to tolerate a moderate change in scale and a significant amount of shape distortion arising as a result of segmentation or the polygonal approximation of the boundary of the object. The method has been evaluated with respect to a large number of examples where several objects partially occlude one another. A summary of the results is presented.