EXTRACTING A VALID BOUNDARY REPRESENTATION FROM A SEGMENTED RANGE IMAGE

A new approach is presented for extracting an explicit 3-D shape model from a single range image. One novel aspect is that the model represe nts both observed object surfaces, and surfaces which bound the volume of occluded space. Another novel aspect is that the approach does not require that the range image segmentation be perfect. The low-level s egmentation may be such that the model-building process encounters top ology versus geometry conflicts. The model-building process is designe d to be ''fail soft'' in the face of such problems. The portion of the 3-D model where a problem presents itself is ''glued'' together in a manner meant to minimize the disturbance in the 3-D shape. The goal is to produce a valid boundary-representation which can be processed by higher-level routines. A third novel aspect of this work is that the i mplementation has been evaluated on over 200 real range images of poly hedral objects, with no operator intervention and all parameters held constant, and obtained a 97% success rate in creating valid b-reps.