This paper reports on a model-based object recognition system and its parallel implementation on the Connection Machine' System. The goal is to be able to recognize a large number of partially occluded, two-dimensional objects in scenes of moderate complexity. In contrast to traditional approaches, the system described here uses a parallel hypothesize and test method that avoids serial search. The basis for hypothesis generation is provided by local boundary features (such as corners formed by intersecting line segments) that constrain an object's position and orientation. Once generated, hypothetical instances of models are either accepted or rejected by a verification process that computes each instance's overall confidence. Even on a massively parallel computer, however, the potential for combinatorial explosion of hypotheses is still of major concern when the number of objects and models becomes large. We control this explosion by accumulating weak evidence in the form of votes in position and orientation space cast by each hypothesis. The density of votes in parameter space is expected to be proportional to the degree to which hypotheses receive support from different local features. Thus, it becomes possible to rank hypotheses prior to verification and test more likely hypotheses first.
The authors report on a model-based object recognition system and its parallel implementation on the Connection Machine system. The goal is to recognize two-dimensional objects in a scene, given a reasonably large database of known objects. The system uses massively parallel hypotheses generation and parameter space clustering in place of serial constraint propagation. Local boundary features that constrain an object's position and orientation provide a basis for hypothesis generation. Parameter space clustering of hypotheses is used to rank hypotheses according to preliminary evidence prior to verification. This greatly reduces the time for recognition and number of hypotheses that must be tested. Experiments show that the time required by this approach scales at a much slower range than either the number of objects in the database or objects in the scene.< >
This paper describes a model-based vision system for recognizing three-dimensional objects in two-dimensional images of natural scenes. The system is implemented entirely in parallel on a CM-2 Connection Machine System. It is novel in that it does not use a three-dimensional representation of the object. Instead, the representation of the object is constructed from a number of images of the object taken from known positions. By interpolating the appearance of the same feature in different views, it is possible to estimate the appearance of the feature from any camera position. By applying this interpolation process to many features, it is possible to reconstruct the appearance of the object from any angle and position. Features observed in the scene to be recognized can then be used to generate hypotheses as to the pose of the object. These hypotheses then compete to explain the observed features of the scene. A novel representation of features is used, which permits features of many types - lines, corners, curvature extrema and inflection points - to be treated identically by the correspondence, interpolation, and hypothesis generation processes.
