19 February 1988 Model-Based Object Recognition Using The Connection Machine
Lewis W. Tucker, Carl R. Feynman, Mike Drumheller, Donna M. Fritzsche, David Waltz
Author Affiliations +
Proceedings Volume 0848, Intelligent Robots and Computer Vision VI; (1988)
Event: Advances in Intelligent Robotics Systems, 1987, Cambridge, CA, United States
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.
© (1988) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lewis W. Tucker, Carl R. Feynman, Mike Drumheller, Donna M. Fritzsche, and David Waltz "Model-Based Object Recognition Using The Connection Machine", Proc. SPIE 0848, Intelligent Robots and Computer Vision VI, (19 February 1988); Logo
Cited by 2 scholarly publications.
Get copyright permission  Get copyright permission on Copyright Marketplace

Object recognition

Data modeling

Image segmentation

Image processing

Model-based design

Computer vision technology


Determining the Pose of an Object
Proceedings of SPIE (June 09 1986)
Three-Dimensional Object Recognition Using Range Data
Proceedings of SPIE (March 27 1989)
Robust regression in computer vision
Proceedings of SPIE (February 01 1991)
Efficient Encoding Of Local Shape Features For 3 D...
Proceedings of SPIE (March 27 1989)
Indexing Shapes for Recognition
Proceedings of SPIE (March 27 1987)

Back to Top