Issue No. 05 - May (1992 vol. 14)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.134058
<p>A framework for 3D object recognition is presented. Its flexibility and extensibility are accomplished through a uniform, parallel, and modular recognition architecture. Concurrent and stacked parameter transforms reconstruct a variety of features from the input scene. At each stage, constraint satisfaction networks collect and fuse the evidence obtained through the parameter transforms, ensuring a globally consistent interpretation of the input scene and allowing for the integration of diverse types of information. The final interpretation of the scene is a small consistent subset of the many initial hypotheses about partial features, primitive features, feature assemblies, and 3D objects computed by the various parameter transforms. A complete, integrated, and implemented system that extracts planar surfaces, patches of quadrics of revolution, and planar intersection curves of these surfaces from a depth map viewing 3D objects is described. Experimental results on the recognition behavior of the system are presented.</p>
uniform parallel architecture; concurrent transforms; information integration; feature extraction; visual recognition; 3D object recognition; flexibility; extensibility; modular recognition architecture; stacked parameter transforms; constraint satisfaction networks; partial features; primitive features; feature assemblies; planar surfaces; quadrics of revolution; planar intersection curves; depth map; parallel processing; pattern recognition; picture processing
R. Bolle, R. Kjeldsen and A. Califano, "A Complete and Extendable Approach to Visual Recognition," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 14, no. , pp. 534-548, 1992.