A Multi-Level Geometric Reasoning System for Vision

Abstract Geometry is known to play an important role in image understanding and machine vision. Geometric reasoning is employed in different forms in model formation and model matching problems in model-based vision research. Geometric representations and reasoning methods are often used implicitly in the design of vision systems and algorithms used there. An approach towards model-based vision in which geometric and algebraic reasoning is explicit is discussed. A multi-level reasoning system for machine vision based on this approach is being designed and developed at General Electric Corporate Research and Development. Three key components of this system—a hierarchical organization of geometric knowledge for its systematic and efficient use as well as to control the search space, labeling algorithms and algebraic reasoning algorithms—are presented. The use of such a system for deriving a three-dimensional model from two-dimensional images as well as for using a two-dimensional image for matching against another two-dimensional image (called view consistency problems) is discussed.

[1]  Kokichi Sugihara,et al.  An Algebraic Approach to Shape-from-Image Problems , 1984, Artif. Intell..

[2]  D. Knuth,et al.  Simple Word Problems in Universal Algebras , 1983 .

[3]  Deepak Kapur,et al.  RRL: A Rewrite Rule Laboratory , 1986, CADE.

[4]  George E. Collins,et al.  Cylindrical Algebraic Decomposition I: The Basic Algorithm , 1984, SIAM J. Comput..

[5]  Joseph L. Mundy,et al.  Wu's Method and its Application to Perspective Viewing , 1988, Artif. Intell..

[6]  Larry S. Davis,et al.  Object recognition using oriented model points , 1986 .

[7]  Joseph A. Goguen,et al.  Putting Theories Together to Make Specifications , 1977, IJCAI.

[8]  Martin Herman,et al.  Geometric Reasoning for Constructing 3D Scene Descriptions from Images , 1988, Artif. Intell..

[9]  V. Torre,et al.  On The Understanding Of Line Drawings , 1987, Other Conferences.

[10]  Rodney A. Brooks,et al.  Symbolic Reasoning Among 3-D Models and 2-D Images , 1981, Artif. Intell..

[11]  Herbert Freeman,et al.  Computer Description of Bodies Bounded by Quadric Surfaces from a Set of Imperfect Projections , 1978, IEEE Transactions on Computers.

[12]  B. Buchberger,et al.  Grobner Bases : An Algorithmic Method in Polynomial Ideal Theory , 1985 .

[13]  M. B. Clowes,et al.  On Seeing Things , 1971, Artif. Intell..

[14]  Ramesh C. Jain,et al.  Three-dimensional object recognition , 1985, CSUR.

[15]  Alexander A. Stepanov,et al.  Operators and algebraic structures , 1981, FPCA '81.

[16]  Martin Herman,et al.  Representation and Incremental Construction of a Three-Dimensional Scene Model , 1986 .

[17]  Robert E. Shostak,et al.  On the SUP-INF Method for Proving Presburger Formulas , 1977, JACM.

[18]  D. W. Thompson,et al.  Three-dimensional model matching from an unconstrained viewpoint , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[19]  David L. Waltz,et al.  Generating Semantic Descriptions From Drawings of Scenes With Shadows , 1972 .

[20]  Deepak Kapur.  Geometry theorem proving using Hilbert's Nullstellensatz , 1986, SYMSAC '86.

[21]  W. Bledsoe.  A new method for proving certain Presburger formulas , 1975, IJCAI 1975.