Abstract
The Geometric Hashing paradigm for model-based recognition of objects in cluttered scenes is discussed. This paradigm enables a unified approach to rigid object recognition under different viewing transformation assumptions both for 2-D and 3-D objects obtained by different sensors, e.g. vision, range, tactile. It is based on an intensive off-line model preprocessing (learning) stage, where model information is indexed into a hash-table using minimal, transformation invariant features. This enables the on-line recognition algorithm to be particularly efficient. The algorithm is straightforwardly parallelizable. Initial experimentation of the technique has led to successful recognition of both 2-D and 3-D objects in cluttered scenes from an arbitrary viewpoint. We, also, compare the Geometric Hashing with the Hough Transform and the alignment techniques. Extensions of the basic paradigm which reduce its worst case recognition complexity are discussed.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
N. Ayache and O. D. Faugeras. HYPER: A New Approach for the Recognition and Positionning of Two-Dimensional Objects. IEEE TPAMI, 8(1):44–54, 1986.
D. H. Ballard. Generalizing the Hough Transform to Detect Arbitrary Shapes. Pattern Recognition, 13(2):111–122, 1981.
D. H. Ballard and B. C. M. Computer Vision. Prentice-Hall, 1982.
P. J. Besl and R. C. Jain. Three-Dimensional Object Recognition. ACM Computing Surveys, 17(1):75–154, 1985.
O. Bourdon and G. Medioni. Object Recognition using Geometric Hashing on the Connection Machine. Technical report, Inst. for Robotics and Intell. Systems, USC, 1989.
R. T. Chin and C. R. Dyer. Model-Based Recognition in Robot Vision. ACM Computing Surveys, 18(1):67–108, 1986.
B. N. Delone and D. A. Raikov. Analytic Geometry, volume 2. Moscow, 1949.
W. E. Grimson and T. Lozano-Pérez. Localizing overlapping parts by searching the interpretation tree. IEEE TPAMI, 9(4):469–482, 1987.
W. E. L. Grimson. The Combinatorics of Object Recognition in Cluttered Environments using Constrained Search. In Proc. of ICCV, pages 218–227, Tampa, Florida, Dec. 1988.
A. Heller and J. Stenstrom. Verification of Recognition and Alignment Hypothesis by Means of Edge Verification Statistics. In Proc. of the DARPA IU Workshop, pages 957–966, Palo Alto, Ca., 1989.
J. Hong and H. J. Wolfson. An Improved Model-Based Matching Method Using Footprints. In Proc. of ICPR, pages 72–78, Rome, Italy, Nov. 1988.
B. K. P. Horn. Robot Vision. MIT Press, 1986.
D. P. Huttenlocher and S. Ullman. Object Recognition using Alignment. In Proc. of ICCV, pages 102–111, London, 1987.
D. P. Huttenlocher and S. Ullman. Recognizing Solid Objects by Alignment. In Proc. of the DARPA IU Workshop, pages 1114–1122, Cambridge, Massachusetts, Apr. 1988.
E. Kishon and H. Wolfson. 3-D Curve Matching. In Proc. of AAAI Workshop on Spatial Reasoning and Multisensor Fusion, pages 250–261, St. Charles, Illinois, 1987.
F. Klein. Elementary Mathematics from an Advanced Standpoint; Geometry. Macmillan, New York, 1925 (Third edition).
I. B. Kuperman. Approximate Linear Algebraic Equations. Van Nostrand, 1971.
Y. Lamdan, J. T. Schwartz, and H. J. Wolfson. Object Recognition by Affine Invariant Matching. In Proc. of CVPR Conf., pages 335–344, Ann Arbor, Michigan, June 1988.
Y. Lamdan, J. T. Schwartz, and H. J. Wolfson. On Recognition of 3-D Objects from 2-D Images. In Proc. of IEEE Int. Conf. on Robotics and Automation, pages 1407–1413, Philadelphia, Pa., Apr. 1988.
Y. Lamdan and H. J. Wolfson. Geometric Hashing: A General and Efficient Model-Based Recognition Scheme. In Proc. of ICCV, pages 238–249, Tampa, Florida, Dec. 1988.
Y. Lamdan and H. J. Wolfson. On the Error Analysis of ‘Geometric Hashing'. Technical report, Robotics Lab, Courant Inst. of Math., NYU, 1989.
S. Linnainmaa, D. Harwood, and L. Davis. Pose Determination of a Three-Dimensional Object Using Triangle Paris. IEEE TPAMI, 10(5):634–647, 1988.
Y. Ohta, K. Maenobu, and T. Sakai. Obtaining Surface Orientation from Texels under Perspective Projection. In Proc. of IJCAI, pages 746–751, Vancouver, B.C., Canada, Aug. 1981.
J. Schwartz and M. Sharir. Some Remarks on Robot Vision. In Trans. of 3'rd Army Conf. on Applied Math. and Computing, pages 1–36, Atlanta, Ga., May 1985.
D. Shoham and S. Ullman. Aligning a Model to an Image using Minimal Information. In Proc. of ICCV, pages 259–263, Tampa, Florida, Dec. 1988.
F. Stein and G. Medioni. Graycode Representation and Indexing: Fast Two Dimensional Object Recognition. Technical report, Inst. for Robotics and Intell. Systems, USC, 1989.
G. Stockman. Object Recognition and Localization via Pose Clustering. J. of Computer Vision, Graphics, and Image Processing, 40(3):361–387, 1987.
D. Thompson and J. Mundy. Three-Dimensional Model Matching from an Unconstrained Viewpoints. In Proc. of IEEE Int. Conf. on Robotics and Automation, pages 208–220, Raleigh, N. Carolina, 1987.
H. J. Wolfson and R. Nussinov. Efficient Detection of Motifs in Biological Macromolecules by Computer Vision Techniques. Technical report, Tel Aviv University, 1990. in preparation.
I. Yaglom and V. Ashkinuze. Ideas and Methods of Affine Projective Geometry. Moscow, 1962.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wolfson, H.J. (1990). Model-based object recognition by geometric hashing. In: Faugeras, O. (eds) Computer Vision — ECCV 90. ECCV 1990. Lecture Notes in Computer Science, vol 427. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0014902
Download citation
DOI: https://doi.org/10.1007/BFb0014902
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-52522-6
Online ISBN: 978-3-540-47011-3
eBook Packages: Springer Book Archive