Polynomial-time object recognition in the presence of clutter, occlusion, and uncertainty

  • Todd A. Cass
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 588)


We consider the problem of object recognition via local geometric feature matching in the presence of sensor uncertainty, occlusion, and clutter. We present a general formulation of the problem and a polynomial-time algorithm which guarantees finding all geometrically feasible interpretations of the data, modulo uncertainty, in terms of the model. This formulation applies naturally to problems involving both 2D and 3D objects.

The primary contributions of this work are the presentation of a robust, provably correct, polynomial-time approach to this class of recognition problems and a demonstration of its practical application; and the development of a general framework for understanding the fundamental nature of the geometric feature matching problem. This framework provides insights for analyzing and improving previously proposed recognition approaches, and enables the development of new algorithms.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Alt, H. & K. Mehlhorn & H. Wagener & E. Welzl, 1988, “Congruence, Similarity, and Symmetries of Geometric Objects”, In Discrete and Computational Geometry, Springer-Verlag, New York, 3:237–256.Google Scholar
  2. 2.
    Baird, H.S., 1985, Model-Based Image Matching Using Location, MIT Press, Cambridge, MA.Google Scholar
  3. 3.
    Bolles, R.C. & R.A. Cain, 1982, “Recognizing and Locating Partially Visible Objects: The Local-feature-focus Method”, International Journal of Robotics Research, 1(3):57–82.Google Scholar
  4. 4.
    Breuel, T. M., 1990, “An Efficient Correspondence Based Algorithm for 2D and 3D Model Based Recognition”, MIT AI Lab Memo 1259.Google Scholar
  5. 5.
    Cass, Todd A., 1988, “A Robust Implementation of 2D Model-Based Recognition”, Proceedings IEEE Conf. on Computer Vision and Pattern Recognition, Ann Arbor, Michigan.Google Scholar
  6. 6.
    Cass, Todd A., 1990, “Feature Matching for Object Localization in the Presence of Uncertainty”, MIT AI Lab Memo 1133.Google Scholar
  7. 7.
    Cass, Todd A., 1990, “Feature Matching for Object Localization in the Presence of Uncertainty”, Proceedings of the International Conference on Computer Vision, Osaka, Japan.Google Scholar
  8. 8.
    Cass, Todd A., 1991, “Polynomial-Time Object Recognition in the Presence of Clutter, Occlusion, and Uncertainty”, MIT AI Lab Memo No. 1302.Google Scholar
  9. 9.
    Edelsbrunner, H., 1987, Algorithms in Combinatorial Geometry, Springer-Verlag.Google Scholar
  10. 10.
    Fischler,M.A. & R.C. Bolles, 1981, “Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography”, Communications of the ACM 24(6):381–395.Google Scholar
  11. 11.
    Ellis, R.E., 1989, “Uncertainty Estimates for Polyhedral Object Recognition”, IEEE Int. Conf. Rob. Aut., pp. 348–353.Google Scholar
  12. 12.
    Grimson, W.E.L., 1990, “The combinatorics of object recognition in cluttered environments using constrained search”, Artificial Intelligence,44:121–166.Google Scholar
  13. 13.
    Grimson, W.E.L. & T. Lozano-Perez, 1987, “Localizing Overlapping Parts by Searching the Interpretation Tree”, IEEE Trans. on Pat. Anal. & Mach. Intel., 9(4):469–482.Google Scholar
  14. 14.
    Huttenlocher, D.P. & T. Cass, 1992, “Measuring the Quality of Hypotheses in Model-Based Recognition”, Proceedings of the European Conference on Computer Vision, Genova, Italy.Google Scholar
  15. 15.
    Huttenlocher, D.P. & S. Ullman, 1990, “Recognizing Solid Objects by Alignment with an Image,” Inter. Journ. Comp. Vision 5(2):195–212.Google Scholar
  16. 16.
    Jacobs, D., 1991, “Optimal Matching of Planar Models in 3D Scenes,” IEEE Conf. Comp. Vis. and Patt. Recog. pp. 269–274.Google Scholar
  17. 17.
    Lowe, D.G., 1986, Perceptual Organization and Visual Recognition, Kluwer Academic Publishers, Boston, MA.Google Scholar
  18. 18.
    Stockman, G. & S. Kopstein & S. Bennet, 1982, “Matching Images to Models for Registration and Object Detection via Clustering”, IEEE Trans. on Pat. Anal. & Mach. Intel.4(3).Google Scholar
  19. 19.
    Thompson, D. & J.L. Mundy, 1987, “Three-Dimensional Model Matching From an Unconstrained Viewpoint”, Proc. IEEE Conf. Rob. Aut. pp. 280.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Todd A. Cass
    • 1
  1. 1.Artificial Intelligence LaboratoryMassachusetts Institute of TechnologyCambridgeUSA

Personalised recommendations