Advertisement

Matching convex polygons and polyhedra, allowing for occlusion

  • Ronen Basri
  • David Jacobs
Submitted Contributions
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1148)

Abstract

We review our recent results on visual object recognition and reconstruction allowing for occlusion. Our scheme uses matches between convex parts of objects in the model and image to determine structure and pose, without relying on specific correspondences between local or global geometric features of the objects. We provide results determining the minimal number of regions required to uniquely determine the pose under a variety of situations, and also showing that, depending on the situation, the problem of determining pose may be a convex optimization problem that is efficiently solved, or it may be a non-convex optimization problem which has no known, efficient solution. We also relate the problem of determining pose using region matching to the problem of finding the transformation that places one polygon inside another and the problem of finding a line that intersects each of a set of 3-D volumes.

Keywords

Image Region Convex Polygon Hausdorff Distance Model Volume Projective Transformation 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Alter, T. D., and W. E. L. Grimson, 1993, “Fast and Robust 3D Recognition by Alignment,” in Proc. Fourth Inter. Conf. Computer Vision: 113–120.Google Scholar
  2. 2.
    Alter, T. D. and D. Jacobs, 1994, “Error Propagation in Full 3D-from-2D Object Recognition,” IEEE Conf. on Computer Vision and Pattern Recognition: 892–898.Google Scholar
  3. 3.
    Pankaj Agarwal, Nina Amenta, Boris Aronov and Micha Sharir. “Largest placements and motion planning of a convex polygon,” submitted to Discrete and Computational Geometry.Google Scholar
  4. 4.
    Amenta, N., 1992, “Finding a Line Traversal of Axial Objects in Three Dimensions,” Proc. of the Third ACM-SIAM Symp. on Discrete Alg.:66–71.Google Scholar
  5. 5.
    Amenta, N., personal communication.Google Scholar
  6. 6.
    Amenta, N., 1994, “Bounded boxes, Hausdorff distance, and a new proof of an interesting Helly-type theorem,” Proceedings of the 10th Annual ACM Symposium on Computational Geometry: 340–347.Google Scholar
  7. 7.
    Bajcsy, R. and Solina, F., 1987. “Three dimensional object representation revisited,” Proc. of The First Int. Conf. on Computer Vision, London: 231–240.Google Scholar
  8. 8.
    R. Basri and D. Jacobs, 1995, “Recognition Using Region Correspondences,” Int. Conf. on Comp. Vis:8–15.Google Scholar
  9. 9.
    R. Basri and D. Jacobs, 1995, “Recognition Using Region Correspondences,” The Weizmann Inst. of Science, TR-CS95-33.Google Scholar
  10. 10.
    Biederman, I. 1985. “Human image understanding: recent research and a theory,” Computer Vision, Graphics, and Image Processing, 32: 29–73.Google Scholar
  11. 11.
    Binford, T.O., 1971. “Visual perception by computer,” IEEE Conf. on Systems and Control.Google Scholar
  12. 12.
    Brooks, R., 1981. “Symbolic reasoning among 3-dimensional models and 2-dimensional images,” Artificial Intelligence, 17: 285–349.CrossRefGoogle Scholar
  13. 13.
    B. Chazelle, 1983, “The Polygon Containment Problem,” in Advances in Computing Research, Vol. 1: Computational Geometry (F. Preparata, Ed.):1–33, JAI Press, London England.Google Scholar
  14. 14.
    L. Chew and K. Kedem, 1993, “A Convex Polygon Among Polygonal Obstacles: Placement and High-Clearance Motion,” Comput. Geom. Theory Appls. 3(2):59–89.Google Scholar
  15. 15.
    Dudani S.A., Breeding K.J., and McGhee R.B., 1977. “Aircraft identification by moments invariants,” IEEE Transactions on Computations, bf C-26(1): 39–46.Google Scholar
  16. 16.
    Fischler, M.A. and Bolles, R.C., 1981. “Random sample consensus: a paradigm for model fitting with application to image analysis and automated cartography,” Com. of the A.C.M. 24(6): 381–395.Google Scholar
  17. 17.
    Hohmeyer, M. and Teller, S., 1991. “Stabbing Isothetic Boxes and Rectangles in O(n log n) Time,” UC Berkeley TR 91/634.Google Scholar
  18. 18.
    Horaud, R., 1987, “New Methods for Matching 3-D Objects with Single Perspective Views,” IEEE Trans. Pattern Anal. Machine Intell., 9(3): 401–412.Google Scholar
  19. 19.
    Hu M.K., 1962. “Visual pattern recognition by moment invariants,” IRE Transactions on Information Theory, IT-8: 169–187.Google Scholar
  20. 20.
    D. Huttenlocher, K. Kedem, and J. Kleinberg, 1992, “On Dynamic Voronoi Diagrams and the Minimum Hausdorff Distance for Point Sets Under Euclidean Motion in the Plane,” Proc. of the Eighth ACM Symposium on Computational Geometry.Google Scholar
  21. 21.
    Huttenlocher, D.P., and Ullman, S., 1990 “Recognizing Solid Objects by Alignment with an Image,” Int. J. Computer Vision, 5(2): 195–212.CrossRefGoogle Scholar
  22. 22.
    D. Jacobs and R. Basri, 1996, “3-D Recognition with Regions,” Forthcoming Tech. Report.Google Scholar
  23. 23.
    Marr, D. and Nishihara, H.K., 1978. “Representation and recognition of the spatial organization of three-dimensional shapes,” Proc. of the Royal Society, London, B200: 269–294.Google Scholar
  24. 24.
    Megiddo, N., 1996. “Finding a Line of Sight Thru Boxes in d-Space in Linear Time,” IBM Technical Report.Google Scholar
  25. 25.
    O. Menadeva, “The robustness to Occlusions in Recognizing Planar Objects with Regions,” The Weizmann Inst. of Science, Forthcoming M.Sc. Thesis.Google Scholar
  26. 26.
    Pentland, A., 1987, “Recognition by Parts,” Proc. of the First Int. Conf. on Computer Vision: 612–620.Google Scholar
  27. 27.
    Persoon E. and Fu K.S., 1977. “Shape descimination using Fourier descriptors,” IEEE Transactions on Systems, Man and Cybernetics 7: 534–541.Google Scholar
  28. 28.
    Reeves A.P., Prokop R.J., Andrews S.E., and Kuhl F.P., 1984. “Three-dimensional shape analysis using moments and Fourier descriptors,” Proc. of Int. Conf. on Pattern Recognition: 447–450.Google Scholar
  29. 29.
    Richard C.W. and Hemami H., 1974. “Identification of three dimensional objects using Fourier descriptors of the boundry curve,” IEEE Transactions on Systems, Man and Cybernetics, 4(4): 371–378.Google Scholar
  30. 30.
    Ruckledge, W., 1995. “Locating Objects Using the Hausdorff Distance,” Fifth Int. Conf. on Comp. Vis:457–464.Google Scholar
  31. 31.
    Sadjadi F.A. and Hall E.L., 1980. “Three-dimensional moment invariants,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2(2): 127–136.Google Scholar
  32. 32.
    M. Sharir and S. Toledo, 1994, “Extremal Polygon Containment Problems,” Comput. Geom. Theory Appls. 4:99–118.Google Scholar
  33. 33.
    Ullman, S. and Basri, R., 1991. “Recognition by linear combinations of models,” IEEE Trans. on PAMI, 13(10): 992–1006.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Ronen Basri
    • 1
  • David Jacobs
    • 2
  1. 1.Dept. of Applied Math.The Weizmann Inst. of ScienceRehovotIsrael
  2. 2.NEC Research InstitutePrincetonUSA

Personalised recommendations