Advertisement

Distinctive representations for the recognition of curved surfaces using outlines and markings

  • David Forsyth
  • Andrew Zisserman
  • Jitendra Malik
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 994)

Abstract

Recognising 3D objects from single images presents a range of significant problems, mostly to do with the nature and distinctiveness of the representations that can be recovered. In such special cases as polyhedra, surfaces of revolution, general cones, canal surfaces and algebraic surfaces, the geometry can be recovered with varying degrees of success and of ambiguity. We discuss these volumetric primitives, comparing their utility to that of surface primitives.

For a model based recognition system, representation is not simply concerned with particular geometric primitives, but the entire recognition process. In our view, representations should be motivated by the way quantities that are measurable in an image influence decisions throughout the recognition process.

When some geometric information is available, its potential distinctiveness can often be substantially enhanced by constructing representations that capture surface markings in an appropriate frame on the surface itself.

Keywords

Object Recognition Computer Vision Invariant Theory Surface Representation Surface Markings 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Asada, H. and Brady, M., “The curvature primal sketch,” PAMI-8, 1, 2–14, 1986.Google Scholar
  2. 2.
    Binford, T.O. “Inferring Surfaces from Images,” Artificial Intelligence, Vol. 17, p.205–244, 1981.Google Scholar
  3. 3.
    Binford, T.O., “Survey of model-based image analysis systems,” IJRR, 1, 1, 18–63, 1982.Google Scholar
  4. 4.
    Burns, J., Weiss, R. and Riseman, E., “View variation of point set and line segment features,” Proc DARPA IU workshop, 1990.Google Scholar
  5. 5.
    Clemens, D.T. and Jacobs, D.W. “Model Group Indexing for Recognition,” Proceedings CVPR, p.4–9, 1991, and PAMI-13, No. 10, p.1007–1017, October 1991.Google Scholar
  6. 6.
    Forsyth, D.A., “Recognising algebraic surfaces by their outlines,” Int. J. Computer Vision, in press.Google Scholar
  7. 7.
    Forsyth, D.A., Mundy, J.L., Zisserman, A., Heller, A., Coehlo, C. and Rothwell, C.A., “Invariant Descriptors for 3D Recognition and Pose,” IEEE Trans. Patt. Anal. and Mach. Intelligence, 13, 10, 1991.Google Scholar
  8. 8.
    Forsyth, D.A., and Zisserman, A., “Reflections on Shading,” Special Issue of I.E.E.E. Pattern Analysis and Machine Intelligence on physical modelling in computer vision, July, 13, 7, 671–679, 1991.Google Scholar
  9. 9.
    Forsyth, D.A., Mundy, J.L., Zisserman, A. and Rothwell, C.A., “Recognising rotationally symmetric surfaces from their outlines,” Proc. Second European Conference on Computer Vision, G. Sandini (ed.), Springer LNCS-x, 1992.Google Scholar
  10. 10.
    Forsyth, D.A., Mundy, J.L., Zisserman, A. and Rothwell, C.A., “Using global consistency to recognise Euclidean objects with an uncalibrated camera,” Proc. CVPR-94, 1994.Google Scholar
  11. 11.
    Forsyth, D.A. and Rothwell, C.A., “Representations of 3D objects that incorporate surface markings,” in Applications of invariance in computer vision, J.L. Mundy, A. Zisserman and D.A.Forsyth, (ed.s), Springer LNCS 825, 1994.Google Scholar
  12. 12.
    Fukunaga, K. (1990) Introduction to Statistical Pattern Recognition 2nd Edition, London: Academic Press.Google Scholar
  13. 13.
    Garding, J. and T. Lindeberg, “Direct computation of shape cues by multi-scale retinotopic processing,” Int. J. Computer Vision, to appearGoogle Scholar
  14. 14.
    Gigus, Z. and Malik, J., “Computing the aspect graph for line drawings of polyhedral objects,” PAMI-12, 2, 113–122, 1990.Google Scholar
  15. 15.
    Grimson, W.E.L. and Lozano-Pérez, T. “Localizing Overlapping Parts by Searching the Interpretation Tree,” PAMI-9, No. 4, p.469–482, July 1987.Google Scholar
  16. 16.
    Huttenlocher, D.P. and Ullman, S. “Object Recognition Using Alignment,” Proceedings ICCVl, p.102–111, 1987.Google Scholar
  17. 17.
    Huttenlocher, D.P. and Ullman, S. “Recognizing Solid Objects by Alignment.” IJCV-5, No. 2, p.255–274, 1990.Google Scholar
  18. 18.
    Lamdan, Y., Schwartz, J.T. and Wolfson, H.J. “Object Recognition by Affine Invariant Matching,” Proceedings CVPR, p.335–344, 1988.Google Scholar
  19. 19.
    J. Liu, J.L. Mundy, D.A. Forsyth, A.P. Zisserman and C.A. Rothwell, “Efficient Recognition of rotationally symmetric surfaces and straight homogeneous generalized cylinders,” IEEE conference on Computer Vision and Pattern Recognition '93, 1993.Google Scholar
  20. 20.
    Malik, J. and Perona, P., “Preattentive texture discrimination with early vision mechanisms,” Journal of Optical Society of America, A 7 (2), May 1990, pp. 923–932.Google Scholar
  21. 21.
    Malik, J. and Rosenholtz, R., “Recovering surface curvature and orientation from texture distortion; a least squares algorithm and analysis,” Proc. ECCV-94, Springer Lecture Notes in Computer Science 801, 1994.Google Scholar
  22. 22.
    Moses, Y. and Ullman, S. “Limitations of Non Model-Based Recognition Systems,” Proc. ECCV, LNCS 588, Springer-Verlag, p.820–828, 1992.Google Scholar
  23. 23.
    Mundy, J.L. and Zisserman, A., “Introduction,” in J.L. Mundy and A.P. Zisserman (ed.s) Geometric Invariance in Computer Vision, MIT Press, 1992.Google Scholar
  24. 24.
    Mundy, J.L. and Zisserman, A., “Repeated structures: image correspondence constraints and 3D structure recovery,” in Applications of invariance in computer vision, J.L. Mundy, A. Zisserman and D.A.Forsyth, (ed.s), Springer LNCS 825, 1994.Google Scholar
  25. 25.
    Nayar, S.K. and Bolle, R., “Reflectance Ratio: a photometric invariant for object recognition,” Proc. ICCV-4, Berlin, 1993.Google Scholar
  26. 26.
    Pillow, N., Utcke, S. and Zisserman, A., ‘Viewpoint-Invariant Representation of Generalized Cylinders Using the Symmetry Set', To appear, Image and Vision Computing.Google Scholar
  27. 27.
    Ponce, J. and Kriegman, D.J., “Toward 3D curved object recognition from image contours,” in J.L. Mundy and A.P. Zisserman (ed.s) Geometric Invariance in Computer Vision, MIT Press, 1992.Google Scholar
  28. 28.
    Rothwell, C.A., Zisserman, A.P., Forsyth, D.A. and Mundy, J.L., “Using Projective Invariants for constant time library indexing in model based vision,” Proc. British Machine Vision Conference, 1991.Google Scholar
  29. 29.
    Rothwell, C.A., Zisserman, A.P, Forsyth, D.A. and Mundy, J.L., “Fast recognition using algebraic invariants,” in J.L. Mundy and A.P. Zisserman (ed.s) Geometric Invariance in Computer Vision, MIT Press, 1992.Google Scholar
  30. 30.
    Rothwell, C.A., Forsyth, D.A., Zisserman, A. and Mundy, J.L., “Extracting projective structure from single perspective views of 3D point sets,” International Conference on Computer Vision, Berlin, 573–582, 1993.Google Scholar
  31. 31.
    Stein, F. and Medioni, G., “Structural indexing: efficient 3D object recognition,” PAMI-14, 125–145, 1992.Google Scholar
  32. 32.
    Sugihara, K., Machine interpretation of line drawings, MIT Press, 1986.Google Scholar
  33. 33.
    Swain, M.J. and Ballard, D.H., “Color Indexing,” Int. J. Computer Vision, 7, 1, 11–32, 1991.Google Scholar
  34. 34.
    Taubin, G. and Cooper, D.B., “Objectrecognition based on moment (or algebraic) invariants,” in J.L. Mundy and A.P. Zisserman (ed.s) Geometric Invariance in Computer Vision, MIT Press, 1992.Google Scholar
  35. 35.
    Thompson, D.W. and Mundy, J.L. “Three-dimensional Model Matching from an Unconstrained Viewpoint,” Proceedings ICRA, p.208–220, April 1987.Google Scholar
  36. 36.
    Utcke, S. and Zisserman, A., ‘Transfer and Invariants of Surfaces of Revolution', OUEL Report, Oxford, 1994.Google Scholar
  37. 37.
    Van Gool, L., Moons, T., Pauwels, E., and Oosterlinck, A., “Semi-differential invariants,” in J.L. Mundy and A.P. Zisserman (ed.s) Geometric Invariance in Computer Vision, MIT Press, 1992.Google Scholar
  38. 38.
    Voorhees, H. and T. Poggio, “Computing texture boundaries from images,” Nature 333, pp. 364–367, 1988PubMedGoogle Scholar
  39. 39.
    Wayner, P.C. “Efficiently Using Invariant Theory for Model-based Matching,” Proceedings CVPR, p.473–478, 1991.Google Scholar
  40. 40.
    Weinshall, D., “Model-based invariants for 3-D vision,” Int. J. Computer Vision, 10, 27–42, 1993.Google Scholar
  41. 41.
    Weiss, I. “Projective Invariants of Shapes,” Proceeding DARPA Image Understanding Workshop, p. 1125–1134, April 1988.Google Scholar
  42. 42.
    Zerroug, M. and Nevatia, R., “Volumetric Descriptions from a Single Intensity Image,” Int. J. Computer Vision, to appear.Google Scholar
  43. 43.
    Zisserman A., Forsyth D., Mundy J., Rothwell C., Liu J. and Pillow N., “3D Object Recognition using Invariance”, Oxford University Engineering Report, OUEL 2027/94, 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • David Forsyth
    • 1
  • Andrew Zisserman
    • 2
  • Jitendra Malik
    • 1
  1. 1.Computer Science DivisionU.C. BerkeleyBerkeleyUSA
  2. 2.Robotics Research GroupOxford UniversityOxfordUK

Personalised recommendations