International Journal of Computer Vision

, Volume 9, Issue 2, pp 83–112 | Cite as

Surface shape from the deformation of apparent contours

  • Roberto Cipolla
  • Andrew Blake


The spatiotemporal analysis of deforming silhouettes (apparent contours) is here extended using the mathematics of perspective projections and tools from differential geometry. Analysis of the image motion of a silhouette or apparent contour enables computation of local surface curvature along the corresponding contour generator on the surface, assuming viewer motion is known. To perform the analysis, a spatiotemporal parameterization of image-curve motion is needed, but is underconstrained (a manifestation of the well-known aperture problem). It is shown that an epipolar parameterization is most naturally matched to the recovery of surface curvature.

One immediate facility afforded by the analysis is that surface patches can be reconstructed in the vicinity of contour generators. Once surface curvature is known, it is possible to discriminate extremal contours from other fixed curves in space. Furthermore, the known robustness of parallax as a cue to depth extends to the case of surface curvature. Its derivative—rate of parallax—is shown theoretically to be a curvature cue that is robust to uncertainties in the known viewer motion. This robustness has been confirmed in experiments.

Finally, the power of the new analysis for robotics applications is demonstrated. Illustrations are given of an Adept robot, equipped with a CCD camera, circumnavigating curved obstacles. When further equipped with a suction gripper the robot manipulator can pick up an object by its curved surface, under visual guidance.


Surface Curvature Local Surface Robot Manipulator Surface Shape Surface Patch 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    E. Arbogast, Modélisation automatique d'objets non polyédriques par observation monoculaire, Ph.D. thesis, Institut National Polytechnique de Grenoble, 1991.Google Scholar
  2. 2.
    S.T.Barnard and M.A.Fischler, Computational stereo, ACM Computing Surveys 14(4):553–572, 1982.Google Scholar
  3. 3.
    H.G.Barrow and J.M.Tenenbaum, Recovering intrinisic scene characteristics from images. In A.Hanson and E.Riseman, eds., Computer Vision Systems. Academic Press: New York, 1978.Google Scholar
  4. 4.
    H.G.Barrow and J.M.Tenenbaum, Interpreting line drawings as three-dimensional surfaces, Artificial Intelligence 17:75–116, 1981.Google Scholar
  5. 5.
    R.H.Bartels, J.C.Beatty, and B.A.Barsky, An Introduction to Splines for Use in Computer Graphics and Geometric Modeling. Morgan Kaufmann: Los Altos, CA, 1987.Google Scholar
  6. 6.
    L.M.H.Beusmans, D.D.Hoffman, and B.M.Bennett, Description of solid shape and its inference from occluding contours, J. Opt. Soc. Amer. A 4:1155–1167, 1987.Google Scholar
  7. 7.
    A.Blake, J.M.Brady, R.Cipolla, Z.Xie, and A.Zisserman, Visual navigation around curved obstacles, Proc. IEEE Intern. Conf. Robotics Automat. 3:2490–2495, 1991.Google Scholar
  8. 8.
    A.Blake and H.Bulthoff, Shape from specularities: Computation and psychophysics, Phil. Trans. Roy. Soc. London 331:237–252, 1991.Google Scholar
  9. 9.
    A.Blake and R.Cipolla, Robust estimation of surface curvature from deformation of apparent contours. O.Faugeras, ed., Proc. 1st Europ. Conf. Comput. Vis., Antibes, Fr., pp. 465–474, Springer-Verlag: New York, 1990.Google Scholar
  10. 10.
    R.C.Bolles, H.H.Baker, and D.H.Marimont, Epipolar-plane image analysis: An approach to determining structure, Intern. J. Comput. Vis. 1:7–55, 1987.Google Scholar
  11. 11.
    M.Brady, J.Ponce, A.Yuille, and H.Asada, Describing surfaces, Comput. Vis. Graph. Image Process. 32:1–28, 1985.Google Scholar
  12. 12.
    J. Callahan and R. Weiss, A model for describing surface shape, Proc. Conf. Comput. Vis. Patt. Recog., San Francisco, pp. 240–245, 1985.Google Scholar
  13. 13.
    J.F.Canny, A computational approach to edge detection, IEEE Trans. Patt. Anal. Mach. INtell. 8:679–698, 1986.Google Scholar
  14. 14.
    R. Cipolla, Active visual inference of surface shape, Ph.D. thesis, University of Oxford, 1991.Google Scholar
  15. 15.
    R. Cipolla and A. Blake, The dynamic analysis of apparent contours, Proc. 3rd Intern. Conf. Comput. Vis., pp. 616–623, 1990.Google Scholar
  16. 16.
    R.Cipolla and M.Yamamoto, Stereoscopic tracking of bodies in motion, Image Vis. Comput. 8(1):85–90, 1990.Google Scholar
  17. 17.
    R.M. Curwen, A. Blake, and R. Cipolla, Parallel implementation of lagrangian dynamics for real-time snakes, Proc. 2nd British Mach. Vis. Conf., 1991.Google Scholar
  18. 18.
    M.P.DoCarmo, Differential Geometry of Curves and Surfaces, Prentice-Hall: Englewood Cliffs, NJ, 1976.Google Scholar
  19. 19.
    O.D Faugeras and G. Toscani, The calibration problem for stereo, Proc. Conf. Comput. Vis. Patt. Recogn., Miami Beach, pp. 15–20, 1986.Google Scholar
  20. 20.
    I.D. Faux and M.J. Pratt, Computational Geometry for Design and Manufacture, Ellis-Horwood, 1979.Google Scholar
  21. 21.
    S. Ganapathy, Decomposition of transformation matrices for robot vision, Proc. IEEE Conf. Robotics, pp. 130–139, 1984.Google Scholar
  22. 22.
    P.J.Giblin and M.G.Soares, On the geometry of a surface and its singular profiles, Image Vis. Comput. 6(4):225–234, 1988.Google Scholar
  23. 23.
    P.J. Giblin and R. Weiss, Reconstruction of surfaces from profiles, Proc. 1st Intern. Conf. Comput. Vis., London, pp. 136–144, 1987.Google Scholar
  24. 24.
    C.G. Harris, Determination of ego-motion from matched points, 3rd Alvey Vis. Conf., pp. 189–192, 1987.Google Scholar
  25. 25.
    H.vonHelmholtz, Treatise on Physiological Optics, Dover: New York, 1925.Google Scholar
  26. 26.
    B.K.P.Horn, Robot Vision. McGraw-Hill, NY, 1986.Google Scholar
  27. 27.
    B.K.P.Horn, Closed-form solution of absolute orientation using unit quaternions. J. Opt. Soc. Amer. A4(4):629–642, 1987.Google Scholar
  28. 28.
    M. Kass, A. Witkin, and D. Terzopoulos, Snakes: active contour models, Proc. 1st Intern. Conf. Comput. Vis., London, pp. 259–268, 1987.Google Scholar
  29. 29.
    J.J.Koenderink, What does the occluding contour tell us about solid shape? Perception 13:321–330, 1984.Google Scholar
  30. 30.
    J.J.Koenderink, Optic flow, Vision Research 26(1):161–179, 1986.Google Scholar
  31. 31.
    J.J.Koenderink, Solid Shape, MIT Press: Cambridge, MA, 1990.Google Scholar
  32. 32.
    J.J.Koenderink and A.J.VanDoorn, Invariant properties of the motion parallax field due to the movement of rigid bodies relative to an observer, Optica Acta 22(9):773–791, 1975.Google Scholar
  33. 33.
    J.J.Koenderink and A.J.VanDoorn, The singularities of the visual mapping, Biological Cybernetics 24:51–59, 1976.Google Scholar
  34. 34.
    J.J.Koenderink and A.J.VanDoorn, The shape of smooth objects and the way contours end, Perception 11:129–137, 1982.Google Scholar
  35. 35.
    M.M.Lipschutz, Differential Geometry, McGraw-Hill: New York, 1969.Google Scholar
  36. 36.
    H.C.Longuet-Higgins and K.Pradzny, The interpretation of a moving retinal image, Proc. Roy. Soc. London B208:385–397, 1980.Google Scholar
  37. 37.
    J.Malik, Interpreting line drawings of curved objects, Intern. J. Comput. Vis. 1:73–103, 1987.Google Scholar
  38. 38.
    D.Marr, Analysis of occluding contour, Proc. Roy. Soc. London 197:441–475, 1977Google Scholar
  39. 39.
    S.J.Maybank, The angular velocity associated with the optical flow field arising from motion through a rigid environment, Proc. Roy. Soc. London A401:317–326, 1985.Google Scholar
  40. 40.
    G. Medioni and Y. Yasumoto, Corner detection and curve representation using curve b-splines, Proc. Conf. Comput. Vis. Patt. Recog., Miami Beach, pp. 764–769, 1986.Google Scholar
  41. 41.
    S. Menet, P. Saint-Marc, and G. Medioni, B-snakes: implementation and application to stereo, Proc. DARPA, pp. 720–726, 1990.Google Scholar
  42. 42.
    R.S.Millman and G.D.Parker, Elements of Differential Geometry, Prentice-Hall: Englewood Cliffs, NJ, 1977.Google Scholar
  43. 43.
    B.O'Neill, Elementary Differential Geometry, Academic Press: San Diego, CA, 1966.Google Scholar
  44. 44.
    C.R.Rao, Linear Statistical Inference and Its Applications, Wiley: New York, 1973.Google Scholar
  45. 45.
    J.H.Rieger and D.L.Lawton, Processing differential image motion, J. Opt. Soc. Amer. A2(2):354–360, 1985.Google Scholar
  46. 46.
    G. Scott, The alternative snake—and other animals, Proc. 3rd Alvey Vis. Conf., pp. 341–347, 1987.Google Scholar
  47. 47.
    R.Y.Tsai, A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf tv cameras and lenses. IEEE J. Robot. Automat. RA-3(4):323–344, 1987.Google Scholar
  48. 48.
    R.Y.Tsai and T.S.Huang, Uniqueness and estimation of three-dimensional motion parameters of a rigid object with curved surfaces, IEEE Trans. Patt. Anal. Mach. Intell. 6(1):13–26, 1984.Google Scholar
  49. 49.
    R.Y. Tsai and R.K. Lenz, A new technique for fully autonomous and efficient 3D robotics hand-eye calibration, 4th Intern. Symp. Robotics Res., Santa Cruz, CA, pp. 287–297, 1987.Google Scholar
  50. 50.
    R.Y.Tsai and R.K.Lenz, Techniques for calibration of the scale factor and image center for high accuracy 3D machine vision metrology, IEEE Trans. Patt. Anal. Mach. Intell. 10(5):713–720, 1988.Google Scholar
  51. 51.
    R. Vaillant and O.D. Faugeras, Using occluding contours for recovering shape properties of objects. (Submitted to Trans. PAMI), 1992.Google Scholar
  52. 52.
    D.Weinshall, Qualitative depth from stereo, with applications, Comput. Vis. Graph. Image Process. 49:222–241, 1990.Google Scholar
  53. 53.
    M.Yamamoto, Motion analysis using the visualized locus method, Trans. Inform. Process. Soc. Japan 22(5):442–449, 1981 (in Japanese).Google Scholar

Copyright information

© Kluwer Academic Publishers 1992

Authors and Affiliations

  • Roberto Cipolla
    • 1
  • Andrew Blake
    • 2
  1. 1.Department of EngineeringUniversity of CambridgeCambridgeEngland
  2. 2.Department of Engineering ScienceUniversity of OxfordOxfordEngland

Personalised recommendations