Toward a Surface Primal Sketch

  • Jean Ponce
  • Michael Brady
Part of the The Kluwer International Series in Engineering and Computer Science book series (SECS, volume 21)


This paper reports progress toward the development of a representation of significant surface changes in dense depth maps. We call the representation the Surface Primal Sketch by analogy with representations of intensity changes, image structure, and changes in curvature of planar curves. We describe an implemented program that detects, localizes, and symbolically describes: steps, where the surface height function is discontinuous; roofs, where the surface is continuous but the surface normal is discontinuous; smooth joins, where the surface normal is continuous but a principal curvature is discontinuous and changes sign; and shoulders, which consist of two roofs and correspond to a step viewed obliquely. We illustrate the performance of the program on range maps of objects of varying complexity.


Principal Curvature Coarse Scale Surface Intersection Umbilic Point Parabolic Point 
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]
    Asada, Haruo and Brady, Michael., The curvature primal sketch. Technical Report AIM-758, MIT, Artificial Intelligence Lab, 1984.Google Scholar
  2. [2]
    Binford, Thomas O., Inferring surfaces from images. Artificial Intelligence 17: 205–244, 1981.CrossRefGoogle Scholar
  3. [3]
    Brady, M., Ponce, J., Yuille, A. and Asada, H., Describing surfaces. In Proc. Seond Int. Symp. on Robotics Research, pages 434–445. Kyoto, Japan, 1984.Google Scholar
  4. [4]
    Brou, P., Finding the orientation of objects in vector maps. Int. J. Rob. Res. 3 (4): 89–175, 1984.CrossRefGoogle Scholar
  5. [5]
    Burt, Peter J. Fast filter transforms for image processing. Comp. Graph. and Im. Proc. 16: 20–51, 1981.CrossRefGoogle Scholar
  6. [6]
    Burt, Peter J., Fast algorithms for estimating local image properties. Comp. Graph, and Im. Proc. 21: 368–382, 1983.CrossRefGoogle Scholar
  7. [7]
    Canny, J. F., Finding edges and lines in images. Technical Report TR-720, MIT, Artificial Intelligence Lab, 1983.Google Scholar
  8. [8]
    Faugeras, O.D., et. al., Towards a flexible vision system. In A. Pugh (editor), Robot Vision. IPS, UK, 1982.Google Scholar
  9. [9]
    Faugeras, O. D., New steps toward a flexible 3-D vision system for robotics. Preprints of the Second International Symposium of Robotics Research. Note: also see In Proc. 7th Int. Conf. Pattern Recogn., pages 796-805; Montreal, Canada, July: 222 – 230, 1984.Google Scholar
  10. [10]
    Faugeras O.D., Hebert, M., A 3-D recognition and positioning algorithm using geometrical matching between primitive surfaces. In Proc. Eighth Int. Joint Conf. On Artificial Intelligence, pages 996–1002. Los Altos: William Kaufmann, August, 1983.Google Scholar
  11. [11]
    Faugeras, O. D. and Hebert, M., The representation, recognitin, and positioning of 3-D shapes from range data. to appear in the Int. Journal of Robotics Research, 1985.Google Scholar
  12. [12]
    Faugeras, O. D., Hebert, M., Pauchon, E., and Ponce, J. Object representation, identification, and positioning from range data. First International Symposium on Robotics Research. MIT Press, 1984, pages 425–446.Google Scholar
  13. [13]
    Grimson, W. E., Computational experiments with a feature based stereo algorithm. Technical Report 762, MIT, Artificial Intelligence Lab, 1984.Google Scholar
  14. [14]
    Haralick, Robert M., Watson, Layne T., Laffey, Thomas J. The topographic primal sketch. Int. J. Rob. Res. 2 (l): 50–72, 1983.CrossRefGoogle Scholar
  15. [15]
    Horn, B. K. P. Understanding image intensities. Artif. Intell. 8, 1977.Google Scholar
  16. [16]
    Huffman, D. A., Impossible objects as nonsense sentences. Machine Intelligence 6. Edinburgh University Press, Edinburgh, 1971, pages 295–323.Google Scholar
  17. [17]
    Ikeuchi, K., Horn, B. K. P., et al. Picking up an object from a pile of objects. First International Symposium on Robotics Research. MIT Press, 1984, pages 139–162.Google Scholar
  18. [18]
    Jacobsen, S. C., Wood, J. E., Knutti, D. F., and Biggers, K. B. The Utah/MIT dextrous hand: work in progress. Int. J. Rob. Res. 3 (4), 1984.Google Scholar
  19. [19]
    Jacobsen, S. C., Wood, J. E., Knutti, D. F., Biggers, K. B., and Iversen, E. K., The verstion I UTAH/MIT dextrous hand. Proc. of the 2nd International Symposium on Robotics Research. MIT Press, Cambridge, 1985.Google Scholar
  20. [20]
    Kapur, D., Mundy, J. L., Musser, D., and Narendran, P. Reasoning about three-dimensional space. In IEEE Int. Conf. on Robotics, pages 405–410. St. Louis, MO, March, 1985.Google Scholar
  21. [21]
    Little, J. J., Recovering shape and determining attitude from extended Gaussian images. Technical Report, Univ. of British Columbia, Dept. of CS, 1985.Google Scholar
  22. [22]
    Marr, D., Early processing of visual information. Phil. Trans. Roy. Soc. B275: 843–524, 1976.Google Scholar
  23. [23]
    Marr, D. and Hildreth, E. C., Theory of edge detection. Proc. R. Soc. London B 207: 187–217, 1980.Google Scholar
  24. [24]
    Richter, J. and Ullman, S., A model for the spatio-temporal organisation of X and Y type ganglion cells in the primate retina. Biol. Cyb. 43: 127–145, 1982.CrossRefGoogle Scholar
  25. [25]
    Salisbury, J. Kenneth and Craig, John J. Articulated hands: force control and kinematic issues. Int. J. Rob. Res. 1 (1): 4–17, 1982.CrossRefGoogle Scholar
  26. [26]
    Terzopoulos, D., The role of constraints and discontinuities in visible-surface reconstruction. Proc. 7th Int. Jt. Conf. Artif. Intell., Karlsruehe: 1073–1077, 1983.Google Scholar
  27. [27]
    Turner, K., Computer perception of curved objects using a television camera. Technical Report, Edinburgh University, 1974.Google Scholar
  28. [28]
    Witkin, A., Scale-space filtering. In 7th Int. Jt. Conf. Artificial Intelligence, pages 1019–1021. Karlsruhe, 1983.Google Scholar
  29. [29]
    Yuille, A. L., Zero-crossings on lines of curvature. In Proc. Conf. Amer. Assoc. Artif. Intell.. Washington, August, 1983.Google Scholar
  30. [30]
    Yuille, A. L. and Poggio, T., Fingerprints theorems for zero-crossings. Technical Report AIM-730, MIT, AI Lab, 1983.Google Scholar
  31. [31]
    Yuille, A. L. and Poggio, T., Scaling theorems for zero crossings. Technical Report AIM-722, MIT, AI Lab, 1983.Google Scholar

Copyright information

© Kluwer Academic Publishers 1987

Authors and Affiliations

  • Jean Ponce
    • 1
  • Michael Brady
    • 1
  1. 1.Artificial Intelligence LaboratoryMassachusetts Institute of TechnologyCambridgeUSA

Personalised recommendations