Skip to main content
Springer Nature Link
Log in

Automatic extraction of deformable part models

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

I deseribe a system that first segments an image into parts, and then fits deformable models to range data associated with the image. Models are represented by using modal dynamics applied to volumetric primitives, which significantly improves the computational complexity of both model recovery and subsequent processing. The segmentation procedure uses two simple mechanisms: a filtering operation to produce a large set of potential object parts, followed by a quadratic integer optimization that searches among these part hypotheses to produce a maximum-likelihood estimate of the image's part structure. Once a segmentation has been produced, a volumetric description is obtained by a fitting procedure that minimizes squared error between the range measurements an the model's visible surface. For simple part shapes, it is possible to compute the deformable model's parameters using only the shape of its symmetry axes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. T.O. Binford, “Visual perception by computer,” Proc. IEEE Conf. Systems and Control, Miami, December, 1971.

  2. G.J. Agin and T.O. Binford, “Computer descriptions of curved objects,” IEEE Tran. PAMI C 25 (4):439–449, 1976

    Google Scholar 

  3. R. Nevatia and T.O. Binford, “Description and recognition of curved objects,” Artificial Intelligence 8 (1):77–98, 1977.

    Google Scholar 

  4. D. Marr and K. Nishihara, “Representation and recognition of the spatial organization of three-dimensional shapes,” Proc. Roy. Soc.—London B, 200:269–294, 1978.

    Google Scholar 

  5. D. Ballard, “Reference frames for active vision,” Proc. Ilth Intern. Joint Conf. Artificial Intelligence, pp. 1635–1641, Detroit, August 20–25, 1989.

  6. I. Beiderman, “Human image understanding: Recent research and a theory,” Comp. Vision, Graphics and Image Process. 32:29–73, 1985.

    Google Scholar 

  7. Jan J. Konderink and Andrea J.van Doorn, “The shape of smooth objects and the way contours end,” Perception 11:129–137, 1982.

    Google Scholar 

  8. Jan J. Konderink and Andrea J.van Doorn, “The internal representation of solid shape with respect to vision,” Biological Cybernetics 32:211–216, 1979.

    Google Scholar 

  9. D. Hoffman and W. Richards, “Parts of recognition.” In From Pixels to Predicates, A. Pentland (ed.), Ablex Publishing: Norwood, N.J., 1985.

    Google Scholar 

  10. M. Leyton, “Perceptual organization as nested control,” Biological Cybernetics 51:141–153, 1984.

    Google Scholar 

  11. D. Terzopolis, A. Witkin, and M. Kass, “Symmetry-seeking models for 3D object reconstruction,” Proc. Ist Intern. Conf. Computer Vision, pp. 269–276, London, 1987.

  12. R. Bajcsy and F. Solina, “Three-dimensional object representation revisited,” Ist Intern. Conf. Computer Vision, London, June 8–11, 1987.

  13. T. Bolt and A. Gross, “Recovery of superquadrics from depth information,” Proc. AAAI Workshop on Spatial Reasoning and Multi-Sensor Fusion, pp. 128–137, October 1987.

  14. A. Pentland, “Perceptual organization and the representation of natural form,” Artificial Intelligence, 28(2):1–38, 1986.

    Google Scholar 

  15. A. Pentland, “Recognition by parts,” Ist Intern. Conf. Computer Vision, London, June 8–11, 1987.

  16. J. Rissanen, “Minimum-length description principle,” Encyclopedia of Statistical Sciences, vol. 5, Wiley: New York, pp. 523–527, 1983.

    Google Scholar 

  17. A. Pentland, “Fractal-based description of natural scenes,” IEEE Trans. PAMI 6(6):661–674, 1984.

    Google Scholar 

  18. M. Gardiner, “The superellipse: A curve that lies between the ellipse and the rectangle, Scientific American, September 1965.

  19. J. Williams, “The theoretical basis of the discrete element method.” In Numerical Methods in Engineering, Theory, and Application, Balkema Publishers: rotterdam, 1987.

    Google Scholar 

  20. A. Pentland and J. Williams, “The perception of non-rigid motion: Interference of material properties and force,” Proc. Intern. Joint Conf. Artificial Intelligence, Detroit, August 20–25, 1989.

  21. A. Pentland and J. Williams, “Good vibrations: Modal dynamics for graphies and animation,” Computer Graphics 23(3):215–222, 1989.

    Google Scholar 

  22. A. Barr, “Global and local deformations of solid primitives,” Computer Graphics 18(3):21–30, 1984.

    Google Scholar 

  23. D'Arcy Thompson, On Growth and Form, 2d ed. University Press: Cambridge, England, 1942.

    Google Scholar 

  24. A. Pentland, “A new sense for depth of field,” IEEE Trans. PAMI 9(4):523–531, 1987.

    Google Scholar 

  25. J.J. Hopfield and D.W. Tank, “neural computation of decisions in optimization problems,” Biological Cybernetics, 52: 141–152, 1985.

    Google Scholar 

  26. P.J. Burt, “Fast algorithms for estimating local image properties,” Comput. Vision, Graphics, and Image Process. 21:368–382. 1983.

    Google Scholar 

  27. A. Pentland and J. Williams, “Virtual Manufacturing,” NSF Engineering Design Res. Conf., Amherst, MA, pp. 301–316, June 11–14, 1989.

  28. M. Bove, “Discrete fourier transform based depth-from-focus,” Proc. Opt. Soc. Am. Conf. Image Understanding and Machine Vision, pp. 115–119, N. Falmouth, MA, June 12–14, 1989.

  29. M. Raibert, Legged Robots that Balance. M.I.T. Press: Cambridge, 1986.

    Google Scholar 

  30. R.A. Hummel and S.W. Zucker, “On the foundations of relaxation labeling processes,” IEEE Trans. PAMI 5(3):267–287, 1983.

    Google Scholar 

  31. J. Tsotsos, “A complexity level for analysis of vision,” Proc. Ist Intern. Conf. Computer Vision, London, pp. 346–355, June 8–11, 1987.

  32. A. Pentland, “Part segmentation for object recognition,” Neural Computation, 1(1):82–91, 1989.

    Google Scholar 

  33. Y.G. Leclerc, “Constructing simple stable descriptions for image partitioning,” Intern. J. Comput. Vision. (1):73–102, 1989.

Download references

Author information

Authors and Affiliations

  1. Vision and Modeling Group, The Media Lab, Massachusetts Institute of Technology, Room E15-387, 20 Ames St., 02139, Cambridge, MA

    Alex P. Pentland

Authors
  1. Alex P. Pentland
    View author publications

    You can also search for this author inPubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Pentland, A.P. Automatic extraction of deformable part models. Int J Comput Vision 4, 107–126 (1990). https://doi.org/10.1007/BF00127812

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00127812

Keywords