Skip to main content
SpringerLink
Log in

From image sequences to recognized moving polyhedral objects

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

Abstract

This paper describes the combination of several novel algorithms into a system that obtains visual motion from a sequence of images and uses it to recover a three-dimensional description of the motion and geometry of the scene in terms of moving extended straight edges. The system goes on to recognize the recovered geometry as an object from a database of wireframe models, a stage that also resolves the depth/speed scaling ambiguity inherent in visual motion processing, resulting in absolute depth and motion recovery. The processing sequence is demonstrated on imagery from a well-carpentered CSG model and on natural imagery of simple polyhedral objects.

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

Access this article

Log in via an institution

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

References

  1. H. von Helmholtz, in Handbuch der physiologischen Optik. Voss, Leipzig, 1866: Ed. and trans. by J.P.C. Southall, Dover, New York, 1962.

    Google Scholar 

  2. H. Wallach and D.N. O'Connell, “The kinetic depth effect”, J. Exp. Psychol. 45:205–217, 1953.

    Google Scholar 

  3. G. Johansson, “Visual perception of biological motion and a model for its analysis”, Percep. Psychophy. 14:201–211, 1973.

    Google Scholar 

  4. D.R. Proffitt and B.I. Bertenthal, “Converging approaches to extracting structure from motion: psychophysical and computational investigations of recovering connectivity from moving point-light displays”. in Proc. 1st Conf. on Artif. Intell. Applications, Denver, December 1984, pp. 232–238 (IEEE Computer Society Press, Silver Spring, MD, 1984).

    Google Scholar 

  5. B.G. Schunck, “The image flow constraint equation”, Compu. Vis., Graph. Image Process. 35, pp. 20–46, 1986.

    Google Scholar 

  6. A. Verri and T. Poggio, “Against quantitative optical flow”, Proc. 1st Intern. Conf. Computer Vision, London, June 1987, pp. 171–180 (IEEE Computer Society Press, Washington, D.C.).

  7. B.K.P. Horn and B.G. Schunck, “Determining optical flow”, Artificial Intelligence 17:185–203, 1981.

    Google Scholar 

  8. B.F. Buxton and H. Buxton, “Monocular depth perception from optical flow by space-time signal processing”, Proc. Roy. Soc. London B 218:22–47, 1983.

    Google Scholar 

  9. D.J. Heeger, “Optical flow from spatiotemporal filters”, Proc. 1st Intern. Conf. Computer Vision, London, 1987, pp. 181–190 (IEEE Computer Society Press, Washington, D.C., 1987).

    Google Scholar 

  10. R.Y. Tsai and T.S. Huang, “Estimating 3D motion parameters of a rigid planar patch”, Report R-921, Coord. Sci. Lab. University of Illinois, 1981.

  11. H.C. Longuet-Higgins, “The visual ambiguity of a moving plane,” Proc. R.Y. Soc. London B 223:165–175, 1984.

    Google Scholar 

  12. B.F. Buxton, H. Buxton, D.W. Murray, and N.S. Williams, “3D solutions to the aperture problem,” Proc. 6th European Conf. on Artificial Intelligence, Pisa, 1984, ed. T. O'Shea, pp. 631–640 (Elsevier, Amsterdam, 1984).

    Google Scholar 

  13. R.Y. Tsai and T.S. Huang, “Uniqueness and estimation of threedimensional motion parameters of rigid objects with curved surfaces,” IEEE Trans. PAMI 6:13–27, 1984.

    Google Scholar 

  14. A.M. Waxman and K. Wohn, “Contour evolution, neighborhood deformation and global image flow: planar surfaces in motion,” Intern. J. Robotics Res. 4:95–108, 1985.

    Google Scholar 

  15. A.M. Waxman, B. Kamgar-Parsi, and M. Subbarao, “Closed-form solutions to image flow equations for 3D structure and motion,” Intern. J. Computer Vision 1:239–258, 1987.

    Google Scholar 

  16. H. Westphal and H-H. Nagel, “Towards the derivation of threedimensional descriptions of image sequences for nonconvex moving objects,” comput. Vision, Graphics Image Process. 34:302–320, 1986.

    Google Scholar 

  17. C.G. Harris, M.C. Ibison, E.P. Sparkes, and M. Stephens, “Structure and motion from optical flow,” Proc. Alvey Vision Conf. Bristol UK, September 1986. To be published in Image and Vision Computing.

  18. G.L. Scott, “Four-line method of locally estimating optic flow,” Image and Vision Computing 5:67–72, 1987.

    Google Scholar 

  19. W.E.L. Grimson and T. Lozano-Perez, “Model-based recognition and localization from sparse range or tactile data,” Intern. J. Robotics Res. 3:3–35, 1984.

    Google Scholar 

  20. W.E.L. Grimson and T. Lozano-Pérez, “Search and sensing strategies for recognition and localization of two and three dimensional objects,” Proc. 3rd Intern. Symp. Robotics Res. Gouvieux, France, October 1985, pp. 81–88, 1985.

  21. D.W. Murray and D.B. Cook, “Using the orientation of fragmentary 3d edge segments for polyhedral object recognition,” Intern. J. Comput. Vision 2:147–163, 1988.

    Google Scholar 

  22. D.A. Castelow and D.W. Murray, “Computing visual motion by matching edges,” Preprint, 1988.

  23. S. Ullman, The Interpretation of Visual Motion, MIT Press, Cambridge, MA 1979.

    Google Scholar 

  24. S. Ullman and E.C. Hildreth, “The measurement of visual motion,” in Physical and Biological Processing of Images, ed. O.J. Braddick and A.C. Sleigh, Springer-Verlag, Berlin, 1983.

    Google Scholar 

  25. D.H. Ballard and C.M. Brown, in Computer Vision, Prentice-Hall, NJ, 1982.

    Google Scholar 

  26. J.F. Canny, “Finding edges and lines in images,” AI-TR No. 720, Artificial Intelligence Laboratory, MIT, Cambridge, MA, 1983.

    Google Scholar 

  27. A. Rosenfeld and A.C. Kak, in Digital Picture Processing, vol. 2, Academic Press, New York, 1982.

    Google Scholar 

  28. P. Burt and B. Julesz, “Modifications of the classical notion of Panum's fusion area,” Perception 9:671–682, 1980.

    Google Scholar 

  29. S.B. Pollard, J.E.W. Mayhew, and J.P. Frisby, “PMF: a stereo correspondence algorithm using a disparity gradient limit,” Perception 14: 449–470, 1985.

    Google Scholar 

  30. S.A. Lloyd, “A binocular stero algorithm based on the disparity-gradient limit and using optimization theory,” Image and Vision Computing 3:177–181, 1985.

    Google Scholar 

  31. C.L. Fennema and W.B. Thompson, “Velocity determination in scenes containing several moving objects,” Comput. Graphics Image Process. 9:301–315, 1979.

    Google Scholar 

  32. B. Neumann. “Motion analysis of image sequences for object grouping and reconstruction,” Proc. Pattern Recog. Conf., Miami, FL, 1980.

  33. A. Spoerri and S. Ullman, “The early detection of motion boundaries,” Proc. 1st Intern. Conf. Computer Vision, London, June 1987, pp. 209–218 (IEEE Computer Society Press, Washington, D.C., 1987).

    Google Scholar 

  34. W.B. Thompson and T-C. Pong, “Detecting moving objects,” Proc. 1st Intern. Conf. Computer Vision, London, June 1987, pp. 201–208 (IEEE Computer Society Press, Washington, D.C., 1987).

    Google Scholar 

  35. G. Adiv, “Determining 3-D motion and structure from optical flow generated by several moving objects,” IEEE Trans. PAMI 7:384–401, 1985.

    Google Scholar 

  36. D.W. Murray and B.F. Buxton, “Scene segmentation from visual motion using global optimization,” IEEE Trans. PAMI 9:220–228, 1987.

    Google Scholar 

  37. R.M. Haralick, “Computer vision theory: the lack thereof,” Comput. Vision, Graphics and Image Process. 36: 372–386, 1986.

    Google Scholar 

  38. J.B. Burns, A.R. Hanson, and E.M. Riseman, “Extracting straight lines,” IEEE Trans. PAMI 8:425–455, 1986.

    Google Scholar 

  39. A. Blake, A. Zisserman, and A.V. Papoulias, “Weak continuity constraints generate uniform scale-space descriptions of plane curves,” Proc. 7th European Conf. on Artificial Intelligence, July 1986, Brighton, UK, pp. 518–528.

  40. U. Ramer, “Extraction of lines structures from photographs of curved objects,” Comput. Graphics and Image Process. 4:81–103, 1975.

    Google Scholar 

  41. H. Asada and J.M. Brady, “The curvature primal sketch,” Proc. Workshop on Computer Vision: Representation and Control, Annapolis, MD, (April 1984), pp. 8–17 (IEEE Computer Society Press, Silver Spring, MD, 1984).

    Google Scholar 

  42. Y. Yasumoto and G. Medioni, “Experiments in estimation of 3-d motion parameters from a sequence of image frames,” Proc. IEEE Conf. on Comput. Vision and Pattern Recog., San Francisco, pp. 89–94, 1985.

  43. D.W. Marquardt, “An algorithm for the least-squares estimation of non-linear parameters,” J. Soc. Ind. Appl. Math. 11 (2): 431–441, 1963.

    Google Scholar 

  44. S.B. Pollard, J. Porrill, J.E.W. Mayhew, and J.P. Frisby, “Matching geometrical descriptions in three-space,” Image and Vision Computing 5:73–78, 1987.

    Google Scholar 

  45. R.C. Bolles, R. Horaud, and M.J. Hannah, “3-DPO: a three dimensional part orientation system,” Proc. 8th Intern. Joint Conf. Artificial Intelligence, Karlsruhe, FRG, pp. 1116–1120, 1983.

  46. O.D. Faugeras and M. Hébert, “A 3D recognition and positioning algorithm using geometric matching between primitive surfaces,” Proc. Intern. Joint Conf. on Artificial Intelligence, Karlsruhe, pp. 996–1002, 1983.

  47. B.D.P. Ruff, “Hardware implementation of the Canny edge detector,” in Workshop on Parallelism and Computer Vision, Oxford, March 1987. To be published (Oxford University Press).

  48. J.M. Brady, “Seeds of perception,” Proc. 3rd Alvey Vision Conference, Cambridge, UK, September 1987, pp. 259–265.

Download references

Author information

Authors and Affiliations

  1. Department of Engineering Science, University of Oxford, Parks Road, OX1 3PJ, Oxford, UK

    David W. Murray, David A. Castelow & Bernard F. Buxton

Authors
  1. David W. Murray
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. David A. Castelow
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bernard F. Buxton
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Murray, D.W., Castelow, D.A. & Buxton, B.F. From image sequences to recognized moving polyhedral objects. Int J Comput Vision 3, 181–208 (1989). https://doi.org/10.1007/BF00133031

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00133031

Keywords

Search

Navigation