Visual perception strategies for 3D reconstruction

  • Éric Marchand
  • François Chaumette
Representation and Shape Perception
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1315)


We propose in this paper an active vision approach for performing the 3D reconstruction of static scenes. The perception-action cycles are handled at various levels: from the definition of perception strategies for scene exploration downto the automatic generation of camera motions using visual servoing. To perform the reconstruction we use a structure from controlled motion method which allows a robust estimation of primitive parameters. As this method is based on particular camera motions, perceptual strategies able to appropriately perform a succession of such individual primitive reconstructions are proposed in order to recover the complete spatial structure of complex scenes. Two algorithms are proposed to ensure the exploration of the scene. The former is an incremental reconstruction algorithm based on the use of a prediction/verification scheme managed using decision theory and Bayes Nets. It allows the visual system to get a complete high level description of the observed part of the scene. The latter, based on the computation of new viewpointsC ensures the complete reconstruction of the scene.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    G. Adiv. Inherent ambiguities in recovering 3D motion and structure from a noisy flow field. IEEE Trans. on PAMI, 11(5):477–489, May 1989.Google Scholar
  2. 2.
    Y. Aloimonos. Purposive and qualitative active vision. In ICPR'90, pp. 346–360, Atlantic City, June 1990.Google Scholar
  3. 3.
    Y. Aloimonos, I. Weiss, A. Bandopadhay. Active vision. IJCV, 1(4):333–356, January 1987.CrossRefGoogle Scholar
  4. 4.
    R. Bajcsy. Active perception. Proc. of the IEEE, 76(8):996–1005, August 1988.CrossRefGoogle Scholar
  5. 5.
    D.H. Ballard. Animate vision. Artificial Intelligence, 48(1):57–86, February 1991.CrossRefGoogle Scholar
  6. 6.
    H. Buxton, S. Gong. Visual surveillance in a dynamic and uncertain world. Artificial Intelligence, 78(1–2):431–459, October 1995.CrossRefGoogle Scholar
  7. 7.
    F. Chaumette, S. Boukir, P. Bouthemy, D. Juvin. Structure from controlled motion. IEEE Trans. on PAMI, 18(5):492–504, May 1996.Google Scholar
  8. 8.
    C. Connoly. The determination of next best views. In IEEE Int. Conf. an Robotics and Automation, pp. 432–435, St Louis, March 1985.Google Scholar
  9. 9.
    C.K. Cowan, P.D. Kovesi. Automatic sensor placement from vision task requirements. IEEE Trans. on PAMI, 10(3):407–416, May 1988.Google Scholar
  10. 10.
    D. Djian, P. Probert, and P. Rives. Active sensing using bayes nets. In Proc. of Int. Conf. an Advanced Robotics, ICAR'95, pp. 895–902, Sant Feliu de Guixols, Spain, September 1995.Google Scholar
  11. 11.
    B. Espiau, F. Chaumette, P. Rives. A new approach to visual servoing in robotics. IEEE Trans. an Robotics and Automation, 8(3):313–326, June 1992.CrossRefGoogle Scholar
  12. 12.
    B. Espiau, P. Rives. Closed-loop recursive estimation of 3D features for a mobile vision system. In IEEE Int. Conf. on Robotics and Automation, pp. 1436–1443, Raleigh, April 1987.Google Scholar
  13. 13.
    S. Hutchinson, G. Hager, P Corke. A tutorial on visual servo control. IEEE Trans. on Robotics and Automation 12(5):651–670, October 1996.CrossRefGoogle Scholar
  14. 14.
    E. Marchand. Stratégies de perception par vision active pour la reconstruction et l'exploration de scènes statiques. PhD thesis, Université de Rennes 1, June 1996.Google Scholar
  15. 15.
    E. Marchand, F. Chaumette. Controlled camera motions for scene reconstruction and exploration. In CVPR'96, pp. 169–176, San Francisco, June 1996.Google Scholar
  16. 16.
    E. Marchand, F. Chaumette, A. Rizzo. Using the task function approach to avoid robot joint limits and kinematic singularities in visual servoing. In IROS'96, pp. 1083–1090, Osaka, Japan, November 1996.Google Scholar
  17. 17.
    E. Marchand, E. Rutten, F. Chaumette. From data-flow task to multi-tasking Applying the synchronous approach to active vision in robotics. IEEE Trans. an Control Systems Technology, 5(2):200–216, Mars 1997.CrossRefGoogle Scholar
  18. 18.
    J. Pearl. Probabilistic reasoning in intelligent systems: Networks of plausible inference. Morgan Kaufmann Publisher Inc., San Mateo, California, 1988.Google Scholar
  19. 19.
    R.D. Rimey, C. Brown. Control of selective perception using bayes nets and decision theory. IJCV, 12(2/3):173–207, April 1994.CrossRefGoogle Scholar
  20. 20.
    M.J. Swain, M.A. Stricker. Promising direction in active vision. International Journal of Computer Vision, 11(2):109–127, October 1993.CrossRefGoogle Scholar
  21. 21.
    K. Tarabanis, P.K. Allen, R. Tsai. A survey of sensor planning in computer vision. IEEE Trans. on Rabatics and Automation, 11(1):86–104, February 1995.CrossRefGoogle Scholar
  22. 22.
    B. Triggs, C. Laugier. Automatic camera placement for robot vision. In IEEE Int. Conf. an Robotics and Automation, pp. 1732–1738, Nagoya, Japon, May 1995.Google Scholar
  23. 23.
    L.E. Wixson. Viewpoint selection for visual search. In CVPR'94, pp. 800–805, Seattle, June 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Éric Marchand
    • 1
  • François Chaumette
    • 1
  1. 1.IRISA - IRRIA Rennes Campus de BeaulieuRennes cedexFrance

Personalised recommendations