Depth and Motion Analysis: The Esprit Project P940

  • Musso Giorgio
Conference paper


Depth and Motion Analysis represents one of the most important issues in passive three- dimensional Computer Vision. The ESPRIT Project P940 is a remarkable research initiative dedicated to these problems, in which some of the main University and Industry Organizations, working in the Computer Vision field, are involved.

The aims of this project are those of investigating passive methods and algorithms for Depth and Motion Analysis, and of designing and building a hardware architecture, capable of implementing this analysis on line with a mobile vehicle, navigating in a structured environment, and with a robot arm for recognition and location purpouses.

In this paper the technical contents of the project as well as the project evolution are described.


Motion Analysis Hardware Architecture Epipolar Line Mobile Vehicle Canny Operator 
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).
    MUSSO G., Applicazioni della visione artificiale nell’automazione industriale e dei servizi. La Visione delle macchine. Tecniche Nuove. Autunno 1989.Google Scholar
  2. (2).
    ROSENFELD A., Computer Vision: basic principles. IEEE Proceedings. August 1988.Google Scholar
  3. (3).
    ESPRIT P940 Technical Annex.Google Scholar
  4. (4).
    AYACHE N. and LUSTMAN F. Fast and reliable passive trinocular stereovision. Proc. First International Conference on Computer Vision, pages 422–427, IEEE June 1987. London, U.K.Google Scholar
  5. (5).
    AYACHE N. and LUSTMAN F. Trinocular stereovision, recent results. Proceeding of International Joint Conference on Artificial Intelligence. August 1987. Milano, Italy.Google Scholar
  6. (6).
    FAUGERAS O.D., LUSTMAN F. and TOSCANI G., Motion and structure from point and lines matches. Proc. of First International Conference on Computer Vision, pages 25–34, IEEE, June 1987. London, U.K.Google Scholar
  7. (7).
    Structure from Motion ESPRIT Project P940, Report R.2.5.1, June 1988Google Scholar
  8. (8).
    Trinocular Stereovision ESPRIT Project P940, Report R. 1.3.4, May 1988Google Scholar
  9. (9).
    FAUGERAS O. et al. Depth and Motion Analysis: the machine being developed within ESPRIT Project P940. IAPR Workshop on Computer Vision. October 1988. TokioGoogle Scholar
  10. (10).
    AYACHE N., FAUGERAS O.D., LUSTMAN F. and ZHANG Z. Visual navigation of a mobile robot: recent steps. Proc. of Int. Symp. and Exposition on Robots. November 1988Google Scholar
  11. (11).
    GARIBOTTO G. A real-time 3-D vision system for a variety of robotic applications. Proceedings 5th ESPRIT Conference 1988.Google Scholar
  12. (12).
    Token Tracking ESPRIT Project P940, Report R.2.4.1., June 1988Google Scholar
  13. (13).
    Differential Techniques for the computation of the Optical Flow ESPRIT Project P940, Report R.4.2.1, June 1988.Google Scholar
  14. (14).
    JAZWINSKY AM. Stochastic Processes and Filtering Theory. Academic Press, 1970.Google Scholar
  15. (15).
    Delaunay Tetrahedrization ESPRIT Project P940, Report R.4.1.4, May 1988.Google Scholar
  16. (16).
    Planes and Quadrics from 3D segments ESPRIT Project P940, Report R.4.1.6, May 1988.Google Scholar
  17. (17).
    AYACHE N. and FAUGERAS OD. Maintaining representations of the environment of a mobile robot. Robert Bolles and Bernard Roth, editors. Robotics Research: the Fourth International Symposium, pages 337–350, MIT Press, 1988.Google Scholar
  18. (18).
    CASSOLINO C., MANGILI F. and VIANO G. Identification and Recognitionof 3D Surface Primitives-Internal Report, ELSAG, 1988Google Scholar
  19. (19).
    APPIANI E., BARBAGELATA G., CONTERNO B. and MANARA R., EMMA2: An Industry-De­veloped Hierarchical Multiprocessor for Very High Performance Signal Processing Applications. Published by the Proceedings of First International Conference on Supercomputing Systems, 1985. St.Petersburg, FLORIDA.Google Scholar
  20. (20).
    FAUGERAS OD. and Toscani G. The calibration problem for stereo, CVPR ’86, pages 15–20, June 1986, Miami.Google Scholar
  21. (21).
    Techniques for Camera Calibration in Stereovision ESPRIT Project P940, Report R.1.1.2, Nov. 1986.Google Scholar
  22. (22).
    CANNY JA Computational approach to edge detection. Published by IEEE Transactions on Pattern Analysis and Machine Intelligence, 8 No6 pages 679–698,1986.Google Scholar
  23. (23).
    DERICHE R. Using canny’s criteria to derive an optimal edge detector recursively implemented. Published by The International Journal of Computer Vision, 2 April 1987.Google Scholar
  24. (24).
    BERTHOD M. Approximation polygonale de chaines de contours. Programmes C, 1986. INRIA.Google Scholar
  25. (25).
    MARR D., Vision. S.Francisco, CA: Freeman, 1982.Google Scholar
  26. (26).
    AYACHE N. and FAUGERAS OD. Building, registrating and fusing noisy visual maps. Published by Proc. First International Conference on Computer Vision, pages 73–82, IEEE, June 1987. London,U.K., also an INRIA Internal Report 596,1986.Google Scholar
  27. (27).
    Deliverables on Demonstrators Specifications.Google Scholar
  28. (28).
    P940 Technical Annex, Last Revision, March 1989.Google Scholar
  29. (29).
    CROWLEY JL. Measuring Image Flow by Tracking Edge-Lines. Second International Conference on Computer Vision, September 1988.Google Scholar

Copyright information

© ECSC, EEC, EAEC, Brussels and Luxembourg 1989

Authors and Affiliations

  • Musso Giorgio
    • 1
  1. 1.Elettronica San GiorgioELSAG S.p.AGenovaItaly

Personalised recommendations