International Journal of Computer Vision

, Volume 13, Issue 1, pp 33–56 | Cite as

Estimating the heading direction using normal flow

  • Yiannis Aloimonos
  • Zoran Duric


If an observer is moving rigidly with bounded rotation then normal flow measurements (i.e., the spatiotemporal derivatives of the image intensity function) give rise to a constraint on the oberver's translation. This novel constraint gives rise to a robust, qualitative solution to the problem of recovering the observer's heading direction, by providing an area where the Focus of Expansion lies. If the rotation of the observer is large then the solution area is large too, while small rotation causes the solution area to be small, thus giving rise to a robust solution. In the paper the relationship between the solution area and the rotation and translation vectors is studied and experimental results using synthetic and real calibrated image sequences are presented. This work demonstrates that the algorithm developed in (Horn and Weldon 1987) for the case of pure translation, if appropriately modified, results in a robust algorithm that works in the case of general rigid motion with bounded rotation. Subsequently, it has the potential to replace expensive accelerometers, inertial systems and inaccurate odometers in practical navigational systems for the problem of kinetic stabilization, which is a prerequisite for any other navigational ability.


Flow Measurement Image Intensity Normal Flow Intensity Function Rigid Motion 
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. J. Aloimonos, “Purposive and qualitative active vision”,Proc. ARPA Image Understanding Workshop, 1990a, 816–828.Google Scholar
  2. J. Aloimonos (Ed.),CVGIP: Image Understanding 56, 1992.Google Scholar
  3. J. Aloimonos and C.M. Brown, “Direct processing of curvilinear sensor motion from a sequence of perspective images”,Proc. Workshop on Computer Vision: Representation and Control, Annapolis, MD, 72–77, 1984.Google Scholar
  4. J. Aloimonos and D. Shulman,Integration of Visual Modules: An Extension of the Marr Paradigm, Academic Press, Boston, 1989.Google Scholar
  5. J. Aloimonos, I. Weiss, and A. Bandopadhay, “Active vision ”,Int'l. J. Comp. Vision 2, 1988, 333–356.Google Scholar
  6. D.H. Ballard, “Parameter networks”,Artificial Intelligence 22, 1984, 235–267.Google Scholar
  7. A. Blake, S. Murray and A. Sinclair, “Egomotion from normal flow”, personal communication, 1992.Google Scholar
  8. A. Bruss and B.K.P. Horn, “Passive navigation”,Computer Vision, Graphics Image Processing 21, 1983, 3–20.Google Scholar
  9. W. Burger and B. Bhanu, “Estimating 3D egomotion from perspective image sequences”,IEEE Trans. PAMI 12, 1990, 1040–1058.Google Scholar
  10. Z. Duric, A. Rosenfeld and L.S. Davis, “Passive navigation using the Frenet-Secret model,” Proc. 4th ICCV, Berlin, Germany, 1993, pp. 363–369.Google Scholar
  11. O. Faugeras and S. Maybank, “Motion from point matches: Multiplicity of solutions”,Int'l. J. Computer Vision 4, 1990, 225–246.Google Scholar
  12. C. Fermüller, “Basic Visual Capabilities,” Ph.D. Thesis, Institute for Automation, Technical University of Vienna, 1993a (also available as Technical Report 668, Center for Automation Research, University of Maryland).Google Scholar
  13. C. Fermüller, “Navigational preliminaries”, inActive Perception, Y. Aloimonos (Ed.), Lawrence Erlbaum Associates, Inc., Publishers, 1993b.Google Scholar
  14. E. Francois and P. Bouthemy, “Derivation of qualitative information in motion analysis”,Image and Vision Computing 8, 1990, 279–288.Google Scholar
  15. B.K.P. Horn, “Relative Orientation”,Int'l J. Comp. Vision 4, 1990, 59–78.Google Scholar
  16. B.K.P. Horn and E.J. Weldon, “Computationally efficient methods of recovering translational motion”,Proc. International Conference on Computer Vision, 1987, 27–11.Google Scholar
  17. J.J. Koenderink and A.J. van Doorn, “Invariant properties of the motion parallax field due to the movement of rigid bodies relative to an observer ”,Optica Acta 22, 1975, 773–791.Google Scholar
  18. G.A. Korn and T.M. Korn,Mathematical Handbook for Engineers and Scientists, McGraw Hill, 1968.Google Scholar
  19. H.C. Longuet-Higgins, “A computer algorithm for reconstructing a scene from two projections”,Nature 293, 1981, 133–135.Google Scholar
  20. H.C. Longuet-Higgins and K. Prazdny, “The interpretation of a moving retinal image”,Proc. Royal Soc. London B 208, 1980, 385–397.Google Scholar
  21. D. Marr,Vision, W.H. Freeman, San Francisco, 1982.Google Scholar
  22. S.J. Maybank, “The angular velocity associated with the optical flow field arising from motion through a rigid environment”,Proc. Royal Soc. London A 401, 1985, 317–326.Google Scholar
  23. S. Negahdaripour, Ph.D. Thesis, MIT Artificial Intelligence Laboratory, 1986.Google Scholar
  24. R.C. Nelson and J. Aloimonos, “Finding motion parameters from spherical flow fields (Or the advantages of having eyes in the back of your head) ”,Biological Cybernetics 58, 1988, 261–273.Google Scholar
  25. R. Nelson and J. Aloimonos, “Using flow field divergence for obstacle avoidance in visual navigation”,IEEE Trans. PAMI 11, 1989, 1102–1106.Google Scholar
  26. M.E. Spetsakis and J. Aloimonos, “Optimal computing of structure from motion using point correspondences in two frames”,Proc. International Conference on Computer Vision, 1988.Google Scholar
  27. M.E. Spetsakis and J. Aloimonos, “Unification theory of structure from motion”, Technical Report CAR-TR-482, Computer Vision Laboratory, Center for Automation Research, University of Maryland, College Park, 1989.Google Scholar
  28. M.E. Spetsakis and J. Aloimonos, “Structure from motion using line correspondences”,Int'l. J. Computer Vision 4, 1990, 171–183.Google Scholar
  29. W.B. Thompson and J.K. Kearney, “Inexact vision”,Proc. Workshop on Motion 1986, 15–22.Google Scholar
  30. W.B. Thompson and J.S. Painter, “Qualitative constraints for structure from motion”, in Y. Aloimonos (Ed.),CVGIP: Image Understanding 56, 1992, 69–77.Google Scholar
  31. M. Tistarelli and G. Sandini, “Dynamic aspects in active vision”, in Y. Aloimonos (Ed.),CVGIP: Image Understanding,56, 1992, 87–104.Google Scholar
  32. R.Y. Tsai and T.S. Huang, “Uniqueness and estimation of three dimensional motion parameters of rigid objects with curved surfaces”,IEEE Trans. PAMI 6, 1984, 13–27.Google Scholar
  33. S. Ullman,The Interpretation of Visual Motion, MIT Press, Cambridge, MA, 1979.Google Scholar
  34. D. Weinshall, “Qualitative depth from stereo with applications”,CVGIP 49, 1990,222–241.Google Scholar
  35. D. Weinshall, “Direct computation of qualitative 3D shape and motion invaraiants”,IEEE Trans. PAMI 13, 1991, 1236–1240.Google Scholar
  36. J. Weng, T.S. Huang and N. Ahuja, “A two step approach to optimal motion and structure estimation”,Proc. IEEE Computer Society Workshop on Computer Vision, 1987.Google Scholar
  37. G. White and E. Weldon. Utilizing Gradient Vector Distributions to Recover Motion Parameters. InProc. IEEE Workshop on Computer Vision, pages 132–137, 1987.Google Scholar
  38. G.S. Young and R. Chellappa, “3-D motion estimation using a sequence of noisy stereo images”,Proc. IEEE Conference on Computer Vision and Pattern Recognition, 1988.Google Scholar
  39. A. Zisserman and R. Cipolla, “Qualitative surface shape from deformations of image curves”,Proc. Workshop on Qualitative Vision, AAAI '90, 1990, 41–45.Google Scholar

Copyright information

© Kluwer Academic Publishers 1994

Authors and Affiliations

  • Yiannis Aloimonos
    • 1
  • Zoran Duric
    • 1
  1. 1.Computer Vision Laboratory, Center for Automation Research, Department of Computer Science and Institute for Advanced Computer StudiesUniversity of Maryland College Park

Personalised recommendations