Visual Form pp 175-185 | Cite as

Computing Egomotion and Shape from Image Motion Using Collinear Points

  • Niels Vitoria da Lobo
  • John K. Tsotsos


Many years ago researchers (Helmholtz 1925, Gibson 1957) hypothesized that the 3-D motion and the shape of the environment are perceivable from the projected motion arising out of the relative motion between a monocular observer and the scene. In this paper, we summarize our recent computational solution to computing egomotion and show how shape information can be computed robustly.


Flow Field Image Flow Relative Depth Image Velocity Collinear Point 
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.


  1. Ballard D.H. and Kimball O.A. (1983), “Rigid body motion from depth and optical flow”, CVGIP, 22, 95–115.Google Scholar
  2. Barron J. (1988), “Determination of egomotion and environmental layout from noisy time-varying image velocity information in monocular image sequences,” PhD. Thesis, Dept. of Computer Science, Univ. of Toronto. Available as RBCV-TR-88-24.Google Scholar
  3. Brass A.R. and Horn B.K.P. (1983), “Passive navigation”, CVGIP, 21, 3–20.Google Scholar
  4. da Vitoria Lobo N. and Tsotsos J.K. (1990), “Extracting Qualitative Shape from Image Motion: Applications to Stereo-Pairs”, Proc. AAAI Workshop on Qualitative Vision, pp. 36-40, Boston, July 1990.Google Scholar
  5. da Vitoria Lobo N. and Tsotsos J.K. (1991), “Using collinear points to compute egomotion and detect non-rigidity” Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 344-350, Hawaii, June 1991.Google Scholar
  6. Fleet D. (1990), “The Measurement of Image Velocity”, PhD. Thesis, Dept. of Computer Science, Univ. of Toronto.Google Scholar
  7. Gibson J.J. (1957), “Optical motions and transformations as stimuli for visual perception”, Psychological Review, 64, No 5, 288–295.CrossRefGoogle Scholar
  8. Heeger D. (1988), “Optical flow using spatiotemporal filters”, IJCV, 1, 279–302.CrossRefGoogle Scholar
  9. Heeger D. and Jepson A.J. (1990), “Simple method for computing 3-D motion and depth,” Proc. ICCV Osaka, Japan, December.Google Scholar
  10. Heimholte H.(1925), Treatise on Physiological Optics, Optical Society of America.Google Scholar
  11. Longuet-Higgins H.C. and Prazdny K. (1980), “The interpretation of a moving retinal image”, Proc. Roy. Soc.Lond., B 208, 385–397.CrossRefGoogle Scholar
  12. Marr D. and Hildreth E.C., (1980), “Theory of edge detection”, Proc Roy. Soc. Lond., B207, 187–217.CrossRefGoogle Scholar
  13. Matthies L., Szeliski R., Kanade T. (1989), “Kaiman filter-based algorithms for estimating depth from image sequences”, IEEE PAMI, 8, No. 1, 109–112.Google Scholar
  14. Mitiche A. (1986), “On kineopsis and computation of structure and motion”, IEEE PAMI, 8, No. 1, 109–112.CrossRefGoogle Scholar
  15. Nelson R. and Aloimonos J. (1988), “Using flow field divergence for obstacle avoidance: towards qualitative vision,” Proc. ICCV Florida, 188-196.Google Scholar
  16. Prazdny K. (1983), “On the information in optical flows”, CVGIP, 22(2), 239–259.Google Scholar
  17. Schunck B. (1986), “The image flow constraint equation”, CVGIP, 35, 20–46.Google Scholar
  18. Terzopoulos D. (1987), “On Matching Deformable Models to Images: Direct and Iterative Solutions”, Proc. Optical Society America, Topical Meeting on Machine Vision, Washington, D.C., March 1987, 160-167.Google Scholar
  19. Watson A. and Ahumada J. (1985) “Model of human visual motion sensing”, J. Optical Society of America, A2, 322–342.Google Scholar
  20. Waxman A.M. (1984), “An image flow paradigm,” CAR-TR-45, Center for Automation Research, Univ. of Maryland.Google Scholar
  21. Waxman A.M. and Wohn K. (1987), CAR-TR-45, Center for Automation Research, Univ. of Maryland. “Image flow theory: a framework for 3-D inference from time-varying imagery,” Chapter Three in Advances in Computer Vision, ed. C. Brown, (Erlbaum Publishers).Google Scholar
  22. Weinshall D. (1990), “Direct computation of qualitative 3-D shape and motion invariants,” Proc ICCV, Osaka, Japan, December.Google Scholar
  23. Witkin A.P. (1983), “Scale-space filtering,” Proc. IJCAI-83, Karlsruhe, Germany, 1019-22.Google Scholar
  24. Woodham R. J. (1990), “Multiple light source optical flow,” Proc. ICCV, Osaka, Japan, December.Google Scholar
  25. Zucker S.W., David C, Dobbins A., Iverson L. (1988), “The organization of curve detection: coarse tangent fields and fine spline coverings,” Proc. ICCV-88, Tampa, 568-577.Google Scholar

Copyright information

© Springer Science+Business Media New York 1992

Authors and Affiliations

  • Niels Vitoria da Lobo
    • 1
  • John K. Tsotsos
    • 1
  1. 1.Department of Computer ScienceUniversity of TorontoTorontoCanada

Personalised recommendations