Robust epipolar geometry using genetic algorithm

  • Jinxiang Chai
  • SongDe Ma
Poster Session I
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1351)


Epipolar geometry is an important constraint to establish the correspondences in stereo vision. The 3 × 3 fundamental matrix describes the epipolar geometry between two uncalibrated images. In this paper, we formulate the epipolar geometry estimation as a global optimization probelm, and then we present a genetic algorithm for parameter searching. Experiments with simulated and real data show that our algorithm performs very well in terms of robustness to outliers, rate of convergence and quality of the final estimation.


Fundamental matrix Epipolar geometry Global Optimization Genetic algorithm 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Faugeras, O.D(1992). What can be seen in the three dimensions with an uncalibrated stereo rig ? In G.Sandini, editor, Proceedings of the 2nd European Conference on Computer Vision, Santa Margherita Italy, pages 563–578. Springer-Verlag.Google Scholar
  2. 2.
    Goldberg, D.E(1989). Genetic Algorithms in Search, Optimization and Machine Learning. Addison Wesley.Google Scholar
  3. 3.
    Harris, C(1987). A combined corner and edge detection. in proceedings alvey conference.Google Scholar
  4. 4.
    Hartely, R.I and R.Gupta(1993), Computing matched-epipolar projections. In Proceedings of the Conference on Computer Vision and Pattern Recognition, New York, pages 549–555.Google Scholar
  5. 5.
    Hartley, R.I(1995). In defence of the 8-point algorithm. Proc. 5th Int Conf on Computere Vision, Boston MA, pages 1064-1-70.Google Scholar
  6. 6.
    Holland, J (1975). Adaptation in natural and artificial systems. University of Michigan Press, Ann Arbor.Google Scholar
  7. 7.
    Laveau, S and O.D.Faugeras(1994). 3-D scence representation as a collection of images. In Proc. International Conference on Pattern Recognition, Jerusalem, Israel.Google Scholar
  8. 8.
    Longuet-Higgins, H.C (1981). A computer algorithm for reconstruction a scene from two projection. Nature, 293:133–135.Google Scholar
  9. 9.
    Luong, Q.T, and O.D.Faugeras(1992). Self-calibration of a camera using multiple images. In Proceedings of the 11th International Conference on Pattern Recognition, The Hag, Netherland, pages 9–12.Google Scholar
  10. 10.
    Maybank, S.J and O.D.Faugeras (1992). A theory of self calibration of a moving camera. International Jounal of Computer Vision, 8(2):123–151.Google Scholar
  11. 11.
    Michalewicz, Z(1992). Genetic algorithms+data structures=evolution programs, Springer-Verlag.Google Scholar
  12. 12.
    Nishimura, E, Xu, G and S.Tsuji(1990). Motion segmentation and correspondence using epipolar constraint. In Proceedings of the 1st Asian Conference on Computer Vision, Osaka, Japan, pages 199–204.Google Scholar
  13. 13.
    Robert, L and M.Hebert(1993). Deriving orientation cues from stereo images. In Proceedings of the Eurapean Conference on Computer Vision, Berlin, Germany, pages 540–543.Google Scholar
  14. 14.
    Shashua, A(1993). Projective depth: a geometric invariant for 3d reconstruction from two perspective/orthographic views and for visual recognition. In Proceedings of International Conference on Computer Vision, Berlin, Germany, pages 583–590.Google Scholar
  15. 15.
    Sinclair, D, B.Boufama and R.Mohr(1994). Independent motion segmentation and collision predection for road vehicales. In proceedings of the Conference on Computer Vision and Pattern Recognition, seattle, Washington, USA, pages 958–961.Google Scholar
  16. 16.
    Xu, G and Z.Zhang(1996). Epipolar geometry in stereo, motion and object recognition. Kluwer Academic Publisher.Google Scholar
  17. 17.
    Zhang, Z, R. Deriche, O.D. Faugeras and Q.T.Luong (1994). A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry. AI jounal, 78:87–119.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Jinxiang Chai
    • 1
  • SongDe Ma
    • 1
  1. 1.National Laboratory of Pattern RecognitionInstitute of Automation Chinese Academy of SciencesBeijingP.R.China

Personalised recommendations