A common framework for kinetic depth, reconstruction and motion for deformable objects

  • Gunnar Sparr
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 801)


In this paper, problems related to depth, reconstruction and motion from a pair of projective images are studied under weak assumptions. Only relative information within each image is used, nothing about their interrelations or about camera calibration. Objects in the scene may be deformed between the imaging instants, provided that the deformations can be described locally by affine transformations. It is shown how the problems can be treated by a common method, based on a novel interpretation of a theorem in projective geometry of M. Chasles, and the notion of “affine shape”. No epipolar geometry is used. The method also enables the computation of the “depth flow”, i.e. a relative velocity in the direction of the ray of sight.


Depth shape reconstruction motion invariants 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    M. Chasles. Question 296. Nouv. Ann. Math., 14(50), 1855.Google Scholar
  2. 2.
    O.D. Faugeras. What can be seen in three dimensions with an uncalibrated stereo rig? In G. Sandini, editor, Computer Vision — ECCV92, pages 563–578. Springer Verlag, jun 1992.Google Scholar
  3. 3.
    O.D. Faugeras and S. Maybanks. Motion from point matches: multiplicity of solutions. Int. J. Computer vision, 4(3):225–246, 1990.Google Scholar
  4. 4.
    R. Hartley, R. Gupta, and Tom Chang. Stereo from uncalibrated cameras. In Proceedings IEEE Conf. on Computer vision and Pattern Recognition, pages 761–764, 1992.Google Scholar
  5. 5.
    A. Heyden. On the consistency of line drawings, obtained by projections of piecewise planar objects. Technical Report ISSN 0347-8475, Dept of Mathematics, Lund Institute of Technology, may 1993.Google Scholar
  6. 6.
    A. Heyden. Reconstruction from three images of six point objects. In Proc Swedish Soc. of Automated Image Analysis, mar 1994.Google Scholar
  7. 7.
    B.P.K. Horn. Relative orientation. Int. J. Computer Vision, 4:59–78, 1990.Google Scholar
  8. 8.
    G.W. Humphreys and V. Bruce. Visual Cognition. Lawrence Erlbaum Associates, Publishers, 1991.Google Scholar
  9. 9.
    J.J. Koenderink and A.J. Van Doom. Affine structure from motion. J. of the Optical Society of America, 8:377–385, 1991.Google Scholar
  10. 10.
    S.J. Maybank. The projective geometry of ambigous surfaces. Philosophical Transactions of the Royal Society, 1990.Google Scholar
  11. 11.
    R. Mohr, L. Quan, F. Veillon, and B. Boufama. Relative 3d reconstruction using multiple uncalibrated images. Technical Report RT 84-IMAG, LIFIA-IRIMAG, jun 1992.Google Scholar
  12. 12.
    D. Schattschneider and W. Walker. Kalejdocykler. Benedikt Taschen Verlag, 1990.Google Scholar
  13. 13.
    A. Shashua. Projective depth: A geometric invariant for 3d reconstruction from two rspective/orthographic views and for visual recognitionep e. In International Conference on Computer Vision, pages 583–590. IEEE, IEEE, 1993.Google Scholar
  14. 14.
    R.N. Shepard. Mind Sights. W.H. Freeman and Company, New York, 1990.Google Scholar
  15. 15.
    A. Sparr and G. Sparr. On a theorem of m. chasles. Technical Report ISRN LUTFD2/TFMA-7001-SE, Dept. of Mathematics, Lund, 1993.Google Scholar
  16. 16.
    G. Sparr. Depth, shape and invariancy. (Book in preparation, Kluwer Verlag).Google Scholar
  17. 17.
    G. Sparr. Projective invariants for affine shapes of point configurations. In Andrew Zisserman and Joe Mundy, editors, ESPRIT/DARPA Invariants Workshop, Reykjavik, apr 1991.Google Scholar
  18. 18.
    G. Sparr. An algebraic/analytic method for reconstruction from image correspondences. In TheoryApplications of Image Analysis, volume 2 of Machine Perception Artificial Intelligence, pages 87–98. World Scientific Publishing Co, 1992. n.Google Scholar
  19. 19.
    G. Sparr. Depth computations from polyhedral images. Image and Vision Computing, 10(10):683–688, dec 1992. Also in Proc. ECCV 92, Springer Lect. Notes in Comp.Sc.Google Scholar
  20. 20.
    G. Sparr. Applications of a theorem of chasles to computer vision. Technical Report ISRN LUTFD2/TFMA-7002-SE, Dept of Mathematics, Lund Institute of Technology, 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Gunnar Sparr
    • 1
  1. 1.Dept. of MathematicsLund University/LTHLundSweden

Personalised recommendations