Advertisement

Image Registration, Optical Flow, and Local Rigidity

  • Martin Lefébure
  • Laurent D. Cohen
Conference paper
Part of the Lecture Notes in Computer Science 2106 book series (LNCS, volume 2106)

Abstract

We address the theoretical problems of optical flow estimation and image registration in a multi-scale framework in any dimension. We start by showing, in the translation case, that convergence to the global minimum is made easier by applying a low pass filter to the images hence making the energy “convex enough”. In order to keep convergence to the global minimum in the general case, we introduce a local rigidity hypothesis on the unknown deformation. We then deduce a new natural motion constraint equation (MCE) at each scale using the Dirichlet low pass operator. This allows us to derive sufficient conditions for convergence of a new multi-scale and iterative motion estimation/registration scheme towards a global minimum of the usual nonlinear energy instead of a local minimum as did all previous methods. We then use an implicit numerical approach. We illustrate our method on synthetic and real examples (Motion, Registration, Morphing).

Keywords

Global Minimum Optical Flow Motion Estimation Image Registration Residual 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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    L. Alvarez, J. Esclarin, M. Lefébure, J. Sanchez. A PDE model for computing the optical flow. Proc. XVI Congresso de Ecuaciones Diferenciales y Aplicaciones, Las Palmas, pp. 1349–1356, 1999.Google Scholar
  2. 2.
    L. Alvarez, J. Weickert, J. Sanchez, Reliable estimation of dense optical flow fields with large displacements. TR 2, Universidad de Las Palmas, November 1999.Google Scholar
  3. 3.
    G. Aubert, R. Deriche and P. Kornprobst. Computing optical flow via variational techniques. SIAM J. Appl. Math., Vol. 60(1), pp. 156–182, 1999.MathSciNetzbMATHCrossRefGoogle Scholar
  4. 4.
    N. Ayache. Medical computer vision, virtual reality and robotics. IVC (13),No 4, May 1995, pp 295–313.CrossRefGoogle Scholar
  5. 5.
    Ruzena Bajcsy and Stane Kovacic. Multiresolution elastic matching. CVGIP, (46),No 1, pp. 1–21, 1989.Google Scholar
  6. 6.
    J.L. Barron, D.J. Fleet, and S.S. Beauchemin. Performance of optical flow. IJCV, 12(1):43–77, 1994.CrossRefGoogle Scholar
  7. 7.
    M. Ben-Ezra, B. Rousso, and S. Peleg. Motion segmentation using convergence properties. In ARPA Im. Unders. Workshop, pp II 1233–1235, 1994.Google Scholar
  8. 8.
    J.R. Bergen and E.H. Adelson. Hierarchical, computationally efficient motion estimation algorithm. J. of the Optical Society Am., 4(35), 1987.Google Scholar
  9. 9.
    P. Bouthemy and J.M. Odobez. Robust multiresolution estimation of parametric motion models. J. of Vis. Comm. and Image Repres., 6(4):348–365, 1995.CrossRefGoogle Scholar
  10. 10.
    G. Christensen, R.D. Rabbitt, and M.I. Miller. 3D brain mapping using a deformable neuroanatomy. Physics in Med and Biol, (39), March: 609–618, 1994.CrossRefGoogle Scholar
  11. 11.
    D. Fleet, M. Black, Y. Yacoob and A. Jepson. Design and use of linear models for image motion analysis. IJCV, 36(3), 2000.Google Scholar
  12. 12.
    P.R. Giaccone, D. Greenhill, G.A. Jones. Recovering very large visual motion fields. SCIA97, pp 917–922.Google Scholar
  13. 13.
    B.K.P. Horn and Brian Schunck. Determining optical flow. Artificial Intelligence, (17)(1-3):185–204, 1981.CrossRefGoogle Scholar
  14. 14.
    M. Irani, B. Rousso, and S. Peleg. Detecting and tracking multiple moving objects using temporal integration. In ECCV92, pp 282–287, 1992.Google Scholar
  15. 15.
    M. Lefébure Estimation de Mouvement et Recalage de Signaux et d’Images: Formalisation et Analyse. PhD Thesis, Université Paris-Dauphine, 1998.Google Scholar
  16. 16.
    Martin Lefébure and Laurent D. Cohen. A multiresolution algorithm for signal and image registration. In In Proc. ICIP’97, Santa Barbara, California, Oct. 1997.Google Scholar
  17. 17.
    M. Lefébure and L.D. Cohen. Motion estimation and registration of signals and images: formalization and analysis. CEREMADE Technical Report, 0102, January 2001. To appear in Journal of Mathematical Imaging and Vision.Google Scholar
  18. 18.
    D. Terzopoulos. Multiresolution algorithms in computational vision. Image Understanding. S. Ullman, W. Richards, 1986.Google Scholar
  19. 19.
    J.P. Thirion. Fast non-rigid matching of 3D medical images. TR 2547, INRIA, 1995.Google Scholar
  20. 20.
    A. Trouvé. Diffeomorphisms groups and pattern matching in image analysis IJCV, 28(3), 1998.Google Scholar
  21. 21.
    J. Weickert. On discontinuity-preserving optic flow. Proc. Computer Vision and Mobile Robotics Workshop, Santorini, pp. 115–122, Sept. 1998.Google Scholar
  22. 22.
    G. Whitten. A framework for adaptive scale space tracking solutions to problems in computational vision. In ICCV’90, Osaka, pp 210–220, Dec 1990.Google Scholar
  23. 23.
    A. Witkin, D. Terzopoulos, M. Kass. Signal matching through scale space. IJCV, 1(2):133–144, 1987.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Martin Lefébure
    • 1
  • Laurent D. Cohen
    • 2
  1. 1.Poseidon TechnologiesNeuilly Sur SeineFrance
  2. 2.CEREMADEUniversité Paris-DauphineParisFrance

Personalised recommendations