Advertisement

Two-Frame Optical Flow Formulation in an Unwarping Multiresolution Scheme

  • C. Cassisa
  • S. Simoens
  • V. Prinet
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5856)

Abstract

In this paper, we propose a new formulation of the Differential Optical Flow Equation (DOFE) between two consecutive images considering spatial and temporal information from both. The displacement field is computed in a Markov Random Field (MRF) framework. The solution is done by minimization of the Gibbs energy using a Direct Descent Energy (DDE) algorithm. A hybrid multiresolution approach, combining pyramidal decomposition and two-step multigrid techniques, is used to estimate small and large displacements. A new pyramidal decomposition method without warping process between pyramid levels is introduced. The experiments carried out on benchmark dataset sequences show the effectiveness of the new optical flow formulation using the proposed unwarped pyramid decomposition schema.

Keywords

Optical flow estimation RMF minimization Multiresolution technique 

References

  1. 1.
    Alvarez, L., Castano, C.A., Garcia, M., Krissian, K., Mazorra, L., Salgado, A., Sanchez, J.: Symmetric Optical Flow. In: Moreno Díaz, R., Pichler, F., Quesada Arencibia, A. (eds.) EUROCAST 2007. LNCS, vol. 4739, pp. 676–683. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  2. 2.
    Alvarez, L., Weickert, J., Sanchez, J.: Reliable Estimation of Dense Optical Flow Fields with Large Displacements. IJCV 39, 41–56 (2000)Google Scholar
  3. 3.
    Baker, S., Roth, S., Scharstein, D., Black, M.J., Lewis, J.P., Szeliski, R.: A Database and Evaluation Methodology for Optical Flow. ICCV 2007, 1–8 (2007), http://vision.middlebury.edu/flow/
  4. 4.
    Barron, J.L., Fleet, D.J., Beauchemin, S.S.: Performance of Optical Flow Techniques. IJCV 12, 43–77 (1994)Google Scholar
  5. 5.
    Black, M.J., Anandan, P.: The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow-Fields. CVIU 63, 75–104 (1996)Google Scholar
  6. 6.
    Burt, P.J., Adelson, E.H.: The Laplacian Pyramid as a Compact Image Code. IEEE Trans. on Communications 3, 532–540 (1983)CrossRefGoogle Scholar
  7. 7.
    Cassisa, C., Prinet, V., Shao, L., Simoens, S., Liu, C.L.: Optical flow robust estimation in a hybrid multi-resolution MRF Framework. In: ICASSP 2008, Las Vegas (2008)Google Scholar
  8. 8.
    Corpetti, T., Menin, E., Perez, P.: Dense estimation of fluid flow. IEEE Trans. on Pattern Analysis and Machine Intelligence, 365–380 (2002)Google Scholar
  9. 9.
    Horn, B.K.P., Schunck, B.G.: Determining Optical Flow. Aritifial Intelligence 17, 185–203 (1981)CrossRefGoogle Scholar
  10. 10.
    Liu, H., Rosenfeld, A., Chellapa, R.: Two-frame multi-scale optical flow estimation using wavelet decomposition. In: ICASSP 2002, vol. 3 (2002)Google Scholar
  11. 11.
    Memin, E., Perez, P.: Dense Estimation and Object-Based Segmentation of the Optical-Flow with Robust Techniques. Int. J. on IP 7, 703–719 (1998)Google Scholar
  12. 12.
    Memin, E., Perez, P.: A multigrid approach to hierarchical motion estimation. In: ICCV 1998, January 1998, pp. 933–938 (1998)Google Scholar
  13. 13.
    Papenberg, N., Bruhn, A., Brox, T., Didas, S., Weickert, J.: Highly Accurate Optic Flow Computation with Theoretically Justified Warping. IJCV, 141–158 (2006)Google Scholar
  14. 14.
    Papenberg, N., Bruhn, A., Brox, T., Weickert, J.: Numerical Justification for Multiresolution Optical Flow Computation. In: IWCVIA 2003, Las Palmas, Spain (2003)Google Scholar
  15. 15.
    Simoncelli, E.P., Freeman, W.T.: The Steerable Pyramid: A Flexible Architecture for Multi-Scale Derivative Computation. In: ICIP 1995, pp. 444–447 (1995)Google Scholar
  16. 16.
    Tikhonov, A.N., Arsenin, V.Y.: Solutions of ill-posed Problems, ch. 2. John Wiley & Sons, Chichester (1977)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • C. Cassisa
    • 1
    • 2
  • S. Simoens
    • 1
  • V. Prinet
    • 2
  1. 1.Lab. of Fluid Mechanics and Acoustics (LMFA)Ecole Centrale LyonFrance
  2. 2.Lab. of Informatics, Automatics and Applied Mathematics (LIAMA)Chinese Academy of SciencesBeijingChine

Personalised recommendations