Estimating translation/deformation motion through phase correlation

  • Filiberto Pla
  • Miroslaw Bober
Session 7: Motion & Stereo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1310)


Phase correlation techniques have been used in image registration to estimate image displacements. These techniques have been also used to estimate optical flow by applying it locally. In this work a different phase correlation-based method is proposed to deal with a deformation/translation motion model, instead of the pure translations that the basic phase correlation technique can estimate. Some experimentals results are also presented to show the accuracy of the motion paramenters estimated and the use of the phase correlation to estimate optical flow.

Key Words

Motion Optical Flow Image Registration Phase Correlation 


  1. 1.
    Alliney, S. and Morandi, C.; “Digital image registration using projections”, IEEE Trans. Patt. Anal. Mach. Intel., vol. PAMI-8, no. 2, pp. 222–233, 1986.Google Scholar
  2. 2.
    Barron, J.; Fleet, D. and Beauchemin, S.; “Performance of optical flow techniques”, Int. J. Comp. Vision, vol. 12, pp. 43–77, 1994.Google Scholar
  3. 3.
    Bober, M. and Kittler, J.; “Robust motion analysis”, Proc. of IEEE Conf., on Computer Vision and Pattern Recognition, Seatle, pp. 947–952, 1994.Google Scholar
  4. 4.
    Bracewell, R. N.; The Fourier transform and its applications, McGraw Hill, 1986.Google Scholar
  5. 5.
    De Castro, E. and Morandi, C.; “Registration of translated and rotated images using finite Fourier transforms”, IEEE Trans. Patt. Anal. Mach. Intel., vol. PAMI-9, no. 5, pp. 700–703, 1987.Google Scholar
  6. 6.
    Ghraravi, H. and Mills, M.; “Block-matching motion estimation algorithms: New results”, IEEE Trans. Circ. and Syst., vol. 37, pp. 649–651, 1990.Google Scholar
  7. 7.
    Horn, B.K.P. and Schunk, B. G.; “Determining optical flow”, Artificial Intelligence, vol. 5, no. 3, pp. 276–287, 1993.Google Scholar
  8. 8.
    Iu, S. L.; “Robust estimation of motion vector fields with discontinuity and occlusion using local outliers rejection”, SPIE, vol. 2094, pp. 588–599, 1993.Google Scholar
  9. 9.
    Jacobson, L. and Wechsler, H.; “Derivation of optical flow using a spatiotemporal-frequency approach”, Computer Vision, Graphics and Image Processing, vol. 38, pp. 29–65, 1987.Google Scholar
  10. 10.
    Konrad, J. and Dubois, E.; “Comparison of stochastic and deterministic solution methods in Bayesian estimation of 2D motion”, Image and Vision Computing, vol. 9, pp. 215–228, 1991.Google Scholar
  11. 11.
    Liu, B. and Zaccarin, A.;“New fast algorithms for the estimation of block motion vectors”, IEEE Trans. Circ. and Syst. Video Tech., vol. 3, no. 2, pp. 148–157, 1993.Google Scholar
  12. 12.
    Lucas, B. D. and Kanade, T.; “An iterative image registration technique with an application to stereo vision”, Proc. DARPA Image Understanding Workshop, pp. 121–130, 1981.Google Scholar
  13. 13.
    Tekalp, A. M.; Digital video processing, Prentice Hall, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Filiberto Pla
    • 1
  • Miroslaw Bober
    • 2
  1. 1.Dept. of Computer ScienceUniversity Jaume ICastellóSpain
  2. 2.Dept. of Electrical and Electronic EngineeringUniversity of SurreyGuilfordUK

Personalised recommendations