A Study of the Yosemite Sequence Used as a Test Sequence for Estimation of Optical Flow

  • Ivar Austvoll
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3540)


Since the publication of the comparative study done by Barron et al. on optical flow estimation, a race was started to achieve more and more accurate and dense velocity fields. For comparison a few synthetic image sequences has been used. The most complex of these is the Yosemite Flying sequence that contains both a diverging field, occlusion and multiple motions at the horizon. About 10 years ago it was suggested to remove the sky region because the correct flow used in earlier work was not found to be the real ground truth for this region. In this paper we present a study of the sky region in this test sequence, and discuss its usefulness for evaluation of optical flow estimation.


Motion Estimation Test Sequence Angular Error Magnitude Error Orientation Tensor 
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.


  1. 1.
    Gibson, J.J.: The Perception of the Visual World. Houghton-Mifflin, Boston (1950)Google Scholar
  2. 2.
    Horn, B., Schunck, B.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)CrossRefGoogle Scholar
  3. 3.
    Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proc. DARPA Image Understanding Workshop, pp. 121–130 (1981)Google Scholar
  4. 4.
    Limb, J.O., Murphy, J.A.: Estimating the velocity of moving images in television signals. Computer Graphics and Image Processing 4, 311–327 (1975)CrossRefGoogle Scholar
  5. 5.
    Barron, J., Fleet, D., Beauchemin, S., Burkitt, T.: Performance of optical flow techniques. Technical Report TR 299, Dept. Comp. Sci., Univ. Western Ontario (1993)Google Scholar
  6. 6.
    Barron, J., Fleet, D., Beauchemin, S.: Performance of optical flow techniques. International Journal of Computer Vision 12, 43–77 (1994)CrossRefGoogle Scholar
  7. 7.
    Black, M.J.: Frequently asked questions. Technical report, Department of Computer Science, Brown University (2005),
  8. 8.
    Ngo, C.W., Pong, T.C., Zhang, H.J.: Motion analysis and segmentation through spatio-temporal slices processing. IEEE Trans. Image Processing 12, 341–355 (2003)CrossRefGoogle Scholar
  9. 9.
    Knutsson, H., Andersson, M.: Loglets: Generalized quadrature and phase for local spatio-temporal structure estimation. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 741–748. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  10. 10.
    Austvoll, I.: Directional filters and a new structure for estimation of optical flow. In: Proc. Int. Conf. Image Proc., vol. II, pp. 574–577. IEEE Signal Processing Soc., Los Alamitos (2000)Google Scholar
  11. 11.
    Austvoll, I.: Motion Estimation using Directional Filters. PhD thesis, NTNU/HIS, PoBox 2557 Ullandhaug, N-4091 Stavanger, Norway (1999)Google Scholar
  12. 12.
    Pauwels, E.J., Van Gool, L.J., Fiddelaers, P., Moons, T.: An extended class of scale-invariant and recursive scale space filters. IEEE Trans. Pattern Anal. and Machine Intell. 17, 691–701 (1995)CrossRefGoogle Scholar
  13. 13.
    Fleet, D., Jepson, A.: Computation of component image velocity from local phase information. International Journal of Computer Vision 5, 77–104 (1990)CrossRefGoogle Scholar
  14. 14.
    Foroosh, H.: Pixelwise-adaptive blind optical flow assuming nonstationary statistics. IEEE Trans. Image Processing 14, 222–230 (2005)CrossRefGoogle Scholar
  15. 15.
    Brox, T., Bruhn, A., Papenberg, N., Joachim, W.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  16. 16.
    Bab-Hadiashar, A., Suter, D.: Robust optical flow computation. Int. J. of Computer Vision 29, 59–77 (1998)CrossRefGoogle Scholar
  17. 17.
    Liu, H., Chellappa, R., Rosenfeld, A.: Accurate dense optical flow estimation using adaptive structure tensors and a parametric model. IEEE Trans. Image Processing 12, 1170–1180 (2003)CrossRefGoogle Scholar
  18. 18.
    Farnebäck, G.: Very high accuracy velocity estimation using orientation tensors, parametric motion, and simultaneous segmentation of the motion field. In: Proc. Int. Conf. Comp. Vis., vol. I, pp. 171–177 (2001)Google Scholar
  19. 19.
    Mémin, E., Pérez, P.: Dense estimation and object-based segmentation of the optical flow with robust techniques. IEEE Trans. Image Processing 7, 703–719 (1998)CrossRefGoogle Scholar
  20. 20.
    Ju, S., Black, M.J., Jepson, A.D.: Skin and bones: Multi-layer, locally affine, optical flow and regularization with transparency. In: IEEE Conf. on Computer Vision and Pattern Recognition, CVPR 1996, San Francisco, CA, vol. 2182, pp. 307–314 (1996)Google Scholar
  21. 21.
    Chen, L.F., Liao, H.Y.M., Lin, J.C.: Wavelet-based optical flow estimation. IEEE Trans. Circuits and Systems for Video Tech. 12, 1–12 (2002)CrossRefGoogle Scholar
  22. 22.
    Granlund, G.H., Knutsson, H.: Signal Processing for Computer Vision. Kluwer Academic Publishers, Dordrecht (1995)Google Scholar
  23. 23.
    Robinson, D., Milanfar, P.: Fundamental performance limits in image registration. IEEE Trans. Image Processing 13, 1185–1199 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Ivar Austvoll
    • 1
  1. 1.Signal and Image Processing Group, Department of Electrical Engineering and Computer ScienceUniversity of StavangerStavangerNorway

Personalised recommendations