A Complete Confidence Framework for Optical Flow

  • Patricia Márquez-Valle
  • Debora Gil
  • Aura Hernàndez-Sabaté
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7584)


Assessing the performance of optical flow in the absence of ground truth is of prime importance for a correct interpretation and application. Thus, in recent years, the interest in developing confidence measures has increased. However, by its complexity, assessing the capability of such measures for detecting areas of poor performance of optical flow is still unsolved.

We define a confidence measure in the context of numerical stability of the optical flow scheme and also a protocol for assessing its capability to discard areas of non-reliable flows. Results on the Middlebury database validate our framework and show that, unlike existing measures, our measure is not biased towards any particular image feature.


Optical flow confidence measures sparsification plots error prediction plots 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: DARPA IU Workshop, pp. 121–130 (1981)Google Scholar
  2. 2.
    Barron, J.L., Fleet, D.J., Beauchemin, S.S.: Performance of optical flow techniques. IJCV 12(1), 43–77 (1994)CrossRefGoogle Scholar
  3. 3.
    Horn, B., Schunck, B.: Determining optical flow. AI 17, 185–203 (1981)Google Scholar
  4. 4.
    Nagel, H.H., Enkelmann, W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. PAMI 8, 565–593 (1986)CrossRefGoogle Scholar
  5. 5.
    Sun, D., Roth, S., Black, M.J.: Secrets of optical flow estimation and their principles. In: CVPR, pp. 2432–2439 (2010)Google Scholar
  6. 6.
    Bigün, J., Granlund, G.H., Wiklund, J.: Multidimensional orientation estimation with applications to texture analysis and optical flow. PAMI 13(8), 775–790 (1991)CrossRefGoogle Scholar
  7. 7.
    Bruhn, A., Weickert, J., Schnörr, C.: Lucas/Kanade meets Horn/Schunck: Combining local and global optic flow methods. IJCV 61(2), 221–231 (2005)Google Scholar
  8. 8.
    García-Barnés, J.: Variational framework for assessment of the left ventricle motion. Math. Mod. of Nat. Phen. 3(6), 76 (2008)CrossRefGoogle Scholar
  9. 9.
    Weickert, J., Schnörr, C.: A theoretical framework for convex regularizers in pde-based computation of image motion. IJCV 45, 245–264 (2001)zbMATHCrossRefGoogle Scholar
  10. 10.
    Kondermann, C., Mester, R., Garbe, C.: A Statistical Confidence Measure for Optical Flows. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 290–301. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  11. 11.
    Bruhn, A., Weickert, J.: A confidence measure for variational optic flow methods. In: Geometric Properties for Incomplete Data, pp. 283–298 (2006)Google Scholar
  12. 12.
    Kybic, J., Nieuwenhuis, C.: Bootstrap optical flow confidence and uncertainty measure. Computer Vision and Image Understanding, 1449–1462 (2011)Google Scholar
  13. 13.
    Cheney, W., Kincaid, D.: Numerical Mathematics and Computing, 6th edn. Bob Pirtle, USA (2008)Google Scholar
  14. 14.
    Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. IJCV 92(1), 1–31 (2011)CrossRefGoogle Scholar
  15. 15.
    Haussecker, H., Spies, H.: Handbook of Computer Vision and Applications, vol. 2. Academic Press (1999)Google Scholar
  16. 16.
    Shi, J., Tomasi, C.: Good features to track, pp. 593–600 (1994)Google Scholar
  17. 17.
    Newbold, P., Carlson, W., Thorne, B.: Statistics for Business and Economics. Pearson Education (2007)Google Scholar
  18. 18.
    Liu, C.: Beyond pixels: exploring new representations and applications for motion analysis. Ph.D. dissertation, Cambridge, MA, USA (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Patricia Márquez-Valle
    • 1
  • Debora Gil
    • 1
  • Aura Hernàndez-Sabaté
    • 1
  1. 1.Computer Vision CenterEdifici O, Campus UABBarcelonaSpain

Personalised recommendations