Advertisement

A Highly Efficient GPU Implementation for Variational Optic Flow Based on the Euler-Lagrange Framework

  • Pascal Gwosdek
  • Henning Zimmer
  • Sven Grewenig
  • Andrés Bruhn
  • Joachim Weickert
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6554)

Abstract

The Euler-Lagrange (EL) framework is the most widely-used strategy for solving variational optic flow methods. We present the first approach that solves the EL equations of state-of-the-art methods on sequences with \(640 \!\times\! 480\) pixels in near-realtime on GPUs. This performance is achieved by combining two ideas: (i) We extend the recently proposed Fast Explicit Diffusion (FED) scheme to optic flow, and additionally embed it into a coarse-to-fine strategy. (ii) We parallelise our complete algorithm on a GPU, where a careful optimisation of global memory operations and an efficient use of on-chip memory guarantee a good performance. Applying our approach to the variational ‘Complementary Optic Flow’ method (Zimmer et al. (2009)), we obtain highly accurate flow fields in less than a second. This currently constitutes the fastest method in the top 10 of the widely used Middlebury benchmark.

Keywords

Global Memory Data Term Smoothness Term British Machine Vision Constancy Assumption 
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.
Download to read the full conference paper text

References

  1. 1.
    Baker, S., Roth, S., Scharstein, D., Black, M.J., Lewis, J.P., Szeliski, R.: A database and evaluation methodology for optical flow. In: Proc. 2007 IEEE International Conference on Computer Vision. IEEE Computer Society Press, Rio de Janeiro (2007)Google Scholar
  2. 2.
    Horn, B., Schunck, B.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)CrossRefGoogle Scholar
  3. 3.
    Nagel, H.H., Enkelmann, W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Transactions on Pattern Analysis and Machine Intelligence 8, 565–593 (1986)CrossRefGoogle Scholar
  4. 4.
    Simoncelli, E.P., Adelson, E.H., Heeger, D.J.: Probability distributions of optical flow. In: Proc. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 310–315. IEEE Computer Society Press, Maui (1991)CrossRefGoogle Scholar
  5. 5.
    Black, M.J., Anandan, P.: The robust estimation of multiple motions: parametric and piecewise smooth flow fields. Computer Vision and Image Understanding 63, 75–104 (1996)CrossRefGoogle Scholar
  6. 6.
    Weickert, J., Schnörr, C.: A theoretical framework for convex regularizers in PDE-based computation of image motion. International Journal of Computer Vision 45, 245–264 (2001)CrossRefzbMATHGoogle Scholar
  7. 7.
    Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High Accuracy Optical Flow Estimation Based on a Theory for Warping. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  8. 8.
    Sun, D., Roth, S., Lewis, J.P., Black, M.J.: Learning Optical Flow. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 83–97. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  9. 9.
    Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: Anisotropic Huber-L 1 optical flow. In: Proc. 20th British Machine Vision Conference. British Machine Vision Association, London (2009)Google Scholar
  10. 10.
    Zimmer, H., Bruhn, A., Weickert, J., Valgaerts, L., Salgado, A., Rosenhahn, B., Seidel, H.-P.: Complementary Optic Flow. In: Cremers, D., Boykov, Y., Blake, A., Schmidt, F.R. (eds.) EMMCVPR 2009. LNCS, vol. 5681, pp. 207–220. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  11. 11.
    Zach, C., Pock, T., Bischof, H.: A Duality Based Approach for Realtime TV- L1 Optical Flow. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214–223. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  12. 12.
    Bruhn, A., Weickert, J.: Towards ultimate motion estimation: Combining highest accuracy with real-time performance. In: Proc. of the Tenth International Conference on Computer Vision, vol. 1, pp. 749–755. IEEE Computer Society Press, Beijing (2005)Google Scholar
  13. 13.
    El Kalmoun, M., Köstler, H., Rüde, U.: 3D optical flow computation using a parallel variational multigrid scheme with application to cardiac C-arm CT motion. Image and Vision Computing 25, 1482–1494 (2007)CrossRefGoogle Scholar
  14. 14.
    Grossauer, H., Thoman, P.: GPU-Based Multigrid: Real-Time Performance in High Resolution Nonlinear Image Processing. In: Gasteratos, A., Vincze, M., Tsotsos, J.K. (eds.) ICVS 2008. LNCS, vol. 5008, pp. 141–150. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  15. 15.
    Chambolle, A.: An algorithm for total variation minimization and applications. Journal of Mathematical Imaging and Vision 20, 89–97 (2004)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Weickert, J., Schnörr, C.: Variational optic flow computation with a spatio-temporal smoothness constraint. Journal of Mathematical Imaging and Vision 14, 245–255 (2001)CrossRefzbMATHGoogle Scholar
  17. 17.
    Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D 60, 259–268 (1992)CrossRefzbMATHGoogle Scholar
  18. 18.
    Grewenig, S., Weickert, J., Bruhn, A.: From Box Filtering to Fast Explicit Diffusion. In: Goesele, M., Roth, S., Kuijper, A., Schiele, B., Schindler, K. (eds.) DAGM 2010. LNCS, vol. 6376, pp. 533–542. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  19. 19.
    NVIDIA Corporation: NVIDIA CUDA Programming Guide. 3rd edn.(2010), http://developer.download.nvidia.com/compute/cuda/3_0/toolkit/docs/NVIDIA_CUDA_ProgrammingGuide.pdf (retrieved June 10, 2009)
  20. 20.
    Perona, P., Malik, J.: Scale space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence 12, 629–639 (1990)CrossRefGoogle Scholar
  21. 21.
    Gentzsch, W., Schlüter, A.: Über ein Einschrittverfahren mit zyklischer Schrittweitenänderung zur Lösung parabolischer Differentialgleichungen. Zeitschrift für angewandte Mathematik und Mechanik 58, T415–T416 (1978)Google Scholar
  22. 22.
    Trottenberg, U., Oosterlee, C., Schüller, A.: Multigrid. Academic Press, San Diego (2001)zbMATHGoogle Scholar
  23. 23.
    Bruhn, A., Weickert, J., Feddern, C., Kohlberger, T., Schnörr, C.: Variational optical flow computation in real-time. IEEE Transactions on Image Processing 14, 608–615 (2005)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Pascal Gwosdek
    • 1
  • Henning Zimmer
    • 1
  • Sven Grewenig
    • 1
  • Andrés Bruhn
    • 2
  • Joachim Weickert
    • 1
  1. 1.Mathematical Image Analysis Group, Faculty of Mathematics and Computer ScienceSaarland UniversitySaarbrückenGermany
  2. 2.Vision and Image Processing Group,Cluster of Excellence Multimodal Computing and InteractionSaarland UniversitySaarbrückenGermany

Personalised recommendations

Cite paper