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.
Chapter PDF
Similar content being viewed by others
Keywords
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.
References
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)
Horn, B., Schunck, B.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)
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)
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)
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)
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)
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)
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)
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)
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)
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)
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)
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)
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)
Chambolle, A.: An algorithm for total variation minimization and applications. Journal of Mathematical Imaging and Vision 20, 89–97 (2004)
Weickert, J., Schnörr, C.: Variational optic flow computation with a spatio-temporal smoothness constraint. Journal of Mathematical Imaging and Vision 14, 245–255 (2001)
Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D 60, 259–268 (1992)
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)
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)
Perona, P., Malik, J.: Scale space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence 12, 629–639 (1990)
Gentzsch, W., Schlüter, A.: Über ein Einschrittverfahren mit zyklischer Schrittweitenänderung zur Lösung parabolischer Differentialgleichungen. Zeitschrift für angewandte Mathematik und Mechanik 58, T415–T416 (1978)
Trottenberg, U., Oosterlee, C., Schüller, A.: Multigrid. Academic Press, San Diego (2001)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gwosdek, P., Zimmer, H., Grewenig, S., Bruhn, A., Weickert, J. (2012). A Highly Efficient GPU Implementation for Variational Optic Flow Based on the Euler-Lagrange Framework. In: Kutulakos, K.N. (eds) Trends and Topics in Computer Vision. ECCV 2010. Lecture Notes in Computer Science, vol 6554. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35740-4_29
Download citation
DOI: https://doi.org/10.1007/978-3-642-35740-4_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35739-8
Online ISBN: 978-3-642-35740-4
eBook Packages: Computer ScienceComputer Science (R0)