Abstract
In this chapter we review the estimation of the two-dimensional apparent motion field of two consecutive images in an image sequence. This apparent motion field is referred to as optical flow field, a two-dimensional vector field on the image plane. Because it is nearly impossible to cover the vast amount of approaches in the literature, in this chapter we set the focus on energy minimization approaches which estimate a dense flow field. The term dense refers to the fact that a flow vector is assigned to every (non-occluded) image pixel. Most dense approaches are based on the variational formulation of the optical flow problem, firstly suggested by Horn and Schunk. Depending on the application, density might be one important property besides accuracy and robustness. In many cases computational speed and real-time capability is a crucial issue. In this chapter we therefore discuss the latest progress in accuracy, robustness and real-time capability of dense optical flow algorithms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alvarez, L., EsclarÃn, J., Lefébure, M., Sánchez, J.: A PDE model for computing the optical flow. In: Proc. XVI Congreso de Ecuaciones Diferenciales y Aplicaciones, Gran Canaria, Spain, pp. 1349–1356 (1999)
Aubert, G., Deriche, R., Kornprobst, P.: Computing optical flow via variational techniques. SIAM J. Appl. Math. 60(1), 156–182 (1999)
Aujol, J.F., Gilboa, G., Chan, T.F., Osher, S.J.: Structure-texture image decomposition: modeling, algorithms, and parameter selection. Int. J. Comput. Vis. 67(1) (2006). doi:10.1007/s11263-006-4331-z
Baker, S., Matthews, I.: Lucas-Kanade 20 years on: a unifying framework. Int. J. Comput. Vis. 56(3), 221–255 (2004)
Baker, S., Roth, S., Scharstein, D., Black, M.J., Lewis, J.P., Szeliski, R.: AÂ database and evaluation methodology for optical flow. In: Online-Proc. International Conference on Computer Vision, Rio de Janeiro, Brazil, October 2007
Barni, M., Cappellini, V., Mecocci, A.: Fast vector median filter based on Euclidean norm approximation. IEEE Signal Process. Lett. 1(6), 92–94 (2004)
Black, M.J., Anandan, P.: A framework for the robust estimation of optical flow. In: Proc. International Conference on Computer Vision, Nice, France, pp. 231–236 (1993)
Brox, T.: From pixels to regions: partial differential equations in image analysis. Ph.D. thesis, Faculty of Mathematics and Computer Science, Saarland University, Germany (2005)
Brox, T., Malik, J.: Large displacement optical flow: descriptor matching in variational motion estimation. IEEE Trans. Pattern Anal. Mach. Intell. (2010). doi:10.1109/TPAMI.2010.143
Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Proc. European Conference on Computer Vision, Prague, Czech Republic, pp. 25–36 (2004)
Bruhn, A., Weickert, J., Feddern, C., Kohlberger, T., Schnörr, C.: Variational optic flow computation in real-time. IEEE Trans. Image Process. 14(5), 608–615 (2005)
Bruhn, A., Weickert, J., Kohlberger, T., Schnörr, C.: A multigrid platform for real-time motion computation with discontinuity-preserving variational methods. Int. J. Comput. Vis. 70(3), 257–277 (2006)
Chambolle, A.: An algorithm for total variation minimization and applications. J. Math. Imaging Vis. 20(1), 89–97 (2004)
Chambolle, A.: Total variation minimization and a class of binary MRF models. In: Proc. International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition, St. Augustine, FL, USA, pp. 136–152 (2005)
Chambolle, A., Caselles, V., Cremers, D., Novaga, M., Pock, T.: An introduction to total variation for image analysis. In: Theoretical Foundations and Numerical Methods for Sparse Recovery. De Gruyter, Berlin (2010)
Chan, T.F., Golub, G.H., Mulet, P.: A nonlinear primal-dual method for total variation-based image restoration. SIAM J. Appl. Math. 20(10), 1964–1977 (1999)
Cohen, I.: Nonlinear variational method for optical flow computation. In: Scandinavian Conf. on Image Analysis, pp. 523–523 (1993)
Coleman, T.F., Hulbert, L.A.: A direct active set algorithm for large sparse quadratic programs with simple bounds. Math. Program., Sers. A, B 45(3), 373–406 (1989)
Cooke, T.: Two applications of graph-cuts to image processing. In: Digital Image Computing: Techniques and Applications (DICTA), Canberra, Australia, pp. 498–504 (2008)
Corpetti, T., Memin, E., Perez, P.: Dense estimation of fluid flows. IEEE Trans. Pattern Anal. Mach. Intell. 24(3), 365–380 (2002)
Deriche, R., Kornprobst, P., Aubert, G.: Optical flow estimation while preserving its discontinuities: a variational approach. In: Proc. Asian Conference on Computer Vision, Singapore, pp. 290–295 (1995)
Devillard, N.: Fast median search: an ANSI C implementation (1998). http://ndevilla.free.fr/median/median/index.html
Felsberg, M.: On the relation between anisotropic diffusion and iterated adaptive filtering. In: Pattern Recognition (Proc. DAGM), Munich, Germany, pp. 436–445 (2008)
Goldluecke, B., Cremers, D.: Convex relaxation for multilabel problems with product label spaces. In: Proc. European Conference on Computer Vision (2010)
Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artif. Intell. 17(1–3), 185–203 (1981)
Karush, W.: Minima of functions of several variables with inequalities as side constraints. Ph.D. thesis, Dept. of Mathematics, University of Chicago (1939)
Klappstein, J.: Optical-flow based detection of moving objects in traffic scenes. Ph.D. thesis, University of Heidelberg, Heidelberg, Germany (2008)
Lempitsky, V., Roth, S., Rother, C.: Fusionflow: discrete-continuous optimization for optical flow estimation. In: Online-Proc. International Conference on Computer Vision and Pattern Recognition, Anchorage, USA, June 2008
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proc. of the 7th International Joint Conference on Artificial Intelligence (IJCAI), Vancouver, British Columbia, Canada, pp. 674–679 (1981)
Luenberger, D.G.: Linear and Nonlinear Programming. Addison-Wesley, Reading (1984)
Masoomzadeh-Fard, A., Venetsanopoulos, A.N.: An efficient vector ranking filter for colour image restoration. In: Proc. Canadian Conference on Electrical and Computer Engineering, Vancouver, BC, Canada, pp. 1025–1028 (1993)
Mémin, E., Pérez, P.: A multigrid approach for hierarchical motion estimation. In: Proc. International Conference on Computer Vision, Bombay, India, pp. 933–938 (1998)
Nagel, H.H., Enkelmann, W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Trans. Pattern Anal. Mach. Intell. 8(5), 565–593 (1986)
Nagel, H.H.: Constraints for the estimation of displacement vector fields from image sequences. In: Proc. Eighth Int. Conf. Artif. Intell., Karlsruhe, Germany, pp. 945–951 (1983)
Nagel, H.-H., Enkelmann, W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Trans. Pattern Anal. Mach. Intell. 8(5), 565–593 (1986)
Papenberg, N., Bruhn, A., Brox, T., Didas, S., Weickert, J.: Highly accurate optic flow computation with theoretically justified warping. Int. J. Comput. Vis. 67(2), 141–158 (2006)
Pock, T.: Fast total variation for computer vision. Ph.D. thesis, Institute for Computer Graphics and Vision, University of Graz, Graz, Austria (2008)
Rabe, C., Volmer, C., Franke, U.: Kalman filter based detection of obstacles and lane boundary. Autonome Mobile Systeme 19(1), 51–58 (2005)
Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D 60(1–4), 259–268 (1992)
Ruhnau, P., Schnoerr, C.: Variational estimation of experimental fluid flows with physics-based spatio-temporal regularization. Meas. Sci. Technol. 18, 755–763 (2007)
Schnörr, C.: Segmentation of visual motion by minimizing convex non-quadratic functionals. In: 12th Int. Conf. on Pattern Recognition, Jerusalem, Israel, pp. 661–663 (1994)
Spies, H., Kirchges̈ner, N., Scharr, H., Jähne, B.: Dense structure estimation via regularised optical flow. In: Proc. Vision, Modeling, and Visualization, Saarbrücken, Germany, pp. 57–64 (2000)
Stein, F.: Efficient computation of optical flow using the Census transform. In: Pattern Recognition (Proc. DAGM), Tübingen, Germany, pp. 79–86 (2004)
Steinbruecker, F., Pock, T., Cremers, D.: Large displacement optical flow computation without warping. In: IEEE International Conference on Computer Vision (ICCV), Kyoto, Japan (2009)
Stewart, E.: Intel Integrated Performance Primitives: How to Optimize Software Applications Using Intel Ipp. Intel Press, Santa Clara (2004)
Sun, D., Roth, S., Lewis, J.P., Black, M.J.: Learning optical flow. In: Proc. European Conference on Computer Vision, Marseille, France, pp. 83–91 (2008)
Sun, D., Roth, S., Black, M.J.: Secrets of optical flow estimation and their principles. In: Proc. International Conference on Computer Vision and Pattern Recognition, pp. 2432–2439 (2010)
Tomasi, C., Kanade, T.: Detection and tracking of point features. Technical Report CMU-CS-91-132, Carnegie Mellon University, April 1991
Trobin, W., Pock, T., Cremers, D., Bischof, H.: Continuous energy minimization via repeated binary fusion. In: European Conference on Computer Vision (ECCV), Marseille, France, October 2008
Trobin, W., Pock, T., Cremers, D., Bischof, H.: An unbiased second-order prior for high-accuracy motion estimation. In: Pattern Recognition (Proc. DAGM), Munich, Germany, pp. 396–405 (2008)
Unger, M., Pock, T., Bischof, H.: Continuous globally optimal image segmentation with local constraints. In: Computer Vision Winter Workshop, February 2008
Weickert, J., Brox, T.: Diffusion and regularization of vector- and matrix-valued images. In: Inverse Problems, Image Analysis and Medical Imaging. Contemporary Mathematics vol. 313, pp. 251–268. AMS, Providence (2002)
Weickert, J., Schnörr, C.: A theoretical framework for convex regularizers in PDE-based computation of image motion. Int. J. Comput. Vis. 45(3), 245–264 (2001)
Yang, Z., Fox, M.D.: Speckle reduction and structure enhancement by multichannel median boosted anisotropic diffusion. EURASIP J. Appl. Signal Process. 2492–2502 (2004). doi:10.1155/S1110865704402091
Yin, W., Goldfarb, D., Osher, S.: Image cartoon-texture decomposition and feature selection using the total variation regularized L 1 functional. In: Variational, Geometric, and Level Set Methods in Computer Vision, Beijing, China, pp. 73–80 (2005)
Zabih, R., Woodfill, J.: Non-parametric local transforms for computing visual correspondence. In: Proc. European Conference on Computer Vision, Prague, Czech Republic, pp. 151–158 (2004)
Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L1 optical flow. In: Pattern Recognition (Proc. DAGM), Heidelberg, Germany, pp. 214–223 (2007)
Zach, C., Gallup, D., Frahm, J.M.: Fast gain-adaptive KLT tracking on the GPU. In: Online-Proc. International Conference on Computer Vision and Pattern Recognition, Anchorage, AK, June 2008
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2011 Springer-Verlag London Limited
About this chapter
Cite this chapter
Wedel, A., Cremers, D. (2011). Optical Flow Estimation. In: Stereo Scene Flow for 3D Motion Analysis. Springer, London. https://doi.org/10.1007/978-0-85729-965-9_2
Download citation
DOI: https://doi.org/10.1007/978-0-85729-965-9_2
Publisher Name: Springer, London
Print ISBN: 978-0-85729-964-2
Online ISBN: 978-0-85729-965-9
eBook Packages: Computer ScienceComputer Science (R0)