Abstract
Selecting optimal models and hyper-parameters is crucial for accurate optic-flow estimation. This paper solves the problem in a generic variational Bayesian framework. The method is based on a conditional model linking the image intensity function, the velocity field and the hyper-parameters characterizing the motion model. Inference is performed at three levels by considering maximum a posteriori problem of marginalized probabilities. We assessed the performance of the proposed method on image sequences of fluid flows and of the “Middlebury” database. Experiments prove that applying the proposed inference strategy on very simple models yields better results than manually tuning smoothing parameters or discontinuity preserving cost functions of classical state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Jaynes, E.T.: Bayesian methods: General background (1986)
Molina, R., Katsaggelos, A.K., Mateos, J.: Bayesian and regularization methods for hyperparameter estimation in image restoration. IEEE Trans. Image Processing 8, 231–246 (1999)
MacKay, D.J.C.: Bayesian interpolation. Neural Computation 4, 415–447 (1992)
Krajsek, K., Mester, R.: Bayesian model selection for optical flow estimation. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 142–151. Springer, Heidelberg (2007)
Nir, T., Bruckstein, A.M., Kimmel, R.: Over-parameterized variational optical flow. Int. J. Comput. Vision 76, 205–216 (2008)
Heas, P., Memin, E., Heitz, D., Mininni, P.: Bayesian selection of scaling laws for motion modeling in images. In: International Conference on Computer Vision (ICCV 2009), Kyoto, Japan (2009)
Liu, T., Shen, L.: Fluid flow and optical flow. Journal of Fluid Mechanics 614, 253 (2008)
Horn, B., Schunck, B.: Determining optical flow. Artificial Intelligence 17, 185–203 (1981)
Black, M., Anandan, P.: The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Computer Vision and Image Understanding 63, 75–104 (1996)
Geman, D., Reynolds, G.: Constrained restoration and the recovery of discontinuities. IEEE Trans. Pattern Anal. Mach. Intell. 14, 367–383 (1992)
Nocedal, J., Wright, S.J.: Numerical Optimization. Springer Series in Operations Research. Springer, New York (1999)
Bruhn, A., Weickert, J., Kohlberger, T., Schnorr, C.: A multigrid platform for real-time motion computation with discontinuity-preserving variational methods. International Journal of Computer Vision 70, 257–277 (2006)
Jordan, M.I., Ghahramani, Z., Jaakkola, T.S., Saul, L.: An introduction to variational methods for graphical models. Machine Learning 37, 183–233 (1999)
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)
Noels, N., Steendam, H., Moeneclaey, M.: The true cramer-rao bound for phase-independent carrier frequency estimation from a psk signal. In: IEEE Global Telecommunications Conference 2002, pp. 1137–1141 (2002)
Yuan, J., Schnoerr, C., Memin, E.: Discrete orthogonal decomposition and variational fluid flow estimation. Journ. of Math. Imaging & Vison 28, 67–80 (2007)
Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M., Szeliski, R.: A database and evaluation methodology for optical flow. In: Int. Conf. on Comp. Vis., ICCV 2007 (2007)
Carlier, J., Wieneke, B.: Report 1 on production and diffusion of fluid mechanics images and data. Fluid project deliverable 1.2 (2005), http://www.fluid.irisa.fr
Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereovision. In: Int. Joint Conf. on Artificial Intel. (IJCAI), pp. 674–679 (1981)
Zitnick, C., Jojic, N., Kang, S.B.: Consistent segmentation for optical flow estimation. In: Tenth IEEE International Conference on Computer Vision (ICCV 2005), vol. 2, pp. 1308–1315 (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
Héas, P., Herzet, C., Mémin, E. (2012). Robust Optic-Flow Estimation with Bayesian Inference of Model and Hyper-parameters. In: Bruckstein, A.M., ter Haar Romeny, B.M., Bronstein, A.M., Bronstein, M.M. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2011. Lecture Notes in Computer Science, vol 6667. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24785-9_65
Download citation
DOI: https://doi.org/10.1007/978-3-642-24785-9_65
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24784-2
Online ISBN: 978-3-642-24785-9
eBook Packages: Computer ScienceComputer Science (R0)