Skip to main content

Approximate Regularization for Structural Optical Flow Estimation

  • Conference paper

Part of the Lecture Notes in Computer Science book series (LNIP,volume 7517)

Abstract

We address the problem of maximum a posteriori (MAP) estimation of optical flow with a geometric prior from gray-value images. We estimate simultaneously the optical flow and the corresponding surface – the structural optical flow (SOF) – subject to three types of constraints: intensity constancy, geometric, and smoothness constraints. Our smoothness constraints restrict the unknowns to locally coincide with a set of finitely parameterized admissible functions. The geometric constraints locally enforce consistency between the optical flow and the corresponding surface. Our theory amounts to a discrete generalization of regularization defined in terms of partial derivatives. The point-wise regularizers are efficiently implemented with linear run-time complexity in the number of discretization points. We demonstrate the applicability of our method by example computations of SOF from photographs of human faces.

Keywords

  • Optical flow
  • Approximation theory
  • Bayesian model

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-642-33140-4_30
  • Chapter length: 13 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   64.99
Price excludes VAT (USA)
  • ISBN: 978-3-642-33140-4
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   84.99
Price excludes VAT (USA)

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. McCane, B., Novins, K., Crannitch, D., Galvin, B.: On Benchmarking Optical Flow. Computer Vision and Image Understanding 84(1) (2001)

    Google Scholar 

  2. Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press (2000)

    Google Scholar 

  3. Horn, B.K., Schunck, B.G.: Determining optical flow. Technical report, Massachusetts Institute of Technology, Cambridge, MA, USA (1980)

    Google Scholar 

  4. Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High Accuracy Optical Flow Estimation Based on a Theory for Warping. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004)

    CrossRef  Google Scholar 

  5. Bruhn, A., Weickert, J., Schnörr, C.: Lucas/kanade meets horn/schunck: combining local and global optic flow methods. Int. J. Comput. Vision 61, 211–231 (2005)

    CrossRef  Google Scholar 

  6. 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)

    CrossRef  Google Scholar 

  7. Lucas, B.D., Kanade, T.: An Iterative Image Registration Technique with an Application to Stereo Vision. In: IJCA 1981, vol. 81, pp. 674–679 (1981)

    Google Scholar 

  8. Kanatani, K.: Statistical Optimization for Geometric Computation: Theory and Practice. Elsevier Science Inc., New York (1996)

    MATH  Google Scholar 

  9. Li, S.Z.: Markov random field modeling in image analysis. Springer-Verlag New York, Inc., Secaucus (2001)

    MATH  Google Scholar 

  10. Nir, T., Bruckstein, A.M., Kimmel, R.: Over-parameterized variational optical flow. Int. J. Comput. Vision 76, 205–216 (2008)

    CrossRef  Google Scholar 

  11. Lamovsky, D.V., Lasaruk, A.: Calibration and Reconstruction Algorithms for a Handheld 3D Laser Scanner. In: Blanc-Talon, J., Kleihorst, R., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2011. LNCS, vol. 6915, pp. 635–646. Springer, Heidelberg (2011)

    CrossRef  Google Scholar 

  12. Corrochano, E.B., Förstner, W.: Uncertainty and projective geometry. In: Handbook of Geometric Computing, pp. 493–534. Springer, Heidelberg (2005)

    Google Scholar 

  13. Hoeffken, M., Oberhoff, D., Kolesnik, M.: Temporal Prediction and Spatial Regularization in Differential Optical Flow. In: Blanc-Talon, J., Kleihorst, R., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2011. LNCS, vol. 6915, pp. 576–585. Springer, Heidelberg (2011)

    CrossRef  Google Scholar 

  14. Cheney, E.: Introduction to approximation theory. AMS Chelsea Publishing Series. AMS Chelsea Pub. (1982)

    Google Scholar 

  15. Björck, Å.: Numerical Methods for Least Squares Problems. SIAM, Philadelphia (1996)

    MATH  CrossRef  Google Scholar 

  16. Salvi, J., Matabosch, C., Fofi, D., Forest, J.: A review of recent range image registration methods with accuracy evaluation. Image Vision Comput. 25, 578–596 (2007)

    CrossRef  Google Scholar 

  17. Wackernagel, H.: Multivariate Geostatistics: An Introduction With Applications. Springer (2003)

    Google Scholar 

  18. Liu, C., Freeman, W.T., Szeliski, R., Kang, S.B.: Noise estimation from a single image. IEEE Computer Vision and Pattern Recognition 1, 901–908 (2006)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2012 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Lasaruk, A. (2012). Approximate Regularization for Structural Optical Flow Estimation. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P., Zemčík, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2012. Lecture Notes in Computer Science, vol 7517. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33140-4_30

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-33140-4_30

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-33139-8

  • Online ISBN: 978-3-642-33140-4

  • eBook Packages: Computer ScienceComputer Science (R0)