Skip to main content
SpringerLink
Log in

A Geometric Framework and a New Criterion in Optical Flow Modeling

  • Published:
Journal of Mathematical Imaging and Vision Aims and scope Submit manuscript

Abstract

We evaluate the dense optical flow between two frames via variational approach. In this paper, a new framework for deriving the regularization term is introduced giving a geometric insight into the action of a smoothing term. The framework is based on the Beltrami paradigm in image denoising. It includes a general formulation that unifies several previous methods. Using the proposed framework we also derive two novel anisotropic regularizers incorporating a new criterion that requires co-linearity between the gradients of optical flow components and possibly the intensity gradient. We call this criterion “alignment” and reveal its existence also in the celebrated Nagel and Enkelmann’s formulation. It is shown that the physical model of rotational motion of a rigid body, pure divergent/convergent flow and irrotational fluid flow, satisfy the alignment criterion in the flow field. Experimental tests in comparison to a recently published method show the capability of the new criterion in improving the optical flow estimations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Alemán, M., Alvarez, L., Gonzalez, E., Mazorra, L., Sàchez, J.: Optic flow estimation in fluid images I. Technical Report 31, Cuadernos Instituto Universitario de Ciencias y Tecnologias Cibernéticas (2005)

  2. Alvarez, L., Weickert, J., Sànchez, J.: Reliable estimation of dense optical flow fields with large displacements. Int. J. Comput. Vis. 39(1), 41–56 (2000)

    Article  MATH  Google Scholar 

  3. Amiaz, T., Kiryati, N.: Dense discontinuous optical flow via contour based segmentation. In: Proc. ICIP 2005, vol. 3, pp. 1264–1267 (2005)

  4. Anderson, J.D.: Fundamentals of Aerodynamic. McGraw-Hill, Singapore (1991)

    Google Scholar 

  5. Aubert, G., Kornprobst, P.: A mathematical study of the relaxed optical flow problem in the BV(Ω) space. SIAM J. Appl. Math. 30(6), 1282–1308 (1999)

    Article  MATH  MathSciNet  Google Scholar 

  6. Aubert, G., Deriche, R., Kornprobst, P.: Computing optical flow via variational techniques. SIAM J. Appl. Math. 60(1), 156–182 (2000)

    Article  MathSciNet  Google Scholar 

  7. Baker, S., Scharstein, D., Lewis, J.P.: A data base and evaluation methodology for optical flow. In: Proc. ICCV (2007)

  8. Barron, J.L., Fleet, D.J., Beauchemin, S.S.: Performance of optical flow techniques. Int. J. Comput. Vis. 12 (1994)

  9. Ben-Ari, R., Sochen, N.: A general framework and new alignment criterion for dense optical flow. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 529–536 (2006)

  10. Bertero, M., Poggio, T.A., Torre, V.: Ill-posed problems in early vision. Proc. IEEE 76(8), 869–889 (1998)

    Article  Google Scholar 

  11. Black, M.J., Anandan, P.: The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Comput. Vis. Image Underst. 63 (1996)

  12. Black, M.J., Fleet, D.J.: Probabilistic detection and tracking of motion boundaries. Comput. Vis. Image Underst. 38 (2000)

  13. Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Proc. of 8th European Conference on Computer Vision. LNCS, vol. 3024, pp. 25–36. Springer, Berlin (2004)

    Google Scholar 

  14. Brox, T., Bruhn, A., Weickert, J.: Variational motion segmentation with level sets. In: Proc. of 9th European Conference on Computer Vision. LNCS, vol. 3951, pp. 471–483. Springer, Berlin (2006)

    Google Scholar 

  15. Carlier, J.: Second set of fluid mechanics image sequences-fluid image analysis and description. Technical Report FP 6-513663, University of Mannheim, CVGPR Group (2006)

  16. Corpetti, T., Mèmin, È., Pèrez, P.: Dense estimation of fluid flows. IEEE Trans. Pattern Anal. Mach. Intell. 24(3), 365–380 (2002)

    Article  Google Scholar 

  17. Cremers, D.: A variational framework for image segmentation combining motion estimation and shape regularization. In: Proc. CVPR, vol. 1, pp. 53–58 (2003)

  18. Cremers, D., Schnörr, C.: Motion competition: Variational integration of motion segmentation and shape regularization. In: Van Gool, L. (ed.) German Conf. on Pattern Recognition. LNCS, vol. 2449, pp. 472–480. Springer, Berlin (2002)

    Google Scholar 

  19. Cremers, D., Soatto, S.: Motion competition: A variational framework for piecewise parametric motion segmentation. Int. J. Comput. Vis. 62, 249–265 (2005)

    Article  Google Scholar 

  20. Cuzol, A., Hellier, P., Mèmin, È.: A low dimensional fluid motion estimator. Int. J. Comput. Vis. 75(3), 329–349 (2007)

    Article  Google Scholar 

  21. Deriche, R., Kornprobst, P., Aubert, G.: Optical flow estimation while preserving its discontinuities: A variational approach. In: Proc. Second Asian Conference on Computer Vision, vol. 2, pp. 290–295 (1995)

  22. Faugeras, O.: Three Dimensional Computer Vision: A Geometric Viewpoint. MIT Press, Cambridge (1993)

    Google Scholar 

  23. Fleet, D.J., Jepson, A.D.: Computation of component image velocity from local phase information. Int. J. Comput. Vis. 5(1), 77–104 (1990)

    Article  Google Scholar 

  24. Horn, B., Schunck, B.: Determining optical flow. Artif. Intell. 17, 185–203 (1981)

    Article  Google Scholar 

  25. KOGS/IAKS Universität Karlsruhe. http://i21www.ira.uka.de/image_sequences

  26. Kimmel, R., Malladi, R., Sochen, N.: Images as embedded maps and minimal surfaces: movies, color, texture, and volumetric medical images. Int. J. Comput. Vis. 39(2), 111–129 (2000)

    Article  MATH  Google Scholar 

  27. Kreyszig, E.: Differential Geometry. Dover, New York (1991)

    Google Scholar 

  28. Lucas, B., Kanade, T.: An iterative image registration technique with application to stereo vision. In: Proc. DARPA Image Understanding Workshop, pp. 121–130 (1981)

  29. Mémin, E., Pérez, P.: Dense estimation and object-based segmentation of the optical flow with robust techniques. IEEE Trans. Image Process. 7(5), 703–719 (1998)

    Article  Google Scholar 

  30. The Middlebury Computer Vision Page. http://vision.middlebury.edu/flow/

  31. Mitiche, A., Bouthemy, P.: Computation and analysis of image motion: A synopsis of current problems and methods. Int. J. Comput. Vis. 19, 29–55 (1998)

    Article  Google Scholar 

  32. Nagel, H.H.: Constraints for the estimation of displacement vector fields from image sequences. In: Proc. Eighth Int. Joint Conf. on Artificial Intelligence, pp. 945–951 (1983)

  33. Nagel, H.H., Enkelmann, W.: An investigation of smoothness constraints for estimation of displacement vector fields from image sequences. IEEE Trans. Pattern Anal. Mach. Intell. 8, 565–593 (1986)

    Article  Google Scholar 

  34. Computer Vision Research Group-University of Otago. http://www.katipo.otago.ac.nz/research/vision/

  35. Papenberg, N., Bruhn, A., Brox, T., Weickert, S., Didas, J.: Highly accurate optical flow computation with theoretically justified warping. Int. J. Comput. Vis. 69(1), 91–103 (2006)

    Google Scholar 

  36. Polyakov, A.M.: Quantum geometry of bosonic strings. Phys. Lett. B 103, 207–210 (1981)

    Article  MathSciNet  Google Scholar 

  37. Proesmans, M., Pauwels, E., Van Gool, M., Oostrelinck, A.: Determination of optical flow and its discontinuities using non-linear diffusion. In: Proc. of European Conference on Computer Vision. LNCS, vol. 801, pp. 295–304. Springer, Berlin (1994)

    Google Scholar 

  38. The Fluid Project. http://www.fluid.irisa.fr/data-eng.htm

  39. Ruhnau, P., Schnörr, C.: Optical stokes flow estimation: an imaging based control approach. Exp. Fluids 42(1), 61–78 (2007)

    Article  Google Scholar 

  40. Sapiro, G., Ringach, D.: Anisotropic diffusion of multi-valued images. In: 12th International Conference on Analysis and Optimization of Systems: Images, Wavelets and PDE’s, vol. 219

  41. Sochen, N., Kimmel, R., Malladi, R.: A general framework for low level vision. IEEE Trans. Image Process. 7, 310–318 (1998)

    Article  MATH  MathSciNet  Google Scholar 

  42. Sochen, N., Kimmel, R., Malladi, R.: From high energy physics to low level vision. Technical report, UC Berkeley CA 94720, August 1996

  43. Sochen, N., Kimmel, R., Bruckstein, A.M.: Diffusions and confusions in signal and image processing. J. Math. Imaging Vis. 14(3), 237–244 (2001)

    Article  MathSciNet  Google Scholar 

  44. Spira, A., Kimmel, R., Sochen, N.: Efficient Beltrami flow using a short-time kernel. In: Proc. of the 4th International Conference on Scale-Space Methods in Computer Vision (2003)

  45. Suter, D.: Motion estimation and vector splines. In: Proc. Conference on Computer Vision and Pattern Recognition, pp. 939–942 (1994)

  46. Tschumperlè, D., Deriche, R.: Vector valued image regularization with PDE’s. A common framework for different applications (2003)

  47. Uras, S., Girosi, F., Verri, A., Torre, V.: A computational approach to motion perception. Biol. Cybern. 60, 79–87 (1988)

    Article  Google Scholar 

  48. Weickert, J.: Anisotropic Diffusion in Image Processing. Teubner, Stuttgart (1998)

    MATH  Google Scholar 

  49. 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)

    Article  MATH  Google Scholar 

  50. Weickert, J., Schnörr, C.: Variational optical flow computation with spatio-temporal smoothness constraint. J. Math. Imaging Vis. 14(3), 245–255 (2001)

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Applied Mathematics, Tel Aviv University, Ramat-Aviv, Tel-Aviv, 69978, Israel

    Rami Ben-Ari & Nir Sochen

Authors
  1. Rami Ben-Ari
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nir Sochen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rami Ben-Ari.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ben-Ari, R., Sochen, N. A Geometric Framework and a New Criterion in Optical Flow Modeling. J Math Imaging Vis 33, 178–194 (2009). https://doi.org/10.1007/s10851-008-0124-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10851-008-0124-z

Keywords

Search

Navigation