Accurate Optical Flow Based on Spatiotemporal Gradient Constancy Assumption

Variational methods for optical flow estimation are known for their excellent performance. The method proposed by Brox et al. [5] exemplifies the strength of that framework. It combines several concepts into single energy functional that is then minimized according to clear numerical procedure. In this paper we propose a modification of that algorithm starting from the spatiotemporal gradient constancy assumption. The numerical scheme allows to establish the connection between our model and the CLG(H) method introduced in [18]. Experimental evaluation carried out on synthetic sequences shows the significant superiority of the spatial variant of the proposed method. The comparison between methods for the realworld sequence is also enclosed.

Authors:

• Adam Rabcewicz

Keywords:

• optical flow
• variational methods
• gradient constancy assumption.

References:

[1] L. Alvarez, J. Weickert, and J. S'anchez. Reliable estimation of dense
optical flow fields with large displacements. International Journal of Computer Vision, 39(1):41-56, August 2000.
[2] T. Amiaz and N. Kiryati. Piecewise-smooth dense optical flow via level
sets. International Journal of Computer Vision, 68(2):111-124, June
2006.
[3] G. Aubert, R. Deriche, and P. Kornprobst. Computing optical flow
via variational techniques. SIAM Journal on Applied Mathematics,
60(1):156-182, 1999.
[4] M. J. Black and P. Anandan. The robust estimation of multiple motions:
Parametric and piecewise-smooth flow fields. Computer Vision and
Image Understanding, 63(1):75-104, January 1996.
[5] T. Brox, A. Bruhn, N. Papenberg, and J. Weickert. High accuracy
optical flow estimation based on a theory for warping. In T. Pajdla
and J. Matas, editors, Proceedings of the 8th European Conference on
Computer Vision, volume 3024 of Lecture Notes in Computer Science,
pages 25-36, Prague, Czech Republic, 2004. Springer.
[6] A. Bruhn and J. Weickert. Towards ultimate motion estimation: Combining
highest accuracy with real-time performance. In Proc. Tenth
International Conference on Computer Vision, volume 1, pages 749-
755, Beijing, China, June 2005. IEEE Computer Society.
[7] A. Bruhn, J. Weickert, T. Kohlberger, and C. Schn¨orr. A multigrid
platform for real-time motion computation with discontinuitypreserving
variational methods. International Journal of Computer
Vision, 70(3):257-277, December 2006.
[8] A. Bruhn, J. Weickert, and C. Schn¨orr. Lucas/Kanade meets
Horn/Schunck: Combining local and global optic flow methods. International
Journal of Computer Vision, 61(3):211-231, February 2005.
[9] I. Cohen. Nonlinear variational method for optical flow computation.
In Proc. Eighth Scandinavian Conference on Image Analysis, volume 1,
pages 523-530, Tromso, Norway, May 1993.
[10] W. Hinterberger, O. Scherzer, C. Schn¨orr, and J. Weickert. Analysis
of optical flow models in the framework of the calculus of variations.
Numerical Functional Analysis and Optimization, 23(1/2):69-89, May
2002.
[11] B. Horn and B. Schunck. Determining optical flow. Artificial Intelligence,
17:185-203, August 1981.
[12] B. D. Lucas and T. Kanade. An iterative image registration technique
with an application to stereo vision. In Proc. Seventh International
Joint Conference on Artificial Intelligence, pages 674-679, Vancouver,
Canada, August 1981.
[13] E. M'emin and P. P'erez. A multigrid approach for hierarchical motion
estimation. In S. Chandran and U. Desai, editors, Proc. Sixth International
Conference on Computer Vision, pages 933-938, Bombay, India,
January 1998. Narosa Publishing House.
[14] E. M'emin and P. P'erez. Hierarchical estimation and segmentation
of dense motion fields. International Journal of Computer Vision,
46(2):129-155, 2002.
[15] H.-H. Nagel. Extending the -oriented smoothness constraint- into the
temporal domain and the estimation of derivatives of optical flow. In
O. D. Faugeras, editor, ECCV-90, volume 427 of Lecture Notes in
Computer Science, pages 139-148. Springer, 1990.
[16] P. Nesi. Variational approach to optical-flow estimation managing
discontinuities. Image and Vision Computing, 11(7):419-439, September
1993.
[17] M. Otte and H.-H. Nagel. Estimation of optical flow based on higherorder
spatiotemporal derivatives in interlaced and non-interlaced image
sequences. Artificial Intelligence, 78(1/2):5-43, November 1995.
[18] A. Rabcewicz. CLG method for optical flow estimation based on
gradient constancy assumption. In X.-C. Tai, K.-A. Lie, T.F. Chan,
and S. Osher, editors, Image Processing Based on Partial Differential
Equations: Proceedings of the International Conference on PDE-Based
Image Processing and Related Inverse Problems, CMA, Oslo, Norway,
August 8-12, 2005, Mathematics and Visualization. Springer-Verlag,
2007.
[19] C. Schn¨orr. On functionals with greyvalue-controlled smoothness terms
for determining optical flow. IEEE Transactions on Pattern Analysis
and Machine Intelligence, 15(10):1074-1079, October 1993.
[20] S. Uras, F. Girosi, A. Verri, and V. Torre. A computational approach to
motion perception. Biological Cybernetics, 60:79-87, 1988.
[21] J. Weickert and C. Schn¨orr. A theoretical framework for convex
regularizers in PDE-based computation of image motion. International
Journal of Computer Vision, 45(3):245-264, December 2001.
[22] J. Weickert and C. Schn¨orr. Variational optic flow computation with
a spatio-temporal smoothness constraint. Journal of Mathematical
Imaging and Vision, 14(3):245-255, May 2001.