Control of the effects of regularization on variational optic flow computations

Journal of Mathematical Imaging and Vision

Volumn 40, Issue 1, 2011, Pages 1-19

  Belhachmi, Z ^a   Hecht, F ^b  

^a UNIVERSITÉ DE LORRAINE   (France)

^b UNIVERSITÉ PIERRE ET MARIE CURIE   (France)

Author keywords

Adaptive finite elements; Computer vision; Confidence measure; Optic flow; Regularization procedure

Indexed keywords

ADAPTIVE FINITE ELEMENT; CONFIDENCE MEASURE; CONVERGENCE ANALYSIS; ENERGY FUNCTIONALS; ERROR INDICATORS; ILL POSED; LOW DENSITY; NON-SMOOTH; NUMERICAL EXPERIMENTS; OPTIC FLOW; OPTIC FLOW COMPUTATION; POSTERIORI; POSTERIORI ANALYSIS; REGULARIZATION PROCEDURE; SINGLE PARAMETER; SPARSE SOLUTIONS; VARIATIONAL MODELS;

COMPUTER VISION; NUMERICAL METHODS;

FINITE ELEMENT METHOD;

EID: 79953197179     PISSN: 09249907     EISSN: None     Source Type: Journal    
DOI: 10.1007/s10851-010-0239-x     Document Type: Article

References (50)

1. Alvarez, L.; Esclarin, J.; Lefebure, M.; Sanchez, J.: A PDE model for computing the optic flow. In: Proc. XVI Congreso de Ecuaciones Diferenciales y Aplicationes, Las Palmas de Gran Canaria, Spain, pp. 1349-1346 (1999)
2. P. Anandan 2000 A computational framework and an algorithm for the measurement of visual motion Int. J. Comput. Vis. 39 1 41 56 10.1023/A:1008170101536
3. Aubert, G.; Derriche, R.; Kornprobst, P.: Optic flow estimation while preserving its discontinuities: a variational approach. In: Proc. Second Asian Conference on Computer Vision, vol. 2, Singapore, 2000. pp. 290-295. Springer, Berlin (1995)
4. G. Aubert R. Deriche P. Kornprobst 1999 Computing optical flow via variational techniques SIAM J. Appl. Math. 60 1 156 182 1740840 0942.35057 10.1137/S0036139998340170
5. Z. Belhachmi C. Bernardi S. Deparis F. Hecht 2006 An efficient discretization of the Navier-Stokes equations in an axisymmetric domain J. Sci. Comput. 27 1-3 97 110 2285768 1101.76031 10.1007/s10915-005-9035-y (Pubitemid 43876931)
6. Z. Belhachmi C. Bernardi A. Karageorghis 2007 Mortar spectral element discretization of nonhomogeneous and anisotropic Laplace and Darcy equations M2AN 41 4 801 824 2362915 1145.65094 10.1051/m2an:2007035
7. Z. Belhachmi D. Bucur 2007 Stability and uniqueness for the crack identification problem SIAM J. Control. Optim. 46 1 253 273 2299628 1136.35102 10.1137/S0363012904441179 (Pubitemid 351271296)
8. J. Bigün H. Granlund J. Wiklund 1991 Multidimensional orientation estimation with applications to textures analysis and optic flow IEEE Trans. Pattern Anal. Mach. Intel. 13 8 775 790 10.1109/34.85668 (Pubitemid 21704202)
9. C. Bernardi R. Verfürth 2000 Adaptive finite element methods for elliptic equations with non-smooth coefficients Numer. Math. 85 579 608 1771781 0962.65096 10.1007/PL00005393
10. A. Borzi K. Ito K. Kunisch 2002 Optimal control formulation for determining the optical flow SIAM J. Sci. Comput. 24 3 818 847 1950513 1041.68103 10.1137/S1064827501386481
11. M. Braack A. Ern 2003 A posteriori control of modeling errors and discretization errors Multiscale Model. Simul. 1 2 221 238 1990196 1050.65100 10.1137/S1540345902410482
12. Bruhn, A.: Variational optic flow computation: accurate modelling and efficient numerics. Ph.D. thesis in Computer Science (2006). Saarland University, Saarbrücken, Germany
13. Bruhn, A.; Weickert, J.: Confidence measure for variational optic flow methods. In: Klette, R.; Kozera, R.; Noakes, L.; Weickert, J. (eds.) Geometric Properties from Incomplete Data, Computational Imaging and Vision. Springer, Dordrecht (2005)
14. Bruhn, A.; Weickert, J.; Schnörr, C.: Combining the advantages of local and global optic flow methods. In: Van Gool, L. (ed.) Pattern Recognition. Lecture Notes in Computer Sciences, vol. 2449, pp. 454-462. Springer, Berlin (2002)
15. A. Bruhn J. Weickert C. Schnörr 2004 Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods Int. J. Comput. Vis. 61 3 211 231
16. A. Bruhn J. Weickert C. Feddern T. Kohlberger C. Schnörr 2005 Real-time optic flow computation with variational methods IEEE Trans. Image Process. 15 5 608 615 10.1109/TIP.2005.846018 (Pubitemid 40690617)
17. Ciarlet, P.G.: Basic error estimates for elliptic problems. In: Ciarlet, P.G.; Lions, J.-L. (eds.) Handbook of Numerical Analysis, vol. II, pp. 17-351. North-Holland, Amsterdam (1991)
18. Cohen, I.: Nonlinear variational method for optical flow computation. In: Proc. Eighth Scandinavian Conference on Image Analysis, vol. 1, pp. 523-530. Tromso, Norway, (1993)
19. T. Dupont R. Scott 1980 Polynomial approximation of functions in Sobolev spaces Math. Comput. 34 441 463 559195 0423.65009 10.1090/S0025-5718-1980- 0559195-7
20. Engl, H.; Hanke, M.; Neubauer, A.: Regularization of Inverse Problems. Kluwer Academic, Dordrecht (1996)
21. H. Engl K. Kunisch A. Neubauer 1989 Convergence rates for Tikhonov regularization of nonlinear ill-posed problems Inverse Probl. 5 523 540 1009037 0695.65037 10.1088/0266-5611/5/4/007
22. Evans, L.C.: Partial Differential Equations. Graduate Studies in Mathematics, 2nd edn.; vol. 19. American Mathematical Society, Providence (2010)
23. Girault, V.; Raviart, P.-A.: Finite Element Methods for the Navier-Stokes Equations, Theory and Algorithms. Springer, Berlin (1986)
24. Hecht, F.; Pironneau, O.: FreeFem++. See www.freefem.org
25. W. Hinterberger O. Scherzer C. Schnörr J. Weickert 2002 Analysis of optical ow models in the framework of calculus of variations Numer. Funct. Anal. Optim. 23 1/2 69 89 1900411 1016.49002 (Pubitemid 34598856)
26. B. Horn B. Schunck 1981 Determining optic flow Artif. Intell. 17 185 203 10.1016/0004-3702(81)90024-2
27. Kondermann, C.; Mester, R.; Grabe, C.: Statistical confidence measure for optical flows. In: Proc. European Conference on Computer Vision. Lectures Notes in Computer Science, vol. 5304, pp. 290-301. Springer, Berlin (2008)
28. Kondermann, C.; Kondermann, D.; Jahne, B.; Grabe, C.: An adaptive confidence measure for optical flows based on linear subspace projections. In: Proc. DAGM Symposium on Pattern Recognition. Lectures Notes in Computer Science, vol. 4713, pp. 132-141. Springer, Berlin (2007)
29. A. Kumar A.R. Tannenbaum G.J. Balas 1996 Optic flow: a curve evolution approach IEEE Trans. Image Process. 5 4 598 610 10.1109/83.491336 (Pubitemid 126777659)
30. Lucas, B.: Generalized image matching by the method of diffrences. PhD thesis, Carnegie Mellon University (1984)
31. Lucas, B.; Kanade, T.: An iterative image registration technique with an application to image stereo. In: Proc. Seventh International Joint Conference on Artificial Intelligence, Vancouver, pp. 674-679 (1981) (Pubitemid 14478744)
32. Mémin, E.; Pérez, P.: A multigrid approach for hierarchical motion estimation. In: Proc. Sixth International Conference on Computer Vision, Bombay, India, pp. 933-938. Narosa Publishing House, Delhi (1998)
33. Nagel, H.H.: Extending the oriented smoothness constraint into the temporal domain and the estimation of the derivatives of optical flow. In: Faugeras, O. (ed.) Computer Vision, ECCV'90. Lectures Notes in Computer Sciences, vol. 427, pp. 139-148. Springer, Berlin (1990)
34. H.H. Nagel W. Enkelmann 1986 An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences IEEE Trans. Pattern Anal. Mach. Intell. 8 565 593 10.1109/TPAMI.1986.4767833
35. Roos, H.-G.; Stynes, M.; Tobiska, L.: Numerical Methods for Singularly Perturbed Differential Equations. Convection-Diffusion and Flow Problems. Springer Series in Computational Mathematics, vol. 24. Springer, Berlin (1996)
36. L.I. Rudin S. Osher E. Fatemi 1992 Nonlinear total variation based noise removal algorithms Physica D 60 259 268 0780.49028 10.1016/0167-2789(92)90242-F
37. Schnörr, C.: Segmentation of visual motion by minimizing convex non quadratic-functionals. In: Proc. Twelfth International Conference on Pattern and Recognition, vol. A, pp. 661-663. IEEE Comput. Soc. Press, Los Alamitos (1994)
38. C. Schnörr 1994 Unique reconstruction of piecewise smooth images by minimizing strictly convex non-quadratic functionals J. Math. Imaging Vis. 4 189 198 10.1007/BF01249896
39. M. Sermesant P. Moireau O. Camara J. Sainte-Marie R. Andriantsimiavona R. Cimrman D.L. Hill D. Chapelle R. Razavi 2006 Cardiac function estimation from MRI using a heart model and data assimilation: advances and difficulties Med. Image Anal. 10 4 642 656 10.1016/j.media.2006.04.002 (Pubitemid 44177294)
40. Simoncelli, E.P.; Adelson, E.H.; Heeger, D.J.: Probability distributions of optical flow. In: Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 310-315. (1991)
41. Shulman, D.; Hervé, J.-Y.: Regularization of discontinuous fields. In: Proc. Workshop on Visual Motion, pp. 81-86 (1989)
42. Sun, D.; Roth, S.; Black, J.M.: Learning optical flow. In: Proc. European Conference on Computer Vision. Lectures Notes in Computer Science, vol. 5304, pp. 83-97. Springer, Berlin (2008)
43. D. Terzopoulos 1986 Image analysis using multigrid relaxation IEEE Trans. Pattern Anal. Mach. Intell. 8 2 129 139 10.1109/TPAMI.1986.4767767 (Pubitemid 16595416)
44. A.N. Tikhonov 1963 Solution of incorrectly formulated problems and the regularization method Sov. Math. Dokl. 4 1035 1038
45. Verfürth, R.: A Review of a Posteriori Error Estimation and Adaptive Mesh-Refinement Techniques. Wiley & Teubner, Amsterdam (1996)
46. Weickert, J.; Bruhn, A.; Brox, T.; Papenberg, N.: A survey on variational methods for small displacements. In: Scherzer, O. (ed.) Mathematical Models for Registration and Applications to Medical Imaging. Mathematics in Industry, vol. 10, pp. 103-136. Springer, Berlin (2006)
47. J. Weickert C. Schnörr 2001 A theoretical framework for convex regularizers in PDE-based computation of image motion Int. J. Comput. Vis. 45 3 245 264 0987.68600 10.1023/A:1013614317973 (Pubitemid 33128009)
48. J. Weickert C. Schnörr 2001 Variational optic flow computations with a spatio-temporal smoothness contraint J. Math. Imaging Vis. 14 245 255 0988.68821 10.1023/A:1011286029287 (Pubitemid 32638802)
49. Werlberger, M.; Trobin, W.; Pock, T.; Wedel, A.; Cremers, D.; Bischof, H.: Anisotropic Huber-L1 optical flow. In: Proc. British Machine Vision Conference, London (2002)
50. Zimmer, H.; Bruhn, A.; Weickert, J.; Valgaerts, L.; Salgado, A.; Rosenhahn, B.; Seidel, H.P.: Complementary optical flow. In: Proc. Energy Minimization Methods in Computer Vision and Pattern Recognition. Lectures Notes in Computer Science, vol. 5681, pp. 207-220. Springer, Berlin (2009)