Skip to main content

2017 | OriginalPaper | Buchkapitel

A Comparison of Isotropic and Anisotropic Second Order Regularisers for Optical Flow

verfasst von : Daniel Maurer, Michael Stoll, Sebastian Volz, Patrick Gairing, Andrés Bruhn

Erschienen in: Scale Space and Variational Methods in Computer Vision

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

In variational optical flow estimation, second order regularisation plays an important role, since it offers advantages in the context of non-fronto-parallel motion. However, in contrast to first order smoothness constraints, most second order regularisers are limited to isotropic concepts. Moreover, the few existing anisotropic concepts are lacking a comparison so far. Hence, our contribution is twofold. (i) First, we juxtapose general concepts for isotropic and anisotropic second order regularization based on direct second order methods, infimal convolution techniques, and indirect coupling models. For all the aforementioned strategies suitable optical flow regularisers are derived. (ii) Second, we show that modelling anisotropic second order smoothness terms gives an additional degree of freedom when penalising deviations from smoothness. This in turn allows us to propose a novel anisotropic strategy which we call double anisotropic regularisation. Experiments on the two KITTI benchmarks show the qualitative differences between the different strategies. Moreover, they demonstrate that the novel concept of double anisotropic regularisation is able to produce excellent results.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Braux-Zin, J., Dupont, R., Bartoli, A.: A general dense image matching framework combining direct and feature-based costs. In: Proceedings of International Conference on Computer Vision, pp. 185–192 (2013) Braux-Zin, J., Dupont, R., Bartoli, A.: A general dense image matching framework combining direct and feature-based costs. In: Proceedings of International Conference on Computer Vision, pp. 185–192 (2013)
3.
Zurück zum Zitat Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004). doi:10.1007/978-3-540-24673-2_3 CrossRef Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004). doi:10.​1007/​978-3-540-24673-2_​3 CrossRef
4.
Zurück zum Zitat Chambolle, A., Lions, P.-L.: Image recovery via total variation minimization and related problems. Numer. Math. 76(2), 167–188 (1997)MathSciNetCrossRefMATH Chambolle, A., Lions, P.-L.: Image recovery via total variation minimization and related problems. Numer. Math. 76(2), 167–188 (1997)MathSciNetCrossRefMATH
5.
Zurück zum Zitat Chan, T., Marquina, A., Mulet, P.: High-order total variation-based image restoration. SIAM J. Sci. Comput. 22(2), 503–516 (2000)MathSciNetCrossRefMATH Chan, T., Marquina, A., Mulet, P.: High-order total variation-based image restoration. SIAM J. Sci. Comput. 22(2), 503–516 (2000)MathSciNetCrossRefMATH
6.
Zurück zum Zitat Charbonnier, P., Blanc-Féraud, L., Aubert, G., Barlaud, M.: Deterministic edge-preserving regularization in computed imaging. IEEE Trans. Image Process. 6(2), 298–311 (1997)CrossRef Charbonnier, P., Blanc-Féraud, L., Aubert, G., Barlaud, M.: Deterministic edge-preserving regularization in computed imaging. IEEE Trans. Image Process. 6(2), 298–311 (1997)CrossRef
7.
Zurück zum Zitat Demetz, O., Stoll, M., Volz, S., Weickert, J., Bruhn, A.: Learning brightness transfer functions for the joint recovery of illumination changes and optical flow. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 455–471. Springer, Cham (2014). doi:10.1007/978-3-319-10590-1_30 Demetz, O., Stoll, M., Volz, S., Weickert, J., Bruhn, A.: Learning brightness transfer functions for the joint recovery of illumination changes and optical flow. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 455–471. Springer, Cham (2014). doi:10.​1007/​978-3-319-10590-1_​30
8.
Zurück zum Zitat Ferstl, D., Reinbacher, C., Ranftl, R., Rüther, M., Bischof, H.: Image guided depth upsampling using anisotropic total generalized variation. In: Proceedings of International Conference on Computer Vision, pp. 993–1000 (2013) Ferstl, D., Reinbacher, C., Ranftl, R., Rüther, M., Bischof, H.: Image guided depth upsampling using anisotropic total generalized variation. In: Proceedings of International Conference on Computer Vision, pp. 993–1000 (2013)
9.
Zurück zum Zitat Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354–3361 (2012) Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354–3361 (2012)
10.
Zurück zum Zitat Hafner, D., Schroers, C., Weickert, J.: Introducing maximal anisotropy into second order coupling models. In: Gall, J., Gehler, P., Leibe, B. (eds.) GCPR 2015. LNCS, vol. 9358, pp. 79–90. Springer, Cham (2015). doi:10.1007/978-3-319-24947-6_7 CrossRef Hafner, D., Schroers, C., Weickert, J.: Introducing maximal anisotropy into second order coupling models. In: Gall, J., Gehler, P., Leibe, B. (eds.) GCPR 2015. LNCS, vol. 9358, pp. 79–90. Springer, Cham (2015). doi:10.​1007/​978-3-319-24947-6_​7 CrossRef
11.
Zurück zum Zitat Hewer, A., Weickert, J., Scheffer, T., Seibert, H., Diebels, S.: Lagrangian strain tensor computation with higher order variational models. In: Proceedings of British Machine Vision Conference, pp. 129.1–129.10 (2013) Hewer, A., Weickert, J., Scheffer, T., Seibert, H., Diebels, S.: Lagrangian strain tensor computation with higher order variational models. In: Proceedings of British Machine Vision Conference, pp. 129.1–129.10 (2013)
12.
Zurück zum Zitat Horn, B., Schunck, B.: Determining optical flow. Artif. Intell. 17, 185–203 (1981)CrossRef Horn, B., Schunck, B.: Determining optical flow. Artif. Intell. 17, 185–203 (1981)CrossRef
13.
Zurück zum Zitat Lefkimmiatis, S., Ward, J.P., Unser, M.: Hessian Schatten-norm regularization for linear inverse problems. IEEE Trans. Image Process. 22(5), 1873–1888 (2013)MathSciNetCrossRef Lefkimmiatis, S., Ward, J.P., Unser, M.: Hessian Schatten-norm regularization for linear inverse problems. IEEE Trans. Image Process. 22(5), 1873–1888 (2013)MathSciNetCrossRef
14.
Zurück zum Zitat Lellmann, J., Morel, J.-M., Schönlieb, C.-B.: Anisotropic third-order regularization for sparse digital elevation models. In: Kuijper, A., Bredies, K., Pock, T., Bischof, H. (eds.) SSVM 2013. LNCS, vol. 7893, pp. 161–173. Springer, Heidelberg (2013). doi:10.1007/978-3-642-38267-3_14 CrossRef Lellmann, J., Morel, J.-M., Schönlieb, C.-B.: Anisotropic third-order regularization for sparse digital elevation models. In: Kuijper, A., Bredies, K., Pock, T., Bischof, H. (eds.) SSVM 2013. LNCS, vol. 7893, pp. 161–173. Springer, Heidelberg (2013). doi:10.​1007/​978-3-642-38267-3_​14 CrossRef
15.
Zurück zum Zitat Lenzen, F., Becker, F., Lellmann, J.: Adaptive second-order total variation: an approach aware of slope discontinuities. In: Kuijper, A., Bredies, K., Pock, T., Bischof, H. (eds.) SSVM 2013. LNCS, vol. 7893, pp. 61–73. Springer, Heidelberg (2013). doi:10.1007/978-3-642-38267-3_6 CrossRef Lenzen, F., Becker, F., Lellmann, J.: Adaptive second-order total variation: an approach aware of slope discontinuities. In: Kuijper, A., Bredies, K., Pock, T., Bischof, H. (eds.) SSVM 2013. LNCS, vol. 7893, pp. 61–73. Springer, Heidelberg (2013). doi:10.​1007/​978-3-642-38267-3_​6 CrossRef
16.
Zurück zum Zitat Lysaker, M., Lundervold, A., Tai, X.C.: Noise removal using fourth-order partial differential equation with applications to medical magnetic resonance images in space and time. IEEE Trans. Image Process. 12(12), 1579–1590 (2003)CrossRefMATH Lysaker, M., Lundervold, A., Tai, X.C.: Noise removal using fourth-order partial differential equation with applications to medical magnetic resonance images in space and time. IEEE Trans. Image Process. 12(12), 1579–1590 (2003)CrossRefMATH
17.
Zurück zum Zitat Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3061–3070 (2015) Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3061–3070 (2015)
18.
Zurück zum Zitat Nagel, H.-H., Enkelmann, W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Trans. Patt. Anal. Mach. Intell. 8(5), 565–593 (1986)CrossRef Nagel, H.-H., Enkelmann, W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Trans. Patt. Anal. Mach. Intell. 8(5), 565–593 (1986)CrossRef
19.
Zurück zum Zitat Nir, T., Bruckstein, A.M., Kimmel, R.: Over-parameterized variational optical flow. Int. J. Comput. Vis. 76(2), 205–216 (2008)CrossRef Nir, T., Bruckstein, A.M., Kimmel, R.: Over-parameterized variational optical flow. Int. J. Comput. Vis. 76(2), 205–216 (2008)CrossRef
20.
Zurück zum Zitat Perona, P., Malik, J.: Scale space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 2, 629–639 (1990)CrossRef Perona, P., Malik, J.: Scale space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 2, 629–639 (1990)CrossRef
21.
Zurück zum Zitat Ranftl, R., Gehrig, S., Pock, T., Bischof, H.: Pushing the limits of stereo using variational stereo estimation. In: IEEE Intelligent Vehicles Symposium, pp. 401–407 (2012) Ranftl, R., Gehrig, S., Pock, T., Bischof, H.: Pushing the limits of stereo using variational stereo estimation. In: IEEE Intelligent Vehicles Symposium, pp. 401–407 (2012)
22.
Zurück zum Zitat Ranftl, R., Bredies, K., Pock, T.: Non-local total generalized variation for optical flow estimation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 439–454. Springer, Cham (2014). doi:10.1007/978-3-319-10590-1_29 Ranftl, R., Bredies, K., Pock, T.: Non-local total generalized variation for optical flow estimation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 439–454. Springer, Cham (2014). doi:10.​1007/​978-3-319-10590-1_​29
23.
Zurück zum Zitat Ranftl, R.: Higher-Order Variational Methods for Dense Correspondence Problems. Ph.D thesis. Graz University of Technology, Austria (2014) Ranftl, R.: Higher-Order Variational Methods for Dense Correspondence Problems. Ph.D thesis. Graz University of Technology, Austria (2014)
24.
Zurück zum Zitat Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: EpicFlow: Edge-preserving interpolation of correspondences for optical flow. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1164–1172 (2015) Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: EpicFlow: Edge-preserving interpolation of correspondences for optical flow. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1164–1172 (2015)
25.
26.
Zurück zum Zitat Scherzer, O.: Denoising with higher order derivatives of bounded variation and an application to parameter estimation. Computing 60(1), 1–27 (1998)MathSciNetCrossRefMATH Scherzer, O.: Denoising with higher order derivatives of bounded variation and an application to parameter estimation. Computing 60(1), 1–27 (1998)MathSciNetCrossRefMATH
27.
28.
Zurück zum Zitat Trobin, W., Pock, T., Cremers, D., Bischof, H.: An Unbiased second-order prior for high-accuracy motion estimation. In: Rigoll, G. (ed.) DAGM 2008. LNCS, vol. 5096, pp. 396–405. Springer, Heidelberg (2008). doi:10.1007/978-3-540-69321-5_40 CrossRef Trobin, W., Pock, T., Cremers, D., Bischof, H.: An Unbiased second-order prior for high-accuracy motion estimation. In: Rigoll, G. (ed.) DAGM 2008. LNCS, vol. 5096, pp. 396–405. Springer, Heidelberg (2008). doi:10.​1007/​978-3-540-69321-5_​40 CrossRef
29.
Zurück zum Zitat Vogel, O., Bruhn, A., Weickert, J., Didas, S.: Direct shape-from-shading with adaptive higher order regularisation. In: Sgallari, F., Murli, A., Paragios, N. (eds.) SSVM 2007. LNCS, vol. 4485, pp. 871–882. Springer, Heidelberg (2007). doi:10.1007/978-3-540-72823-8_75 CrossRef Vogel, O., Bruhn, A., Weickert, J., Didas, S.: Direct shape-from-shading with adaptive higher order regularisation. In: Sgallari, F., Murli, A., Paragios, N. (eds.) SSVM 2007. LNCS, vol. 4485, pp. 871–882. Springer, Heidelberg (2007). doi:10.​1007/​978-3-540-72823-8_​75 CrossRef
30.
Zurück zum Zitat Weickert, J., Welk, M., Wickert, M.: L 2-Stable nonstandard finite differences for anisotropic diffusion. In: Kuijper, A., Bredies, K., Pock, T., Bischof, H. (eds.) SSVM 2013. LNCS, vol. 7893, pp. 380–391. Springer, Heidelberg (2013). doi:10.1007/978-3-642-38267-3_32 CrossRef Weickert, J., Welk, M., Wickert, M.: L 2-Stable nonstandard finite differences for anisotropic diffusion. In: Kuijper, A., Bredies, K., Pock, T., Bischof, H. (eds.) SSVM 2013. LNCS, vol. 7893, pp. 380–391. Springer, Heidelberg (2013). doi:10.​1007/​978-3-642-38267-3_​32 CrossRef
31.
Zurück zum Zitat Weickert, J., Schnörr, C.: A theoretical framework for convex regularizers in PDE-based computation of image motion. Int. J. Comput. Vision 45(3), 245–264 (2001)CrossRefMATH Weickert, J., Schnörr, C.: A theoretical framework for convex regularizers in PDE-based computation of image motion. Int. J. Comput. Vision 45(3), 245–264 (2001)CrossRefMATH
32.
Zurück zum Zitat Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: Anisotropic Huber-\(L^1\) optic flow. In: Proceedings of British Machine Vision Conference (2009) Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: Anisotropic Huber-\(L^1\) optic flow. In: Proceedings of British Machine Vision Conference (2009)
33.
Zurück zum Zitat Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-\(L^1\) optical flow. In: Proceedings of German Pattern Recognition, pp. 214–223 (2007) Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-\(L^1\) optical flow. In: Proceedings of German Pattern Recognition, pp. 214–223 (2007)
Metadaten
Titel
A Comparison of Isotropic and Anisotropic Second Order Regularisers for Optical Flow
verfasst von
Daniel Maurer
Michael Stoll
Sebastian Volz
Patrick Gairing
Andrés Bruhn
Copyright-Jahr
2017
DOI
https://doi.org/10.1007/978-3-319-58771-4_43