Advertisement

Pooling-Based Feature Extraction and Coarse-to-fine Patch Matching for Optical Flow Estimation

  • Xiaolin TangEmail author
  • Son Lam Phung
  • Abdesselam Bouzerdoum
  • Van Ha Tang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11364)

Abstract

This paper presents a pooling-based hierarchical model to extract a dense matching set for optical flow estimation. The proposed model down-samples basic image features (gradient and colour) with min and max pooling, to maintain distinctive visual features from the original resolution to the highly down-sampled layers. Subsequently, patch descriptors are extracted from the pooling results for coarse-to-fine patch matching. In the matching process, the local optimum correspondence of patches is found with a four-step search, and then refined by a velocity propagation algorithm. This paper also presents a method to detect matching outliers by checking the consistency of motion-based and colour-based segmentation. We evaluate the proposed method on two benchmarks, MPI-Sintel and Kitti-2015, using two criteria: the matching accuracy and the accuracy of the resulting optical flow estimation. The results indicate that the proposed method is more efficient, produces more matches than the existing algorithms, and improves significantly the accuracy of optical flow estimation.

Keywords

Optical flow estimation Coarse-to-fine patch matching Pooling-based feature extraction 

References

  1. 1.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2281 (2012)CrossRefGoogle Scholar
  2. 2.
    Bailer, C., Taetz, B., Stricker, D.: Flow fields: dense correspondence fields for highly accurate large displacement optical flow estimation. In: ICCV, pp. 4015–4023 (2015)Google Scholar
  3. 3.
    Barnes, C., Shechtman, E., Goldman, D.B., Finkelstein, A.: The generalized patchmatch correspondence algorithm. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6313, pp. 29–43. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15558-1_3CrossRefGoogle Scholar
  4. 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. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004).  https://doi.org/10.1007/978-3-540-24673-2_3CrossRefGoogle Scholar
  5. 5.
    Brox, T., Malik, J.: Large displacement optical flow: descriptor matching in variational motion estimation. IEEE Trans. Pattern Anal. Mach. Intell. 33, 500–513 (2011)CrossRefGoogle Scholar
  6. 6.
    Brox, T., Malik, J., Bregler, C.: Large displacement optical flow. In: CVPR, pp. 41–48 (2009)Google Scholar
  7. 7.
    Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 611–625. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33783-3_44CrossRefGoogle Scholar
  8. 8.
    Chen, Q., Koltun, V.: Full flow: optical flow estimation by global optimization over regular grids. In: CVPR, pp. 4706–4714 (2016)Google Scholar
  9. 9.
    Dollár, P., Zitnick, C.L.: Structured forests for fast edge detection. In: ICCV, pp. 1841–1848 (2013)Google Scholar
  10. 10.
    Dong, X., Shen, J., Shao, L.: Hierarchical superpixel-to-pixel dense matching. IEEE Trans. Circ. Syst. Video Technol. 27(12), 2518–2526 (2017)CrossRefGoogle Scholar
  11. 11.
    Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: ICCV, pp. 2758–2766 (2015)Google Scholar
  12. 12.
    He, K., Sun, J.: Computing nearest-neighbor fields via propagation-assisted KD-trees. In: CVPR, pp. 111–118 (2012)Google Scholar
  13. 13.
    Hu, Y., Li, Y., Song, R.: Robust interpolation of correspondences for large displacement optical flow. In: CVPR, vol. 2017-Janua, pp. 4791–4799 (2017)Google Scholar
  14. 14.
    Hu, Y., Song, R., Li, Y.: Efficient coarse-to-fine patchmatch for large displacement optical flow. In: CVPR, pp. 5704–5712 (2016)Google Scholar
  15. 15.
    Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: Flownet 2.0: evolution of optical flow estimation with deep networks. In: CVPR, pp. 1–8 (2017)Google Scholar
  16. 16.
    Liu, C., Yuen, J., Member, S., Torralba, A.: SIFT flow: dense correspondence across scenes and its applications. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 978–994 (2011)CrossRefGoogle Scholar
  17. 17.
    Liu, C., Yuen, J., Torralba, A., Sivic, J., Freeman, W.T.: SIFT flow: dense correspondence across different scenes. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5304, pp. 28–42. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-88690-7_3CrossRefGoogle Scholar
  18. 18.
    Lu, J., Li, Y., Yang, H., Min, D., Eng, W., Do, M.N.: PatchMatch filter: edge-aware filtering meets randomized search for visual correspondence. IEEE Trans. Pattern Anal. Mach. Intell. 39(9), 1866–1879 (2017)CrossRefGoogle Scholar
  19. 19.
    Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: CVPR, pp. 4040–4048 (2015)Google Scholar
  20. 20.
    Menze, M., Heipke, C., Geiger, A.: Joint 3D estimation of vehicles and scene flow. In: ISPRS Workshops, pp. 427–434 (2015)CrossRefGoogle Scholar
  21. 21.
    Menze, M., Heipke, C., Geiger, A.: Object scene flow. ISPRS J. Photogrammetry Remote Sens. 140, 60–76 (2018)CrossRefGoogle Scholar
  22. 22.
    Ranjan, A., Black, M.J.: Optical flow estimation using a spatial pyramid network. In: CVPR, pp. 1–8 (2017)Google Scholar
  23. 23.
    Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Epicflow: edge-preserving interpolation of correspondences for optical flow. In: CVPR, pp. 1164–1172 (2015)Google Scholar
  24. 24.
    Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Deepmatching: hierarchical deformable dense matching. Int. J. Comput. Vis. 120, 300–323 (2016)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Sevilla-Lara, L., Sun, D., Learned-Miller, E.G., Black, M.J.: Optical flow estimation with channel constancy. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 423–438. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10590-1_28CrossRefGoogle Scholar
  26. 26.
    Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: CVPR, pp. 1–8 (2017)Google Scholar
  27. 27.
    Unger, M., Werlberger, M., Pock, T., Bischof, H.: Joint motion estimation and segmentation of complex scenes with label costs and occlusion modeling. In: CVPR, pp. 1878–1885 (2012)Google Scholar
  28. 28.
    Wulff, J., Sevilla-Lara, L., Black, M.J.: Optical flow in mostly rigid scenes. In: CVPR, pp. 6911–6920 (2017)Google Scholar
  29. 29.
    Xu, J., Ranftl, R., Koltun, V.: Accurate optical flow via direct cost volume processing. In: CVPR, pp. 1289–1297 (2017)Google Scholar
  30. 30.
    Yang, J., Li, H.: Dense, accurate optical flow estimation with piecewise parametric model. In: CVPR, pp. 1019–1027 (2015)Google Scholar
  31. 31.
    Yang, Y., Soatto, S.: S2F: slow-to-fast interpolator flow. In: CVPR, pp. 3767–3776 (2017)Google Scholar
  32. 32.
    Yao, J., Boben, M., Fidler, S., Urtasun, R.: Real-time coarse-to-fine topologically preserving segmentation. In: CVPR, pp. 2947–2955 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Xiaolin Tang
    • 1
    Email author
  • Son Lam Phung
    • 1
  • Abdesselam Bouzerdoum
    • 1
    • 2
  • Van Ha Tang
    • 1
  1. 1.School of Electrical, Computer and Telecommunications EngineeringUniversity of WollongongWollongongAustralia
  2. 2.Division of Information and Computing Technology, College of Science and EngineeringHamad Bin Khalifa UniversityDohaQatar

Personalised recommendations