Movatterモバイル変換

[0]ホーム
URL:

Skip to main content

Advertisement

Springer Nature Link
Log in

GraphFlow – 6D Large Displacement Scene Flow via Graph Matching

  • Conference paper
  • First Online:

Part of the book series:Lecture Notes in Computer Science ((LNIP,volume 9358))

Included in the following conference series:

Abstract

We present an approach for computing dense scene flow from two large displacement RGB-D images. When dealing with large displacements the crucial step is to estimate the overall motion correctly. While state-of-the-art approaches focus on RGB information to establish guiding correspondences, we explore the power of depth edges. To achieve this, we present a new graph matching technique that brings sparse depth edges into correspondence. An additional contribution is the formulation of a continuous-label energy which is used to densify the sparse graph matching output. We present results on challenging Kinect images, for which we outperform state-of-the-art techniques.

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

Access this chapter

Similar content being viewed by others

Notes

  1. 1.
  2. 2.

    Adjusting the weighting parameters of [15] did not improve the results.

References

  1. Alvarez, L., Deriche, R., Papadopoulo, T., Sánchez, J.: Symmetrical dense optical flow estimation with occlusions detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part I. LNCS, vol. 2350, pp. 721–735. Springer, Heidelberg (2002)

    Chapter  Google Scholar 

  2. Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.: PatchMatch: a randomized correspondence algorithm for structural image editing. TOG28(3), 24 (2009)

    Article  Google Scholar 

  3. Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)

    Chapter  Google Scholar 

  4. Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. TPAMI24(4), 509–522 (2002)

    Article  Google Scholar 

  5. Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. TPAMI23(11), 1222–1239 (2001)

    Article  Google Scholar 

  6. Brox, T., Malik, J.: Large displacement optical flow: descriptor matching in variational motion estimation. TPAMI33(3), 500–513 (2011)

    Article  Google Scholar 

  7. Canny, J.: A computational approach to edge detection. TPAMI8(6), 679–698 (1986)

    Article  Google Scholar 

  8. Conte, D., Foggia, P., Sansone, C., Vento, M.: Thirty years of graph matching in pattern recognition. IJPRAI18(03), 265–298 (2004)

    Google Scholar 

  9. Ferstl, D., Riegler, G., Ruether, M., Bischof, H.: CP-Census: a novel model for dense variational scene flow from RGB-D data. In: Proceedings of BMVC (2014)

    Google Scholar 

  10. Foggia, P., Percannella, G., Vento, M.: Graph matching and learning in pattern recognition in the last 10 years. IJPRAI 28(01) (2014)

    Google Scholar 

  11. Grzegorzek, M., Theobalt, C., Koch, R., Kolb, A. (eds.): Time-of-Flight and Depth Imaging. LNCS, vol. 8200. Springer, Heidelberg (2013)

    Google Scholar 

  12. Hadfield, S., Bowden, R.: Scene particles: unregularized particle-based scene flow estimation. TPAMI36(3), 564–576 (2014)

    Article  Google Scholar 

  13. Hammer, P., Hansen, P., Simeone, B.: Roof duality, complementation and persistency in quadratic 0–1 optimization. Math. Program.28(2), 121–155 (1984)

    Article MathSciNet  Google Scholar 

  14. Herbst, E., Ren, X., Fox, D.: RGB-D flow: Dense 3-d motion estimation using color and depth. In: Proceedings of ICRA, pp. 2276–2282. IEEE (2013)

    Google Scholar 

  15. Hornácek, M., Fitzgibbon, A., Rother, C.: Sphereflow: 6 DoF scene flow from RGB-D pairs. In: Proceedings of CVPR. IEEE (2014)

    Google Scholar 

  16. Huguet, F., Devernay, F.: A variational method for scene flow estimation from stereo sequences. In: Proceedings of ICCV. IEEE (2007)

    Google Scholar 

  17. Jaimez, M., Souiai, M., Gonzalez-Jimenez, J., Cremers, D.: A primal-dual framework for real-time dense RGB-D scene flow. In: Proceedings of ICRA. IEEE (2015)

    Google Scholar 

  18. Leordeanu, M., Zanfir, A., Sminchisescu, C.: Locally affine sparse-to-dense matching for motion and occlusion estimation. In: Proceedings of ICCV. IEEE (2013)

    Google Scholar 

  19. Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV60(2), 91–100 (2004)

    Article  Google Scholar 

  20. Quiroga, J., Devernay, F., Crowley, J.: Local/global scene flow estimation. In: Proceedings of ICIP. IEEE (2013)

    Google Scholar 

  21. Rabe, C., Müller, T., Wedel, A., Franke, U.: Dense, robust, and accurate motion field estimation from stereo image sequences in real-time. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 582–595. Springer, Heidelberg (2010)

    Chapter  Google Scholar 

  22. Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Epicflow: edge-preserving interpolation of correspondences for optical flow (2015).arXiv:1501.02565

  23. Sellent, A., Ruhl, K., Magnor, M.: A loop-consistency measure for dense correspondences in multi-view video. Image Vis. Comput.30(9), 641–654 (2012)

    Article  Google Scholar 

  24. Smith, D.K.: Network flows: theory, algorithms, and applications. J. Oper. Res. Soc.45(11), 1340–1340 (1994)

    Article  Google Scholar 

  25. Torresani, L., Kolmogorov, V., Rother, C.: A dual decomposition approach to feature correspondence. TPAMI35(2), 259–271 (2013)

    Article  Google Scholar 

  26. Vedula, S., Baker, S., Rander, P., Collins, R., Kanade, T.: Three-dimensional scene flow. In: Proceedings of ICCV, vol. 2, pp. 722–729. IEEE (1999)

    Google Scholar 

  27. Verhagen, B., Timofte, R., Van Gool, L.: Scale-invariant line descriptors for wide baseline matching. In: Proceedings of WACV. IEEE (2014)

    Google Scholar 

  28. Vogel, C., Schindler, K., Roth, S.: Piecewise rigid scene flow. In: Proceedings of ICCV. IEEE (2013)

    Google Scholar 

  29. Wang, Y., Zhang, J., Liu, Z., Wu, Q., Chou, P., Zhang, Z., Jia, Y.: Completed dense scene flow in RGB-D space. In: Jawahar, C.V., Shan, S. (eds.) ACCV 2014 Workshops. LNCS, vol. 9008, pp. 191–205. Springer, Heidelberg (2015)

    Chapter  Google Scholar 

  30. Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: Deepflow: large displacement optical flow with deep matching. In: Proceedings of ICCV. IEEE (2013)

    Google Scholar 

  31. Xu, L., Jia, J., Matsushita, Y.: Motion detail preserving optical flow estimation. TPAMI34(9), 1744–1757 (2012)

    Article  Google Scholar 

  32. Yoon, K.J., Kweon, I.S.: Locally adaptive support-weight approach for visual correspondence search. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2005, vol. 2, pp. 924–931. IEEE (2005)

    Google Scholar 

  33. Zhang, L., Koch, R.: An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency. J. Vis. Commun. Image Represent.24(7), 794–805 (2013)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. TU Dresden, Dresden, Germany

    Hassan Abu Alhaija, Anita Sellent & Carsten Rother

  2. Heidelberg University, Heidelberg, Germany

    Hassan Abu Alhaija & Daniel Kondermann

  3. TU Darmstadt, Darmstadt, Germany

    Anita Sellent

Authors
  1. Hassan Abu Alhaija

    You can also search for this author inPubMed Google Scholar

  2. Anita Sellent

    You can also search for this author inPubMed Google Scholar

  3. Daniel Kondermann

    You can also search for this author inPubMed Google Scholar

  4. Carsten Rother

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence toHassan Abu Alhaija.

Editor information

Editors and Affiliations

  1. Institute of Computer Science III, University of Bonn, Bonn, Germany

    Juergen Gall

  2. MPI for Intelligent Systems, University of Tübingen, Tübingen, Germany

    Peter Gehler

  3. Computer Vision Group, Visual Computing Institute, RWTH Aachen, Aachen, Germany

    Bastian Leibe

Rights and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Abu Alhaija, H., Sellent, A., Kondermann, D., Rother, C. (2015). GraphFlow – 6D Large Displacement Scene Flow via Graph Matching. In: Gall, J., Gehler, P., Leibe, B. (eds) Pattern Recognition. DAGM 2015. Lecture Notes in Computer Science(), vol 9358. Springer, Cham. https://doi.org/10.1007/978-3-319-24947-6_23

Download citation

Publish with us

[8]ページ先頭
©2009-2025 Movatter.jp