Advertisement

Stereo Fusion from Multiple Viewpoints

  • Christian Unger
  • Eric Wahl
  • Peter Sturm
  • Slobodan Ilic
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7476)

Abstract

Advanced driver assistance using cameras is a first important step towards autonomous driving tasks. However, the computational power in automobiles is highly limited and hardware platforms with enormous processing resources such as GPUs are not available in serial production vehicles. In our paper we address the need for a highly efficient fusion method that is well suited for standard CPUs.

We assume that a number of pairwise disparity maps are available, which we project to a reference view pair and fuse them efficiently to improve the accuracy of the reference disparity map. We estimate a probability density function of disparities in the reference image using projection uncertainties. In the end the most probable disparity map is selected from the probability distribution.

We carried out extensive quantitative evaluations on challenging stereo data sets and real world images. These results clearly show that our method is able to recover very accurate disparity maps in real-time.

Keywords

Fusion Method Stereo Match Multiple Viewpoint Reference View Stereo Method 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. In: ICCV, pp. 377–384 (1999) Google Scholar
  2. 2.
    Collins, R.T.: A space-sweep approach to true multi-image matching. In: CVPR, p. 358 (1996)Google Scholar
  3. 3.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient belief propagation for early vision. IJCV 70(1), 41–54 (2006)CrossRefGoogle Scholar
  4. 4.
    Gargallo, P., Sturm, P.: Bayesian 3D modeling from images using multiple depth maps. In: CVPR, pp. 885–891 (2005)Google Scholar
  5. 5.
    Hirschmüller, H.: Accurate and efficient stereo processing by semi-global matching and mutual information. In: CVPR, pp. 807–814 (2005)Google Scholar
  6. 6.
    Hirschmüller, H., Innocent, P.R., Garibaldi, J.: Real-time correlation-based stereo vision with reduced border errors. IJCV 47(1-3), 229–246 (2002)zbMATHCrossRefGoogle Scholar
  7. 7.
    Hirschmuüller, H.: Stereo vision in structured environments by consistent semi-global matching. In: CVPR, pp. 2386–2393 (2006)Google Scholar
  8. 8.
    Hosni, A., Bleyer, M., Gelautz, M., Rhemann, C.: Local stereo matching using geodesic support weights. In: ICIP (2009)Google Scholar
  9. 9.
    Koch, R., Pollefeys, M., Van Gool, L.: Multi Viewpoint Stereo from Uncalibrated Video Sequences. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 55–71. Springer, Heidelberg (1998)Google Scholar
  10. 10.
    Kolmogorov, V., Zabih, R.: Multi-camera Scene Reconstruction via Graph Cuts. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part III. LNCS, vol. 2352, pp. 82–96. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  11. 11.
    Merrell, P., Akbarzadeh, A., Wang, L., Frahm, J.M., Yang, R., Nistér, D.: Real-time visibility-based fusion of depth maps. In: ICCV, pp. 1–8 (2007)Google Scholar
  12. 12.
    Okutomi, M., Kanade, T.: A multiple-baseline stereo. PAMI 15(1), 353–363 (1993)CrossRefGoogle Scholar
  13. 13.
    Sato, T., Kanbara, M., Yokoya, N., Takemura, H.: Dense 3-D reconstruction of an outdoor scene by hundreds-baseline stereo using a hand-held video camera. IJCV 47, 119–129 (2002)zbMATHCrossRefGoogle Scholar
  14. 14.
    Scharstein, D., Szeliski, R., Zabih, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV 47, 7–42 (2002)zbMATHCrossRefGoogle Scholar
  15. 15.
    Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: CVPR (2006)Google Scholar
  16. 16.
    Szeliski, R.: A multi-view approach to motion and stereo. In: CVPR, p. 1157 (1999)Google Scholar
  17. 17.
    Unger, C., Benhimane, S., Wahl, E., Navab, N.: Efficient disparity computation without maximum disparity for real-time stereo vision. In: BMVC (2009)Google Scholar
  18. 18.
    Zach, C.: Fast and high quality fusion of depth maps. In: 3DPVT (2008)Google Scholar
  19. 19.
    Zhang, G., Jia, J., Wong, T.T., Bao, H.: Consistent depth maps recovery from a video sequence. PAMI 31(6), 974–988 (2009)CrossRefGoogle Scholar
  20. 20.
    Zitnick, L.C., Kang, S.B., Uyttendaele, M., Winder, S., Szeliski, R.: High-quality video view interpolation using a layered representation. In: SIGGRAPH (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Christian Unger
    • 1
    • 2
  • Eric Wahl
    • 2
  • Peter Sturm
    • 3
  • Slobodan Ilic
    • 1
  1. 1.Technische Universität MünchenGermany
  2. 2.BMW GroupMünchenGermany
  3. 3.INRIA Rhône-Alpes and Laboratoire Jean KuntzmannFrance

Personalised recommendations