Skip to main content
SpringerLink
Log in

Improving Border Localization of Multi-Baseline Stereo Using Border-Cut

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

This paper presents a novel algorithm that improves the localization of disparity discontinuities of disparity maps obtained by multi-baseline stereo. Rather than associating a disparity label to every pixel of a disparity map, it associates a position to every disparity discontinuity. This formulation allows us to find an approximate solution to a 2D labeling problem with robust smoothing term by minimizing multiple 1D problems, thus making possible the use of dynamic programming. Dynamic programming allows the efficient computation of the visibility of most of the cameras during the minimization. The proposed algorithm is not a stereo matcher on it own since it requires an initial disparity map. Nevertheless, it is a very effective way of improving the border localization of disparity maps obtained from a large class of stereo matchers. Whilst the proposed minimization strategy is particularly suitable for stereo with occlusion, it may be used for other labeling problems.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  • Amir, R. C. J., Amini, A., & Weymouth, T. E. (1990). Using dynamic programming for solving variational problems in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(9), 855–867.

    Article  Google Scholar 

  • Belhumeur, P. N. (1996). A Bayesian approach to binocular stereopsis. International Journal of Computer Vision, 19(3), 237–260.

    Article  Google Scholar 

  • Birchfield, S., & Tomasi, C. (1998). A pixel dissimilarity measure that is insensitive to image sampling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(4), 401–406.

    Article  Google Scholar 

  • Bleyer, M., & Gelautz, M. (2004). A layered stereo algorithm using image segmentation and global visibility constraints. In International conference on image processing.

  • Boykov, Y., Veksler, O., & Zabih, R. (1999). Fast approximate energy minimization via graph cut. In International conference on computer vision (pp. 377–384).

  • Cox, I. J., Hingorani, S., Maggs, B. M., & Rao, S. B. (1996). A maximum likelihood stereo algorithm. Computer Vision and Image Understanding, 63(3), 542–567.

    Article  Google Scholar 

  • Drouin, M.-A., Trudeau, M., & Roy, S. (2005a). Geo-consistency for wide multi-camera stereo. In IEEE conference on computer vision and pattern recognition (pp. 351–359).

  • Drouin, M.-A., Trudeau, M., & Roy, S. (2005b). Fast multiple-baseline stereo with occlusion. In 3-D digital imaging and modeling (pp. 540–548).

  • Egnal, G., & Wildes, R. P. (2002). Detecting binocular half-occlusions: Empirical comparisons of five approaches. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(8), 1127–1133.

    Article  Google Scholar 

  • Faugeras, O. D., & Keriven, R. (1998). Complete dense stereovision using level set methods. In European conference on computer vision (pp. 379–393).

  • Felzenszwalb, P. F., & Huttenlocher, D. P. (2006). Efficient belief propagation for early vision. International Journal of Computer Vision, 70(1), 41–54.

    Article  Google Scholar 

  • Fusiello, A., Roberto, V., & Trucco, E. (1997). Efficient stereo with multiple windowing. In IEEE conference on computer vision and pattern recognition.

  • Goesele, M., Curless, B., & Seitz, S. M. (2006). Multi-view stereo revisited. In IEEE conference on computer vision and pattern recognition (pp. 2402–2409).

  • Gong, M., & Yang, Y.-H. (2003). Fast stereo matching using reliability-based dynamic programming and consistency constraint. In International conference on computer vision.

  • Intille, S., & Bobick, A. F. (2002). Disparity-space images and large occlusion stereo. In European conference on computer vision (pp. 179–186).

  • Ishikawa, H., & Geiger, D. (1998). Occlusions, discontinuities, and epipolar lines in stereo. In European conference on computer vision (pp. 232–248).

  • Kanade, T., & Okutomi, M. (1994). A stereo matching algorithm with an adaptive window: Theory and experiment. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(9), 920–932.

    Article  Google Scholar 

  • Kang, S., Szeliski, R., & Chai, J. (2001). Handling occlusions in dense multiview stereo. In IEEE conference on computer vision and pattern recognition.

  • Kolmogorov, V., & Zabih, R. (2001). Computing visual correspondence with occlusions via graph cuts. In IEEE conference on computer vision and pattern recognition (pp. 508–515).

  • Kolmogorov, V., & Zabih, R. (2002). Multi-camera scene reconstruction via graph cuts. In European conference on computer vision.

  • Kutulakos, K., & Seitz, S. (2000). A theory of shape by space carving. International Journal of Computer Vision, 38(3), 133–144.

    Article  Google Scholar 

  • Leung, C., Appleton, B., & Sun, C. (2004). Fast stereo matching by iterated dynamic programming and quadtree subregioning. In The British machine vision conference.

  • Nakamura, Y., Matsuura, T., Satoh, K., & Ohta, Y. (1996). Occlusion detectable stereo-occlusion patterns in camera matrix. In IEEE conference on computer vision and pattern recognition.

  • Ohta, Y., & Kanade, T. (1985). Stereo by intra- and inter-scanline using dynamic programming. IEEE Transactions on Pattern Analysis and Machine Intelligence, 7(2), 139–154.

    Article  Google Scholar 

  • Osher, S. J., & Fedkiw, R. P. (2002). Level set methods and dynamic implicit surfaces. Berlin: Springer.

    Google Scholar 

  • Park, J., & Inoue, S. (1998). Acquisition of sharp depth map from multiple cameras. Signal Processing and Image Communication, 14, 7–19.

    Article  Google Scholar 

  • Roy, S. (1999). Stereo without epipolar lines: A maximum-flow formulation. International Journal of Computer Vision, 34(2/3), 147–162.

    Article  Google Scholar 

  • Sanfourche, M., Besnerais, G. L., & Champagant, F. (2004). On the choice of the correlation term for multi-baseline stereo-vision. In The British machine vision conference.

  • Scharstein, D., & Szeliski, R. (2002). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47(1–3), 7–42.

    Article  MATH  Google Scholar 

  • Scharstein, D., & Szeliski, R. (2007). Middlebury stereo vision page. [Online] Available: www.middlebury.edu/stereo.

  • Seitz, S. M., & Dyer, C. R. (1999). Photorealistic scene reconstruction by voxel coloring. International Journal of Computer Vision, 35(2), 151–173.

    Article  Google Scholar 

  • Seitz, S. M., Curless, B., Diebel, J., Scharstein, D., & Szeliski, R. (2006). A comparison and evaluation of multi-view stereo reconstruction algorithms. In IEEE conference on computer vision and pattern recognition (pp. 519–528).

  • Strecha, C., Fransens, R., & Van Gool, L. (2006). Combined depth and outlier estimation in multi-view stereo. In IEEE conference on computer vision and pattern recognition (vol. 2, pp. 2394–2401).

  • Sun, J., Zheng, N., & Shum, H. (2003). Stereo matching using belief propagation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(7), 787–800.

    Article  Google Scholar 

  • Sun, J., Li, Y., Kang, S. B., & Shum, H.-Y. (2005). Symmetric stereo matching for occlusion handling. In IEEE conference on computer vision and pattern recognition (pp. 399–406).

  • Szeliski, R., & Zabih, R. (1999). An experimental comparison of stereo algorithms. In Vision algorithms: theory and practice (pp. 1–19). Berlin: Springer.

    Google Scholar 

  • Szeliski, R., Zabithh, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwale, A., Tappen, M., & Rother, C. (2006). A comparative study of energy minimization methods for Markov random fields. In European conference on computer vision.

  • Veksler, O. (1999). Efficient graph-based energy minimization methods in computer vision. Ph.D. dissertation, Cornell University.

  • Veksler, O. (2003). Fast variable window for stereo correspondence using integral images. In IEEE conference on computer vision and pattern recognition.

  • Veksler, O. (2005). Stereo correspondence by dynamic programming on a tree. In IEEE conference on computer vision and pattern recognition.

  • Wei, Y., & Quan, L. (2005). Asymmetrical occlusion handling using graph cut for multi-view stereo. In IEEE conference on computer vision and pattern recognition, June 2005 (pp. 902–909).

  • Yoon, K.-J., & Kweon, I. S. (2006). Stereo matching with symmetric cost functions. In IEEE conference on computer vision and pattern recognition (vol. 2, pp. 2371–2377).

Download references

Author information

Author notes

  1. Marc-Antoine Drouin

    Present address: Institute of Information Technology of the National Research Council Canada, Ottawa, Canada

Authors and Affiliations

  1. Département d’informatique et recherche opérationelle, Université de Montréal, Montréal, Canada

    Marc-Antoine Drouin, Martin Trudeau & Sébastien Roy

Authors
  1. Marc-Antoine Drouin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Martin Trudeau
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sébastien Roy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Marc-Antoine Drouin.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Drouin, MA., Trudeau, M. & Roy, S. Improving Border Localization of Multi-Baseline Stereo Using Border-Cut. Int J Comput Vis 83, 233–247 (2009). https://doi.org/10.1007/s11263-009-0223-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11263-009-0223-3

Keywords

Search

Navigation