Performance of MRF-Based Stereo Algorithms for Cluttered Scenes

  • Fahim Mannan
  • Michael Langer
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 83)


This paper evaluates the performance of different Markov Random Field (MRF) based stereo algorithms for cluttered scenes. These scenes are generated by randomly placing objects within a 3D volume. The scenes, which model natural cluttered scenes such as forests or bushes, contain many depth discontinuities and monocularly visible pixels. Widely used benchmark datasets do not contain stereo pairs with dense clutter, so we address how well existing stereo algorithms perform for such scenes. We use Expansion, Swap, Max Product Belief Propagation (BPM), Sequential Tree Reweighted Message Passing (TRW-S) and Sequential Belief Propagation (BP-S), all with different forms of data and smoothness terms. The results are compared with the ground truth disparity and energy.We found Expansion, TRW-S, and BP-M with the Potts model to work well for most scenes, in that the correct binocular correspondence is found for most points that are binocularly visible. We also found that the energy for the ground truth is much larger than what is found by the optimizers. This shows that there is room for improving the model for cluttered scenes.


Markov Random Field Binocular Visibility Stereo Pair Scene Category Depth Discontinuity 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Birchfield, S., Tomasi, C.: Multiway cut for stereo and motion with slanted surfaces. In: IEEE International Conference on Computer Vision, vol. 1, p. 489 (1999)Google Scholar
  2. 2.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision 47(1-3), 7–42 (2002)zbMATHCrossRefGoogle Scholar
  3. 3.
    Langer, M.S.: Surface visibility probabilities in 3d cluttered scenes. In: European Conference on Computer Vision, pp. 401–412. Springer, Heidelberg (2008)Google Scholar
  4. 4.
    Chen, J., Cihlar, J.: Plant canopy gap-size analysis theory for improving optical measurements of leaf-area index. Applied Optics 34(27), 6211–6222 (1995)CrossRefGoogle Scholar
  5. 5.
    van Gardingen, P.R., Jackson, G.E., Hernandez-Daumas, S., Russell, G., Sharp, L.: Leaf area index estimates obtained for clumped canopies using hemispherical photography. Agricultural and Forest Meteorology 94(3-4), 243–257 (1999)CrossRefGoogle Scholar
  6. 6.
    Riao, D., Valladares, F., Condés, S., Chuvieco, E.: Estimation of leaf area index and covered ground from airborne laser scanner (lidar) in two contrasting forests. Agricultural and Forest Meteorology 124(3-4), 269–275 (2004)CrossRefGoogle Scholar
  7. 7.
    Li, S.: Markov Random Field Modeling in Image Analysis. Springer Publishing Company, Incorporated, Heidelberg (2009)zbMATHGoogle Scholar
  8. 8.
    Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., Tappen, M., Rother, C.: A comparative study of energy minimization methods for markov random fields with smoothness-based priors. IEEE Transactions on Pattern Analysis and Machine Intelligence 30, 1068–1080 (2008)CrossRefGoogle Scholar
  9. 9.
    Birchfield, S., Tomasi, C.: A pixel dissimilarity measure that is insensitive to image sampling. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 401–406 (1998)CrossRefGoogle Scholar
  10. 10.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 1222–1239 (2001)CrossRefGoogle Scholar
  11. 11.
    Pearl, J.: Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann Publishers Inc., San Francisco (1988)Google Scholar
  12. 12.
    Tappen, M.F., Freeman, W.T.: Comparison of graph cuts with belief propagation for stereo, using identical mrf parameters. In: IEEE International Conference on Computer Vision, Washington, DC, USA, p. 900. IEEE Computer Society, Los Alamitos (2003)CrossRefGoogle Scholar
  13. 13.
    Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(10), 1568–1583 (2006)CrossRefGoogle Scholar
  14. 14.
    Wainwright, M., Jaakkola, T., Willsky, A.: Map estimation via agreement on (hyper)trees: Message-passing and linear-programming approaches. IEEE Transactions on Information Theory 51(11), 3697–3717 (2005)CrossRefMathSciNetGoogle Scholar
  15. 15.
    Huang, J., Lee, A., Mumford, D.: Statistics of range images. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 324–331 (2000)Google Scholar
  16. 16.
    Lee, A.B., Mumford, D., Huang, J.: Occlusion models for natural images: A statistical study of a scale-invariant dead leaves model. International Journal of Computer Vision 41(1-2), 35–59 (2001)zbMATHCrossRefGoogle Scholar
  17. 17.
    Belhumeur, P.N., Mumford, D.: A bayesian treatment of the stereo correspondence problem using half-occluded regions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 506–512 (1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Fahim Mannan
    • 1
  • Michael Langer
    • 1
  1. 1.School of Computer ScienceMcGill University 

Personalised recommendations