Advertisement

Fast Tiered Labeling with Topological Priors

  • Ying Zheng
  • Steve Gu
  • Carlo Tomasi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7575)

Abstract

We consider labeling an image with multiple tiers. Tiers, one on top of another, enforce a strict vertical order among objects (e.g. sky is above the ground). Two new ideas are explored: First, under a simplification of the general tiered labeling framework proposed by Felzenszwalb and Veksler [1], we design an efficient O(KN) algorithm for the approximate optimal labeling of an image of N pixels with K tiers. Our algorithm runs in over 100 frames per second on images of VGA resolutions when K is less than 6. When K = 3, our solution overlaps with the globally optimal one by Felzenszwalb and Veksler in over 99% of all pixels but runs 1000 times faster. Second, we define a topological prior that specifies the number of local extrema in the tier boundaries, and give an O(NM) algorithm to find a single, optimal tier boundary with exactly M local maxima and minima. These two extensions enrich the general tiered labeling framework and enable fast computation. The proposed topological prior further improves the accuracy in labeling details.

Keywords

Markov Random Field Local Extremum Relation Graph Label Problem Bottom Tier 
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.

References

  1. 1.
    Felzenszwalb, P., Veksler, O.: Tiered scene labeling with dynamic programming. In: IEEE CVPR, pp. 3097–3104 (2010)Google Scholar
  2. 2.
    Li, S.: Markov random field modeling in computer vision. Computer science workbench. Springer (1995)Google Scholar
  3. 3.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE PAMI 23, 1222–1239 (2001)CrossRefGoogle Scholar
  4. 4.
    Ishikawa, H.: Exact optimization for markov random fields with convex priors. IEEE PAMI 25, 1333–1336 (2003)CrossRefGoogle Scholar
  5. 5.
    Winn, J., Shotton, J.: The layout consistent random field for recognizing and segmenting partially occluded objects. In: IEEE CVPR, pp. 37–44 (2006)Google Scholar
  6. 6.
    Kohli, P., Ladicky, L., Torr, P.: Robust higher order potentials for enforcing label consistency. IJCV 82, 302–324 (2009)CrossRefGoogle Scholar
  7. 7.
    Liu, X., Veksler, O., Samarabandu, J.: Order-preserving moves for graph-cut-based optimization. IEEE PAMI 32, 1182–1196 (2010)CrossRefGoogle Scholar
  8. 8.
    Strekalovskiy, E., Cremers, D.: Generalized ordering constraints for multilabel optimization. In: ICCV (2011)Google Scholar
  9. 9.
    Greig, D., Porteous, B., Seheult, A.: Exact maximum a posteriori estimation for binary images. Journal of the Royal Statistical Society 51(2), 271–279 (1989)Google Scholar
  10. 10.
    Kolmogorov, V., Rother, C.: Minimizing nonsubmodular functions with graph cuts-a review. IEEE PAMI 29, 1274–1279 (2007)CrossRefGoogle Scholar
  11. 11.
    Liu, C., Yuen, J., Torralba, A.: Sift flow: Dense correspondence across scenes and its applications. IEEE PAMI 33, 978–994 (2011)CrossRefGoogle Scholar
  12. 12.
    Edelsbrunner, H., Letscher, D., Zomorodian, A.: Topological persistence and simplification. Discrete & Computational Geometry 28, 511–533 (2002)MathSciNetzbMATHCrossRefGoogle Scholar
  13. 13.
    Edelsbrunner, H., Harer, J., Zomorodian, A.: Hierarchical morse-smale complexes for piecewise linear 2-manifolds. Discrete & Computational Geometry 30, 87–107 (2003)MathSciNetzbMATHCrossRefGoogle Scholar
  14. 14.
    Gu, S., Zheng, Y., Tomasi, C.: Oscillation regularization. In: The 37th International Conference on Acoustics, Speech, and Signal Processing (2012)Google Scholar
  15. 15.
    Felzenszwalb, P., Huttenlocher, D.: Distance transforms of sampled functions. Technical Report TR2004-1963, Cornell Computing and Information Science (2004)Google Scholar
  16. 16.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV 42, 145–175 (2001)zbMATHCrossRefGoogle Scholar
  17. 17.
    Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: IEEE CVPR, pp. 413–420 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Ying Zheng
    • 1
  • Steve Gu
    • 1
  • Carlo Tomasi
    • 1
  1. 1.Duke UniversityU.S.A.

Personalised recommendations