Precision-Recall-Classification Evaluation Framework: Application to Depth Estimation on Single Images

  • Guillem Palou Visa
  • Philippe Salembier
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8689)


Many computer vision applications involve algorithms that can be decomposed in two main steps. In a first step, events or objects are detected and, in a second step, detections are assigned to classes. Examples of such “detection plus classification” problems can be found in human pose classification, object recognition or action classification among others. In this paper, we focus on a special case: depth ordering on single images. In this problem, the detection step consists of the image segmentation, and the classification step assigns a depth gradient to each contour or a depth order to each region. We discuss the limitations of the classical Precision-Recall evaluation framework for these kind of problems and define an extended framework called “Precision-Recall-Classfication” (PRC). Then, we apply this framework to depth ordering problems and design two specific PRC measures to evaluate both the local and the global depth consistencies. We use these measures to evaluate precisely state of the art depth ordering systems for monocular images. We also propose an extension to the method of [2] applying an optimal graph cut on a hierarchical segmentation structure. The resulting system is proven to provide better results than state of the art algorithms.


Precision-Recall Detection Classification Depth ordering 


  1. 1.
    Arbeláez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE TPAMI 33(5), 898–916 (2011)CrossRefGoogle Scholar
  2. 2.
    Calderero, F., Caselles, V.: Recovering relative depth from low-level features without explicit T-junction detection and interpretation. IEEE IJCV (2013) (in Press)Google Scholar
  3. 3.
    Dimiccoli, M.: Monocular Depth Estimation for Image Segmentation and Filtering. Ph.D. thesis, Universitat Politecnica de Catalunya (2009)Google Scholar
  4. 4.
    Fowlkes, C.C., Martin, D.R., Malik, J.: Local figure-ground cues are valid for natural images. Journal of Vision 7(8), 2 (2007)CrossRefGoogle Scholar
  5. 5.
    Hoiem, D., Efros, A.A., Hebert, M.: Recovering Surface Layout from an Image. IEEE IJCV 75(1), 151–172 (2007)CrossRefGoogle Scholar
  6. 6.
    Hoiem, D., Efros, A.A., Hebert, M.: Recovering Occlusion Boundaries from an Image. IEEE IJCV 91(3), 328–346 (2011)zbMATHMathSciNetCrossRefGoogle Scholar
  7. 7.
    Kumar, M.P., Packer, B., Koller, D.: Self-paced learning for latent variable models. In: Advances in Neural Information Processing Systems, pp. 1189–1197 (2010)Google Scholar
  8. 8.
    Lee, A.B., Mumford, D., Huang, J.: Occlusion models for natural images: A statistical study of a scale-invariant dead leaves model. IEEE IJCV 41(1-2), 35–59 (2001)zbMATHCrossRefGoogle Scholar
  9. 9.
    Leichter, I., Lindenbaum, M.: Boundary ownership by lifting to 2.1D. In: IEEE ICCV, pp. 9–16 (2009)Google Scholar
  10. 10.
    Liu, B., Gould, S., Koller, D.: Single image depth estimation from predicted semantic labels. In: IEEE CVPR, pp. 1253–1260 (2010)Google Scholar
  11. 11.
    Maire, M.: Simultaneous Segmentation and Figure/Ground Organization Using Angular Embedding. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 450–464. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  12. 12.
    Maire, M., Arbelaez, P., Fowlkes, C., Malik, J.: Using contours to detect and localize junctions in natural images. In: IEEE CVPR, pp. 1–8 (2008)Google Scholar
  13. 13.
    Maire, M.R.: Contour Detection and Image Segmentation. Ph.D. thesis, University of California, Berkeley (2009)Google Scholar
  14. 14.
    Martin, D.R., Fowlkes, C.C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE TPAMI 26(5), 530–549 (2004)CrossRefGoogle Scholar
  15. 15.
    Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Comm. on Pure and Applied Mathematics 42(5), 577–685 (1989)zbMATHMathSciNetCrossRefGoogle Scholar
  16. 16.
    Palou, G., Salembier, P.: Depth ordering on image sequences using motion occlusions. In: IEEE ICIP, Orlando, FL, USA (2012)Google Scholar
  17. 17.
    Palou, G., Salembier, P.: Monocular Depth Ordering Using T-junctions and Convexity Occlusion Cues. IEEE Trans. on Image Proc. (2013)Google Scholar
  18. 18.
    Ren, X., Fowlkes, C.C., Malik, J.: Figure/Ground Assignment in Natural Images. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 614–627. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  19. 19.
    Salembier, P., Garrido, L.: Binary partition tree as an efficient representation for image processing, segmentation, and information retrieval. IEEE Trans. on Image Processing 9(4), 561–576 (2000)CrossRefGoogle Scholar
  20. 20.
    Saxena, A., Ng, A., Chung, S.: Learning Depth from Single Monocular Images. In: IEEE NIPS, vol. 18 (2005)Google Scholar
  21. 21.
    Serra, J., Kiran, B.R., Cousty, J.: Hierarchies and Climbing Energies. In: Alvarez, L., Mejail, M., Gomez, L., Jacobo, J. (eds.) CIARP 2012. LNCS, vol. 7441, pp. 821–828. Springer, Heidelberg (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Guillem Palou Visa
    • 1
  • Philippe Salembier
    • 1
  1. 1.Technical University of CataloniaBarcelonaSpain

Personalised recommendations