Advertisement

Superpixel Segmentation: An Evaluation

  • David Stutz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9358)

Abstract

In recent years, superpixel algorithms have become a standard tool in computer vision and many approaches have been proposed. However, different evaluation methodologies make direct comparison difficult. We address this shortcoming with a thorough and fair comparison of thirteen state-of-the-art superpixel algorithms. To include algorithms utilizing depth information we present results on both the Berkeley Segmentation Dataset [3] and the NYU Depth Dataset [19]. Based on qualitative and quantitative aspects, our work allows to guide algorithm selection by identifying important quality characteristics.

References

  1. 1.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels. Technical report, École Polytechnique Fédérale de Lausanne, Lusanne, Switzerland, June 2010Google Scholar
  2. 2.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2281 (2012)CrossRefGoogle Scholar
  3. 3.
    Arbeláez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2011)CrossRefGoogle Scholar
  4. 4.
    Drucker, F., MacCormick, J.: Fast superpixels for video analysis. In: WMVC, pp. 1–8. IEEE Computer Society, Snowbird, Utah, December 2009Google Scholar
  5. 5.
    Felzenswalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)CrossRefGoogle Scholar
  6. 6.
    Gupta, S., Arbeláez, P., Malik, J.: Perceptual organization and recognition of indoor scenes from RGB-D images. In: CVPR, pp. 564–571. IEEE Computer Society, Portland, Oregon, June 2013Google Scholar
  7. 7.
    Levinshtein, A., Stere, A., Kutulakos, K.N., Fleet, D.J., Dickinson, S.J., Siddiqi, K.: TurboPixels: fast superpixels using geometric flows. IEEE Trans. Pattern Anal. Mach. Intell. 31(12), 2290–2297 (2009)CrossRefGoogle Scholar
  8. 8.
    Lui, M.Y., Tuzel, O., Ramalingam, S., Chellappa, R.: Entropy rate superpixel segmentation. In: CVPR, pp. 2097–2104. IEEE Computer Society, Providence, RI, June 2011Google Scholar
  9. 9.
    Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans. Pattern Anal. Mach. Intell. 26(5), 530–549 (2004)CrossRefGoogle Scholar
  10. 10.
    Mester, R., Conrad, C., Guevara, A.: Multichannel segmentation using contour relaxation: fast super-pixels and temporal propagation. In: Heyden, A., Kahl, F. (eds.) SCIA 2011. LNCS, vol. 6688, pp. 250–261. Springer, Heidelberg (2011) CrossRefGoogle Scholar
  11. 11.
    Moore, A.P., Prince, S.J.D., Warrell, J., Mohammed, U., Jones, G.: Superpixel lattices. In: CVPR, pp. 1–8. IEEE Computer Society, Anchorage, AK, June 2008Google Scholar
  12. 12.
    Neubert, P., Protzel, P.: Superpixel benchmark and comparison. In: Forum Bildverarbeitung, Regensburg, Germany, November 2012Google Scholar
  13. 13.
    Papon, J., Abramov, A., Schoeler, M., Wörgötter, F.: Voxel cloud connectivity segmentation - supervoxels for point clouds. In: CVPR, pp. 2027–2034. IEEE Computer Society, Portland, Oregon, June 2013Google Scholar
  14. 14.
    Perbet, F., Maki, A.: Homogeneous superpixels from random walks. In: (IAPR) MVA, pp. 26–30. Nara, Japan, June 2011Google Scholar
  15. 15.
    Ren, X., Bo, L.: Discriminatively trained sparse code gradients for contour detection. In: Bartlett, P.L., Pereira, F.C.N., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) NIPS, vol. 25, pp. 584–592. Curran Associates, Red Hook, New York (2012)Google Scholar
  16. 16.
    Ren, X., Malik, J.: Learning a classification model for segmentation. In: ICCV, pp. 10–17. IEEE Computer Society, Nice, France, October 2003Google Scholar
  17. 17.
    Rohkohl, C., Engel, K.: Efficient image segmentation using pairwise pixel similarities. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 254–263. Springer, Heidelberg (2007) CrossRefGoogle Scholar
  18. 18.
    Schick, A., Fischer, M., Stiefelhagen, R.: Measuring and evaluating the compactness of superpixels. In: ICPR, pp. 930–934. IEEE Computer Society, Tsukuba, Japan, November 2012Google Scholar
  19. 19.
    Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 746–760. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  20. 20.
    Siva, P., Wong, A.: Grid seams: A fast superpixel algorithm for real-time applications. In: CRV, pp. 127–134. IEEE Computer Society, Montreal, Canada, May 2014Google Scholar
  21. 21.
    Stutz, D.: Superpixel segmentation using depth information. B.Sc. thesis, Computer Vision Group, RWTH Aachen University, Aachen, Germany, September 2014. http://davidstutz.de/projects/superpixelsseeds/
  22. 22.
    Tang, D., Fu, H., Cao, X.: Topology preserved regular superpixel. In: ICME, pp. 765–768. IEEE Computer Society, Melbourne, Australia, July 2012Google Scholar
  23. 23.
    Van den Bergh, M., Boix, X., Roig, G., de Capitani, B., Van Gool, L.: SEEDS: superpixels extracted via energy-driven sampling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol. 7578, pp. 13–26. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  24. 24.
    Vedaldi, A., Soatto, S.: Quick shift and Kernel methods for mode seeking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 705–718. Springer, Heidelberg (2008) CrossRefGoogle Scholar
  25. 25.
    Veksler, O., Boykov, Y., Mehrani, P.: Superpixels and supervoxels in an energy optimization framework. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 211–224. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  26. 26.
    Wang, S., Lu, H., Yang, F., Yang, M.H.: Superpixel tracking. In: ICCV, pp. 1323–1330. IEEE Computer Society, Barcelona, Spain, November 2011Google Scholar
  27. 27.
    Weikersdorfer, D., Gossow, D., Beetz, M.: Depth-adaptive superpixels. In: ICPR. pp. 2087–2090. IEEE Computer Society, Tsukuba, Japan, November 2012Google Scholar
  28. 28.
    Zeng, G., Wang, P., Wang, J., Gan, R., Zha, H.: Structure-sensitive superpixels via geodesic distance. In: ICCV, pp. 447–454. IEEE Computer Society, Barcelona, Spain, November 2011Google Scholar
  29. 29.
    Zhang, Y., Hartley, R., Mashford, J., Burn, S.: Superpixels via pseudo-boolean optimization. In: ICCV, pp. 1387–1394. IEEE Computer Society, Barcelona, Spain, November 2011Google Scholar
  30. 30.
    Zhang, Y., Hartley, R., Mashford, J., Burn, S.: Superpixels, occlusion and stereo. In: DICTA, pp. 84–91. IEEE Computer Society, Noosa, Australia, December 2011Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Open Access This chapter is distributed under the terms of the Creative Commons Attribution Noncommercial License, which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.

Authors and Affiliations

  1. 1.Computer Vision GroupRWTH Aachen UniversityAachenGermany

Personalised recommendations