Advertisement

Spherical Superpixels: Benchmark and Evaluation

  • Liang Wan
  • Xiaorui Xu
  • Qiang ZhaoEmail author
  • Wei Feng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11366)

Abstract

Although a variety of superpixel algorithms have been developed and adopted as elementary tools in low-level computer vision and multimedia applications, most of them are designed for planar images. The quick growth of spherical panoramic images raises the urgent need of spherical superpixel algorithms and also a unifying benchmark of spherical image segmentation for the quantitative evaluation. In this paper, we present a general framework to establish spherical superpixel algorithms by extending planar counterparts, under which two spherical superpixel algorithms are developed. Furthermore, we propose the first segmentation benchmark of real-captured spherical images, which are manually annotated via a three-stage process. We use this benchmark to evaluate eight algorithms, including four spherical ones and the four corresponding planar ones, and discuss the results with respect to quantitative segmentation quality, runtime as well as visual quality.

Keywords

Superpixels Spherical image Panorama Benchmark Evaluation 

Notes

Acknowledgments

This work is supported by National Natural Science Foundation of China (61572354, 61671325, 61702479).

References

  1. 1.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE TPAMI 34(11), 2274–2282 (2012)CrossRefGoogle Scholar
  2. 2.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE TPAMI 33(5), 898–916 (2011)CrossRefGoogle Scholar
  3. 3.
    Van den Bergh, M., Boix, X., Roig, G., Van Gool, L.: Seeds: superpixels extracted via energy-driven sampling. IJCV 111(3), 298–314 (2015)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Bu, S., Liu, Z., Han, J., Wu, J.: Superpixel segmentation based structural scene recognition. In: ACM MM, pp. 681–684 (2013)Google Scholar
  5. 5.
    Cabral, R., Furukawa, Y.: Piecewise planar and compact floorplan reconstruction from images. In: IEEE CVPR, pp. 628–635 (2014)Google Scholar
  6. 6.
    Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE TPAMI 24(5), 603–619 (2002)CrossRefGoogle Scholar
  7. 7.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. IJCV 59(2), 167–181 (2004)CrossRefGoogle Scholar
  8. 8.
    Feng, W., Jia, J., Liu, Z.Q.: Self-validated labeling of markov random fields for image segmentation. IEEE TPAMI 32(10), 1871–1887 (2010)CrossRefGoogle Scholar
  9. 9.
    Fu, H., Cao, X., Tang, D., Han, Y., Xu, D.: Regularity preserved superpixels and supervoxels. IEEE TMM 16(4), 1165–1175 (2014)Google Scholar
  10. 10.
    Giraud, R., Ta, V.T., Papadakis, N.: Robust shape regularity criteria for superpixel evaluation. In: IEEE ICIP (2017)Google Scholar
  11. 11.
    Koniusz, P., Mikolajczyk, K.: Segmentation based interest points and evaluation of unsupervised image segmentation methods. In: BMVC, pp. 1–11 (2009)Google Scholar
  12. 12.
    Lei, J., et al.: A universal framework for salient object detection. IEEE TMM 18(9), 1783–1795 (2016)Google Scholar
  13. 13.
    Levinshtein, A., Stere, A., Kutulakos, K.N., Fleet, D.J., Dickinson, S.J., Siddiqi, K.: Turbopixels: fast superpixels using geometric flows. IEEE TPAMI 31(12), 2290–2297 (2009)CrossRefGoogle Scholar
  14. 14.
    Li, L., Feng, W., Wan, L., Zhang, J.: Maximum cohesive grid of superpixels for fast object localization. In: IEEE CVPR, pp. 3174–3181 (2013)Google Scholar
  15. 15.
    Li, Z., Chen, J.: Superpixel segmentation using linear spectral clustering. In: IEEE CVPR, pp. 1356–1363 (2015)Google Scholar
  16. 16.
    Liu, M.Y., Tuzel, O., Ramalingam, S., Chellappa, R.: Entropy rate superpixel segmentation. In: IEEE CVPR, pp. 2097–2104 (2011)Google Scholar
  17. 17.
    Liu, S., et al.: Fashion parsing with weak color-category labels. IEEE TMM 16(1), 253–265 (2014)Google Scholar
  18. 18.
    Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: IEEE ICCV, pp. 416–423 (2001)Google Scholar
  19. 19.
    Micusik, B., Kosecka, J.: Piecewise planar city 3D modeling from street view panoramic sequences. In: IEEE CVPR, pp. 2906–2912 (2009)Google Scholar
  20. 20.
    Neubert, P., Protzel, P.: Compact watershed and preemptive SLIC: on improving trade-offs of superpixel segmentation algorithms. In: IEEE ICPR, pp. 996–1001 (2014)Google Scholar
  21. 21.
    Ren, Z., Hu, Y., Chia, L.T., Rajan, D.: Improved saliency detection based on superpixel clustering and saliency propagation. In: ACM MM, pp. 1099–1102 (2010)Google Scholar
  22. 22.
    Schick, A., Fischer, M., Stiefelhagen, R.: An evaluation of the compactness of superpixels. PRL 43, 71–80 (2014)CrossRefGoogle Scholar
  23. 23.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE TPAMI 22(8), 888–905 (2000)CrossRefGoogle Scholar
  24. 24.
    Strassburg, J., Grzeszick, R., Rothacker, L., Fink, G.A.: On the influence of superpixel methods for image parsing. In: VISAPP (2), pp. 518–527 (2015)Google Scholar
  25. 25.
    Stutz, D., Hermans, A., Leibe, B.: Superpixels: an evaluation of the state-of-the-art. CVIU 166, 1–27 (2017)Google Scholar
  26. 26.
    Tasli, H.E., Cigla, C., Gevers, T., Alatan, A.A.: Super pixel extraction via convexity induced boundary adaptation. In: IEEE ICME, pp. 1–6 (2013)Google Scholar
  27. 27.
    Xiao, J., Ehinger, K.A., Oliva, A., Torralba, A.: Recognizing scene viewpoint using panoramic place representation. In: IEEE CVPR, pp. 2695–2702 (2012)Google Scholar
  28. 28.
    Yang, H., Zhang, H.: Efficient 3D room shape recovery from a single panorama. In: CVPR, pp. 5422–5430 (2016)Google Scholar
  29. 29.
    Yao, J., Boben, M., Fidler, S., Urtasun, R.: Real-time coarse-to-fine topologically preserving segmentation. In: IEEE CVPR, pp. 2947–2955 (2015)Google Scholar
  30. 30.
    Zhao, Q., Wan, L., Feng, W., Zhang, J., Wong, T.: Cube2video: navigate between cubic panoramas in real-time. IEEE TMM 15(8), 1745–1754 (2013)Google Scholar
  31. 31.
    Zhao, Q., Dai, F., Ma, Y., Wan, L., Zhang, J., Zhang, Y.: Spherical superpixel segmentation. IEEE TMM 20(6), 1406–1417 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Liang Wan
    • 1
    • 2
  • Xiaorui Xu
    • 1
    • 2
  • Qiang Zhao
    • 3
    Email author
  • Wei Feng
    • 1
    • 2
  1. 1.College of Intelligence and ComputingTianjin UniversityTianjinChina
  2. 2.Key Research Center for Surface Monitoring and Analysis of Cultural Relics (SMARC)SACHTianjinChina
  3. 3.Institute of Computing TechnologyChinese Academy of SciencesBeijingChina

Personalised recommendations