Advertisement

International Journal of Computer Vision

, Volume 111, Issue 3, pp 298–314 | Cite as

SEEDS: Superpixels Extracted Via Energy-Driven Sampling

  • Michael Van den BerghEmail author
  • Xavier Boix
  • Gemma Roig
  • Luc Van Gool
Article

Abstract

Superpixel algorithms aim to over-segment the image by grouping pixels that belong to the same object. Many state-of-the-art superpixel algorithms rely on minimizing objective functions to enforce color homogeneity. The optimization is accomplished by sophisticated methods that progressively build the superpixels, typically by adding cuts or growing superpixels. As a result, they are computationally too expensive for real-time applications. We introduce a new approach based on a simple hill-climbing optimization. Starting from an initial superpixel partitioning, it continuously refines the superpixels by modifying the boundaries. We define a robust and fast to evaluate energy function, based on enforcing color similarity between the boundaries and the superpixel color histogram. In a series of experiments, we show that we achieve an excellent compromise between accuracy and efficiency. We are able to achieve a performance comparable to the state-of-the-art, but in real-time on a single Intel i7 CPU at 2.8 GHz.

Keywords

Superpixels Segmentation over-segmentation hill-climbing clustering histograms 

Notes

Acknowledgments

This work has been in part supported by the European Commission projects RADHAR (FP7 ICT 248873) and IURO (FP7 ICT 248314).

Supplementary material

11263_2014_744_MOESM1_ESM.pdf (1.3 mb)
Supplementary material 1 (pdf 1310 KB)

References

  1. Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & Süsstrunk, S. (2012). SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2274–2282.CrossRefGoogle Scholar
  2. Alexe, B., Deselaers, T., & Ferrari, V. (2012). Measuring the objectness of image windows. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2189–2202.CrossRefGoogle Scholar
  3. Arbelaez, P., Maire, M., Fowlkes, C., & Malik, J. (2011). Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(5), 898–916.CrossRefGoogle Scholar
  4. Boix, X., Gonfaus, J. M., van de Weijer, J., Bagdanov, A., Serrat, J., & Gonzàlez, J. (2012). Harmony potentials. International Journal of Computer Vision, 96(1), 83–102.CrossRefzbMATHMathSciNetGoogle Scholar
  5. Comaniciu, D., & Meer, P. (2002). Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5), 603–619.CrossRefGoogle Scholar
  6. Cour, T., Benezit, F., & Shi, J. (2005). Spectral segmentation with multiscale graph decomposition. In: Proceedings of the computer vision and pattern recognition.Google Scholar
  7. Eriksson, A., Olsson, C., & Kahl, F. (2007). Normalized cuts revisited: A reformulation for segmentation with linear grouping constraints. In: Proceedings of the IEEE international conference on computer vision.Google Scholar
  8. Felzenszwalb, P., & Huttenlocher, D. (2004). Efficient graph-based image segmentation. International Journal of Computer Vision, 59(2), 167–181.CrossRefGoogle Scholar
  9. Fulkerson, B., Vedaldi, A., & Soatto, S. (2009). Class segmentation and object localization with superpixel neighborhoods. In: Proceddings of the IEEE international conference on computer vision.Google Scholar
  10. Levinshtein, A., Stere, A., Kutulakos, K., Fleet, D., Dickinson, S., & Siddiqi, K. (2009). Turbopixels: Fast superpixels using geometric flows. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(12), 2290–2297.CrossRefGoogle Scholar
  11. Liu, M.Y., Tuzel, O., Ramalingam, S., & Chellappa, R. (2011). Entropy rate superpixel segmentation. In: Proceedings of the computer vision and pattern recognition.Google Scholar
  12. Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2001). A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings of the IEEE international conference on computer vision.Google Scholar
  13. Meyer, & F., Maragos, P. (1999). Multiscale morphological segmentations based on watershed, flooding, and eikonal PDE. In: Proceedings of the international conference on Scale-Space Theories in computer vision.Google Scholar
  14. Moore, A., Prince, S., Warrell, J., Mohammed, U., & Jones, G. (2008). Superpixel lattices. In: Proceedings of the computer vision and pattern recognition.Google Scholar
  15. Moore, A., Prince, S., & Warrell, J. (2010). Lattice cut. In: Proceedings of the computer vision and pattern recognition.Google Scholar
  16. Ren, X., & Malik, J. (2003). Learning a classication model for segmentation. In: Proceedings of the IEEE international conference on computer vision.Google Scholar
  17. Sharp, H. (1968). Cardinality of finite topologies. Journal of Combinatorial Theory, 5(1), 82–86.CrossRefzbMATHMathSciNetGoogle Scholar
  18. Shi, J., & Malik, J. (2000). Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8), 888–905.CrossRefGoogle Scholar
  19. Shotton, J., Johnson, M., & Cipolla, R. (2008). Semantic texton forests for image categorization and segmentation. In: Proceedings of the computer vision and pattern recognition.Google Scholar
  20. Van den Bergh, M., Boix, X., Roig, G., de Capitani, B, & Van Gool, L. (2012) . Seeds: Superpixels extracted via energy-driven sampling. In: Proceedings of the European conference on computer vision. Google Scholar
  21. Vedaldi, A., Soatto, S. (2008). Quick shift and kernel methods for mode seeking. In: Proceedings of the European conference on computer vision.Google Scholar
  22. Veksler, O., & Boykov, Y. (2010). Superpixels and supervoxels in an energy optimization framework. In: Proceedings of the European conference on computer vision.Google Scholar
  23. Vincent, L., & Soille, P. (1991). Watersheds in digital spaces: An efficient algorithm based on immersion simulations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13, 583–598.CrossRefGoogle Scholar
  24. Wang, S., Lu, H., Yang, F., & Yang, M.H. (2011). Superpixel tracking. In: Proceedings IEEE international conference on computer vision.Google Scholar
  25. Wertheimer M (1938) Laws of organization in perceptual forms. Harcourt, Brace & Jovanovitch.Google Scholar
  26. Wu, Z., & Leahy, R. (1993). An optimal graph theoretic approach to data clustering: Theory and its application to image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(11), 1101–1113.CrossRefGoogle Scholar
  27. Xu, L., Li, W., & Schuurmans, D. (2009). Fast normalized cut with linear constraints. In: Proceedings of the computer vision and pattern recognition.Google Scholar
  28. Zeng, G., Wang, P., Wang, J., Gan, R., & Zha, H. (2011). Structure-sensitive superpixels via geodesic distance. In: Proceedings IEEE international conference on computer vision.Google Scholar
  29. Zhang Y, Hartley R, Mashford J, & Burn S (2011) Superpixels via pseudo-boolean optimization. In: Proceedings IEEE international conference on computer vision.Google Scholar
  30. Zitnick, C., Jojic, N., & Kang, S. (2005). Consistent segmentation for optical flow estimation. In: Proceedings IEEE international conference on computer vision.Google Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • Michael Van den Bergh
    • 1
    Email author
  • Xavier Boix
    • 1
  • Gemma Roig
    • 1
  • Luc Van Gool
    • 1
  1. 1.ETH Zurich - Computer Vision LaboratoryZurichSwitzerland

Personalised recommendations