Dynamic Hierarchical Segmentation of Remote Sensing Images

  • Giuseppe Scarpa
  • Giuseppe Masi
  • Raffaele Gaetano
  • Luisa Verdoliva
  • Giovanni Poggi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8156)

Abstract

Recursive tree-structured segmentation is a powerful tool to deal with the non-stationary nature of images. By fitting model parameters to each region/class under analysis one can adapt the segmentation algorithm to the local image statistics, thus improving accuracy. However, a single model/segmenter cannot fit regions with wildly different nature, and one should be allowed to select in a suitable library the tool most suited to the local statistics. In this paper, we implement this dynamic segmentation/classification paradigm, using two segmenters, based on spectral and textural properties, respectively, and defining suitable rules for switching model locally. Experiments on remote-sensing mosaics show that the multiple-model dynamic algorithm largely outperforms comparable single-model segmenters.

Keywords

Image segmentation image model hierarchical segmentation 

References

  1. 1.
    Benboudjema, D., Pieczynski, W.: Unsupervised Statistical Segmentation of Nonstationary Images Using Triplet Markov Fields. IEEE Trans. on Pattern Analysis and Machine Intelligence 29, 1367–1378 (2007)CrossRefGoogle Scholar
  2. 2.
    Liu, G., Qin, Q., Mei, T., Xie, W., Wang, L.: Supervised Image Segmentation Based on Tree-Structured MRF Model in Wavelet Domain. IEEE Geoscience and Remote Sensing Letters 6, 850–854 (2009)CrossRefGoogle Scholar
  3. 3.
    D’Elia, C., Poggi, G., Scarpa, G.: A tree-structured Markov random field model for Bayesian image segmentation. IEEE Trans. on Image Processing 12, 1259–1273 (2003)MathSciNetCrossRefGoogle Scholar
  4. 4.
    D’Elia, C., Marrocco, C., Molinara, M., Poggi, G., Scarpa, G., Tortorella, F.: Detection of microcalcifications clusters in mammograms through TS-MRF segmentation and SVM-based classification. In: The 17th International Conference on Pattern Recognition, ICPR 2004, vol. 3, pp. 742–745 (2004)Google Scholar
  5. 5.
    Masi, G., Gaetano, R., Scarpa, G., Poggi, G.: Dynamic segmentation for image information mining. In: IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010, pp. 1992–1995 (July 2010)Google Scholar
  6. 6.
    Li, S.Z.: Markov random field modeling in image analysis. Springer (2001)Google Scholar
  7. 7.
    Scarpa, G., Haindl, M.: Unsupervised texture segmentation by spectral-spatial-independent clustering. In: The 18th International Conference on Pattern Recognition, ICPR 2006, vol. 2, pp. 151–154 (August 2006)Google Scholar
  8. 8.
    Scarpa, G., Haindl, M., Zerubia, J.: A Hierarchical Finite-State Model for Texture Segmentation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2007, vol. 1, pp. I-1209–I-1212 (2007)Google Scholar
  9. 9.
    Gaetano, R., Scarpa, G., Poggi, G.: Hierarchical texture-based segmentation of multiresolution remote-sensing images. IEEE Trans. on Geoscience and Remote Sensing 47, 2129–2141 (2009)CrossRefGoogle Scholar
  10. 10.
    Gaetano, R., Scarpa, G., Poggi, G.: Recursive Texture Fragmentation and Reconstruction segmentation algorithm applied to VHR images. In: IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2009, pp. IV–101–104 (2009)Google Scholar
  11. 11.
    Li, Y., Bretschneider, T.R.: Semantic-Sensitive Satellite Image Retrieval. IEEE Trans. on Geoscience and Remote Sensing 45, 853–860 (2007)CrossRefGoogle Scholar
  12. 12.
    Cagnazzo, M., Poggi, G., Verdoliva, L.: Region-based transform coding of multispectral images. IEEE Trans. on Image Processing 16, 2916–2926 (2007)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Cagnazzo, M., Parrilli, S., Poggi, G., Verdoliva, L.: Improved class-based coding of multispectral images with shape-adaptive wavelet transform. IEEE Geoscience and Remote Sensing Letters 4, 566–570 (2009)CrossRefGoogle Scholar
  14. 14.
    Parrilli, S., Poderico, M., Angelino, C.V., Scarpa, G., Verdoliva, L.: A nonlocal approach for SAR image denoising. In: IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010, pp. 726–729 (2010)Google Scholar
  15. 15.
    Mikes, S., Haindl, M., Scarpa, G.: Remote sensing segmentation benchmark. In: The 7th IAPR International Workshop on Pattern Recognition in Remote Sensing, PRRS 2012, Tsukuba Science City, Japan (November 2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Giuseppe Scarpa
    • 1
  • Giuseppe Masi
    • 1
  • Raffaele Gaetano
    • 2
  • Luisa Verdoliva
    • 1
  • Giovanni Poggi
    • 1
  1. 1.DIETIUniversity Federico II of NaplesItaly
  2. 2.TELECOM-ParisTechFrance

Personalised recommendations