Classification of Polarimetric SAR Data Based on Multidimensional Watershed Clustering

  • Wen Yang
  • Hao Wang
  • Yongfeng Cao
  • Haijian Zhang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4093)


This paper proposes a polarimetric synthetic aperture radar (PolSAR) data classification method which applies multi-dimensional transform to identify density peaks and valleys for polarimetric signatures clustering. The new approach firstly introduces an improved maximum homogeneous region filter which can effectively preserve structure feature and polarimetric signatures. Then polarimetric signatures are extracted based on Freeman-Durden three-component composition. Finally, we obtain the classification results by multi-dimensional watershed clustering on the extracted polarimetric signatures. The effectiveness of this classification scheme is demonstrated using the full polarimetric L-band SAR imagery.


Synthetic Aperture Radar Unsupervised Classification Density Space Catchment Basin Speckle Reduction 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Touzi, R., Boerner, W.M., Lee, J.S., Lueneburg, E.: A Review of Polarimetry in the Context of Synthetic Aperture Radar: Concepts and Information Extraction. Can. J. Remote Sensing 30(3), 380–407 (2004)CrossRefGoogle Scholar
  2. 2.
    Lee, J.S., Grues, M.R., Pottier, E., Ferro-Famil, L.: Unsupvised Terrain Classification Preserving Polarimetric Scattering Characteristics. IEEE Trans. Geosci. Remote Sensing 42(4), 722–731 (2004)CrossRefGoogle Scholar
  3. 3.
    Freeman, A., Durden, S.L.: A Three-component Scattering Model for Polarimetric SAR Data. IEEE Trans.Geosci.Remote Sensing 36(3), 963–973 (1998)CrossRefGoogle Scholar
  4. 4.
    Lee, J.S., Grues, M.R., Grandi, G., Polarimetric, S.A.R.: speckle filtering and its implication for classification. IEEE Trans.Geosci.Remote Sensing 37(5), 2363–2373 (1999)CrossRefGoogle Scholar
  5. 5.
    Andy, M.Y., Chris, D., Tony, F.C.: Dynamic Cluster Formation Using Level Set Methods. IEEE Trans. Pattern Anal. Machine Intell. 28(6), 877–889 (2006)CrossRefGoogle Scholar
  6. 6.
    Najman, L., Schmitt, M.: Geodesic Saliecy of Watershed Edges and Hierarchical Segmentation. IEEE Trans. Pattern Anal. Machine Intell. 18(12), 1163–1173 (1996)CrossRefGoogle Scholar
  7. 7.
    Hao, W., Yongfeng, C., Hong, S.: Clustering Analysis Based on Watershed Transform. In: Proceedings of CCSP 2005, August 2005, pp. 375–378 (2005)Google Scholar
  8. 8.
    Grimaud, M.: A New Measure of Contrast: Dynamics. In: Proc. Image Algebra and Morphological Processing III, San Diego, July 1992. SPIE, vol. 1769, pp. 292–305 (1992)Google Scholar
  9. 9.
    Yongfeng, C., Hong, S., Xin, X.: One Novel and Efficient Multi-level Thresholding Method. In: Proceedings of SPIE, vol. 5286(1), pp. 330–333 (2003)Google Scholar
  10. 10.
    Lee, J.S., Grunes, M.R., Pottier, E.: Quantitative Comparison of Classification Capability: Fully Polarimetric versus Dual and Single-polarisation SAR. IEEE Trans. Geosci. Remote Sensing 39(11), 2343–2351 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Wen Yang
    • 1
    • 2
  • Hao Wang
    • 1
  • Yongfeng Cao
    • 1
  • Haijian Zhang
    • 1
  1. 1.School of Electronic InformationWuhan UniversityWuhanChina
  2. 2.SOA Key Laboratory for Polar SciencePolar Research Institute of ChinaShanghaiChina

Personalised recommendations