Improved Classification of SAR Sea Ice Imagery Based on Segmentation

This paper presents a method for semi-supervised classification of polarimetric synthetic aperture radar (PolSAR) sea ice data. The method consists of two steps. In the first stage, a markov random field on region adjacency graph is constructed on the initial watershed oversegmented result. While in the second stage, the Wishart distribution model and maximum a posterior (MAP) are applied as the criterion for obtaining the optimal classification. Good experimental results and less time- consuming are obtained when this method is applied to PolSAR data sets of sea ice in the Beaufort Sea acquired by the airborne AIRSAR.

[1]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[2]  N. R. Goodman.  Statistical analysis based on a certain multivariate complex Gaussian distribution , 1963 .

[3]  Jeff A. Bilmes,et al.  A gentle tutorial of the em algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models , 1998 .

[4]  Laurent Ferro-Famil,et al.  Unsupervised classification of multifrequency and fully polarimetric SAR images based on the H/A/Alpha-Wishart classifier , 2001, IEEE Trans. Geosci. Remote. Sens..

[5]  J. S. Lee,et al.  A review of polarimetry in the context of synthetic aperture radar: concepts and information extraction , 2004 .

[6]  Scott T. Acton,et al.  Polarimetric SAR image segmentation using texture partitioning and statistical analysis , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[7]  Kari Saarinen.  Color image segmentation by a watershed algorithm and region adjacency graph processing , 1994, Proceedings of 1st International Conference on Image Processing.

[8]  I. Hajnsek,et al.  Classification strategies for polarimetric SAR sea ice data , 2003 .

[9]  Stan Z. Li,et al.  Markov Random Field Modeling in Image Analysis , 2001, Computer Science Workbench.

[10]  Laurent Najman,et al.  Geodesic Saliency of Watershed Contours and Hierarchical Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Hong Sun,et al.  An Unsupervised Segmentation Method Using Markov Random Field on Region Adjacency Graph for SAR Images , 2006, 2006 CIE International Conference on Radar.

[12]  Knut Conradsen,et al.  A test statistic in the complex Wishart distribution and its application to change detection in polarimetric SAR data , 2003, IEEE Trans. Geosci. Remote. Sens..