Segmentation of textured polarimetric SAR scenes by likelihood approximation

A hierarchical stepwise optimization process is developed for polarimetric synthetic aperture radar image segmentation. We show that image segmentation can be viewed as a likelihood approximation problem. The likelihood segment merging criteria are derived using the multivariate complex Gaussian, the Wishart distribution, and the K-distribution. In the presence of spatial texture, the Gaussian-Wishart segmentation is not appropriate. The K-distribution segmentation is more effective in textured forested areas. The validity of the product model is also assessed, and a field-adaptable segmentation strategy combining different criteria is examined.

[1]  Rama Chellappa,et al.  Unsupervised segmentation of polarimetric SAR data using the covariance matrix , 1992, IEEE Trans. Geosci. Remote. Sens..

[2]  Thomas L. Ainsworth,et al.  Unsupervised classification using polarimetric decomposition and the complex Wishart classifier , 1999, IEEE Trans. Geosci. Remote. Sens..

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

[4]  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..

[5]  Arno Schäpe,et al.  Multiresolution Segmentation : an optimization approach for high quality multi-scale image segmentation , 2000 .

[6]  Dan R. Sheen,et al.  Statistical and spatial properties of forest clutter measured with polarimetric synthetic aperture radar (SAR) , 1992, IEEE Trans. Geosci. Remote. Sens..

[7]  J. Lira,et al.  An automated region growing algorithm for segmentation of texture regions in SAR images , 1998 .

[8]  Shaun Quegan,et al.  Quantitative comparison of the performance of SAR segmentation algorithms , 1998, IEEE Trans. Image Process..

[9]  Mihai Datcu,et al.  Model-based despeckling and information extraction from SAR images , 2000, IEEE Trans. Geosci. Remote. Sens..

[10]  Linda G. Shapiro,et al.  Image Segmentation Techniques , 1984, Other Conferences.

[11]  Paris W. Vachon,et al.  Coherence estimation for SAR imagery , 1999, IEEE Trans. Geosci. Remote. Sens..

[12]  J. Le Moigne.  Refining Image Segmentation by Integration of Edge and Region Data , 1992, [Proceedings] IGARSS '92 International Geoscience and Remote Sensing Symposium.

[13]  Ron Kwok,et al.  Classification of multi-look polarimetric SAR imagery based on complex Wishart distribution , 1994 .

[14]  Morris Goldberg,et al.  Hierarchy in Picture Segmentation: A Stepwise Optimization Approach , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  A. K. Milne,et al.  Segmentation of radar imagery using the Gaussian Markov random field model , 1999 .

[16]  Donald B. Percival,et al.  Probability density functions for multilook polarimetric signatures , 1994, IEEE Trans. Geosci. Remote. Sens..

[17]  R. K. Hawkins,et al.  The CCRS Airborne SAR Systems: Radar for Remote Sensing Research , 1995 .

[18]  Knut Conradsen,et al.  Evaluation of the Wishart test statistics for polarimetric SAR data , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[19]  K. Ranson,et al.  K-distribution for multi-look processed polarimetric SAR imagery , 1994, Proceedings of IGARSS '94 - 1994 IEEE International Geoscience and Remote Sensing Symposium.

[20]  D. Blacknell,et al.  Comparison of parameter estimators for K-distribution , 1994 .

[21]  Steven W. Zucker,et al.  Region growing: Childhood and adolescence* , 1976 .

[23]  U. Benz,et al.  Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information , 2004 .

[24]  Donald B. Percival,et al.  Maximum likelihood estimation of K distribution parameters for SAR data , 1993, IEEE Trans. Geosci. Remote. Sens..

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

[26]  Rod Cook,et al.  MUM (Merge Using Moments) segmentation for SAR images , 1994, Remote Sensing.

[27]  J. Kong,et al.  K-Distribution and Polarimetric Terrain Radar Clutter , 1990, Progress In Electromagnetics Research.

[28]  Ridha Touzi,et al.  A review of speckle filtering in the context of estimation theory , 2002, IEEE Trans. Geosci. Remote. Sens..

[29]  L. Norikane,et al.  Data volume reduction for imaging radar polarimeter , 1989, Digest on Antennas and Propagation Society International Symposium.

[30]  G. Liu,et al.  Study on segmentation and interpretation of multi-look polarimetric SAR images , 2000 .

[31]  Jin Au Kong,et al.  Classification of Earth Terrain Using Polarimetric Synthetic Aperture Radar Images , 1989, Progress In Electromagnetics Research.

[32]  Philippe Marthon,et al.  An optimal multiedge detector for SAR image segmentation , 1998, IEEE Trans. Geosci. Remote. Sens..

[33]  Rod Cook,et al.  Segmentation and simulated annealing , 1996, Remote Sensing.

[34]  Knut Conradsen,et al.  Polarimetric segmentation using Wishart test statistic , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[35]  D. M. Smith,et al.  Speckle reduction and segmentation of Synthetic Aperture Radar images , 1996 .

[36]  S. Quegan,et al.  Understanding Synthetic Aperture Radar Images , 1998 .

[37]  A. Lopes,et al.  A statistical and geometrical edge detector for SAR images , 1988 .

[38]  J.-M. Beaulieu,et al.  Utilisation of contour criteria in micro-segmentation of SAR images , 2004 .

[39]  Armand Lopes,et al.  Optimal speckle reduction for the product model in multilook polarimetric SAR imagery and the Wishart distribution , 1997, IEEE Trans. Geosci. Remote. Sens..