Polarimetric SAR Image Segmentation Using Statistical Region Merging

The statistical region merging (SRM) algorithm exhibits efficient performance in solving significant noise corruption and does not depend on the data distribution. These advantages make SRM suitable for the segmentation of synthetic aperture radar (SAR) images, which are characterized by speckle noise and different distributions of various data types and spatial resolutions. However, the original SRM algorithm is designed for RGB and gray images characterized by additive noise and having a range of [0, 255]. In this letter, the SRM algorithm is generalized so that it can be applied to images with larger range and multiplicative noise. The original 4-neighborhood models are also generalized into 8-neighborhood models. The effectiveness of the generalized SRM (GSRM) algorithm is demonstrated by AirSAR and ESAR L-band Polarimetric SAR (PolSAR) data. Given that the input data of the GSRM algorithm can be single- or multi-dimensional, the proposed GSRM algorithm can be used for single- and multi-polarized as well as for fully polarimetric SAR data.

[1]  Frank Nielsen,et al.  Statistical region merging , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Frank Nielsen,et al.  Semi-supervised statistical region refinement for color image segmentation , 2005, Pattern Recognit..

[3]  E. Pottier,et al.  Polarimetric Radar Imaging: From Basics to Applications , 2009 .

[4]  Ridha Touzi,et al.  Segmentation of textured polarimetric SAR scenes by likelihood approximation , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Richard Nock.  Fast and reliable color region merging inspired by decision tree pruning , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[6]  Gabriel Vasile,et al.  Hierarchical segmentation of Polarimetric SAR images using heterogeneous clutter models , 2009, 2009 IEEE International Geoscience and Remote Sensing Symposium.

[7]  Carlos López-Martínez,et al.  An evaluation of PolSAR speckle filters , 2009, 2009 IEEE International Geoscience and Remote Sensing Symposium.

[8]  Carlos López-Martínez,et al.  Filtering and Segmentation of Polarimetric SAR Data Based on Binary Partition Trees , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[9]  H.T. Li,et al.  Object-oriented classification of polarimetric SAR imagery based on Statistical Region Merging and Support Vector Machine , 2008, 2008 International Workshop on Earth Observation and Remote Sensing Applications.

[10]  Deren Li,et al.  HIERARCHICAL CLASSIFICATION OF POLARIMETRIC SAR IMAGE BASED ON STATISTICAL REGION MERGING , 2012 .

[11]  C. McDiarmid.  Concentration , 1862, The Dental register.

[12]  Frank Nielsen,et al.  On region merging: the statistical soundness of fast sorting, with applications , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[13]  Lionel Bombrun,et al.  Segmentation of Polarimetric SAR Data based on the Fisher Distribution for Texture Modeling , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[14]  Rabab Kreidieh Ward,et al.  Segmentation and Classification of Polarimetric SAR Data Using Spectral Graph Partitioning , 2010, IEEE Transactions on Geoscience and Remote Sensing.