Hierarchical Segmentation of Polarimetric SAR Images Using Heterogeneous Clutter Models

Author

Bombrun, Lionel ; Vasile, Gabriel ; Gay, Michel ; Totir, Felix

Author_Institution

Grenoble Image sPeech Signal Automatics Lab. (GIPSA-Lab.), Grenoble Inst. of Technol., Grenoble, France

Volume

49

Issue

2

fYear

2011

Firstpage

726

Lastpage

737

Abstract

In this paper, heterogeneous clutter models are used to describe polarimetric synthetic aperture radar (PolSAR) data. The KummerU distribution is introduced to model the PolSAR clutter. Then, a detailed analysis is carried out to evaluate the potential of this new multivariate distribution. It is implemented in a hierarchical maximum likelihood segmentation algorithm. The segmentation results are shown on both synthetic and high-resolution PolSAR data at the X- and L-bands. Finally, some methods are examined to determine automatically the “optimal” number of segments in the final partition.

Keywords

geophysical image processing; geophysical techniques; image segmentation; maximum likelihood estimation; radar clutter; radar polarimetry; synthetic aperture radar; Fisher probability density function; KummerU distribution; L-band; PolSAR clutter; X-band; heterogeneous clutter models; hierarchical maximum likelihood segmentation algorithm; multivariate distribution; polarimetric SAR images; polarimetric synthetic aperture radar data; spherically invariant random vectors; synthetic high-resolution PolSAR data; Fisher probability density function (PDF); KummerU PDF; polarimetric synthetic aperture radar (PolSAR) data; segmentation; spherically invariant random vectors (SIRV);

fLanguage

English

Journal_Title

Geoscience and Remote Sensing, IEEE Transactions on

Publisher

ieee

ISSN

0196-2892

Type

jour

DOI

10.1109/TGRS.2010.2060730

Filename

5570982