A test statistic for high resolution polarimetric SAR data classification

Author

Formont, Pierre ; Ovarlez, Jean-Philippe ; Pascal, Frédéric ; Vasile, Gabriel ; Ferro-Famil, Laurent

Author_Institution

French Aerosp. Lab., ONERA, Palaiseau, France

fYear

2010

fDate

25-30 July 2010

Firstpage

1871

Lastpage

1874

Abstract

Modern SAR systems have high resolution which leads the backscattering clutter to be non-Gaussian. In order to properly classify images from these systems, a non-Gaussian noise model is considered: the SIRV model. A statistical test of equality of covariance matrices is used to classify pixels, taking into account the critical region of the test which rejects the likeliness of a covariance matrix to any of the class centers. This test is applied on experimental data obtained with the ONERA RAMSES system in X-band. The results show a good separation between natural and man-made areas of the image.

Keywords

Gaussian noise; covariance matrices; image classification; image resolution; radar clutter; radar imaging; radar polarimetry; radar resolution; statistical testing; synthetic aperture radar; ONERA RAMSES system; SIRV model; X-band; backscattering clutter; covariance matrices equality; high resolution polarimetric SAR data classification; nonGaussian noise model; test statistic; Approximation methods; Classification algorithms; Covariance matrix; Facsimile; Maximum likelihood estimation; Noise; Pixel; Image classification; polarimetry; statistics; synthetic aperture radar;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2010 IEEE International

Conference_Location

Honolulu, HI

ISSN

2153-6996

Print_ISBN

978-1-4244-9565-8

Electronic_ISBN

2153-6996

Type

conf

DOI

10.1109/IGARSS.2010.5651074

Filename

5651074