Quantitative comparison of classification capability: fully-polarimetric versus partially polarimetric SAR

Author

Lee, J.S. ; Grunes, M.R. ; Ainsworth, T.L. ; Pottier, E. ; Krogager, E. ; Boerner, W.M.

Author_Institution

Remote Sensing Div., Naval Res. Lab., Washington, DC, USA

Volume

3

fYear

2000

fDate

2000

Firstpage

1101

Abstract

This paper addresses the land-use classification capabilities of partially polarimetric SAR versus fully polarimetric SAR. A variety of polarization combinations are investigated for application to crop and tree age classification. Based on the circular Gaussian distribution, maximum likelihood classifiers for all polarization combinations were used to assess quantitative classification accuracy. Thus, it allows optimally selecting the combination of polarizations for crop, tree and terrain classification

Keywords

agriculture; geophysical signal processing; geophysical techniques; radar imaging; radar polarimetry; remote sensing by radar; synthetic aperture radar; terrain mapping; vegetation mapping; SAR; agriculture; circular Gaussian distribution; classification; crop; discrimination; full polarimetry; geophysical measurement technique; image classification; land surface; land use; maximum likelihood classifier; partial polarimetry; polarization combination; quantitative classification accuracy; radar imaging; radar polarimetry; radar remote sensing; synthetic aperture radar; terrain mapping; tree age; vegetation mapping; Classification tree analysis; Covariance matrix; Crops; Electronic mail; Laboratories; Maximum likelihood estimation; Polarization; Remote sensing; Scattering; Speckle;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2000. Proceedings. IGARSS 2000. IEEE 2000 International

Conference_Location

Honolulu, HI

Print_ISBN

0-7803-6359-0

Type

conf

DOI

10.1109/IGARSS.2000.858035

Filename

858035