DocumentCode :
3064887
Title :
Nonlinear PCA based polarimetric decomposition
Author :
Avezzano, R.G. ; Licciardi, G. ; Del Frate, Fabio ; Schiavon, Giovanni ; Chanussot, Jocelyn
Author_Institution :
DICII, Tor Vergata Univ. of Rome, Rome, Italy
fYear :
2013
fDate :
21-26 July 2013
Firstpage :
3006
Lastpage :
3009
Abstract :
The operational level reached by polarimetric data processing techniques has been demonstrated during the last decade. The next generation of spaceborne Synthetic Aperture Radar satellites will implement full- or dual- polarimetric capabilities. In few years a huge amount of data will have to be processed in a fast and reliable way, implementing polarimetric decompositions or accurate classifications. Two neural network approaches for fast and accurate processing of polarimetric data are presented. In the first approach a neural network based processing chain for fast model based polarimetric decomposition is developed, while in the second approach a Non-Linear Principal Component Analisys of polarimetric data has been performed using an Auto Associative Neural Network. The results show a considerable reduction of computational effort and a substantial data compression with a minimun loss of information.
Keywords :
data analysis; geophysics computing; neural nets; principal component analysis; radar polarimetry; remote sensing by radar; synthetic aperture radar; autoassociative neural network; dual polarimetric capabilities; fast model based polarimetric decomposition; full polarimetric capabilities; neural network approach; neural network based processing chain; nonlinear PCA; polarimetric data processing techniques; principal component analisys; spaceborne SAR satellites; synthetic aperture radar; Accuracy; Covariance matrices; Neural networks; Principal component analysis; Scattering; Training; Vectors; NLPCA; Neural Networks; POLSAR; Target Decomposition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2013 IEEE International
Conference_Location :
Melbourne, VIC
ISSN :
2153-6996
Print_ISBN :
978-1-4799-1114-1
Type :
conf
DOI :
10.1109/IGARSS.2013.6723458
Filename :
6723458
Link To Document :
بازگشت