Title :
Unsupervised classification and analysis of natural scenes from polarimetric interferometric SAR data
Author :
Ferro-Famil, L. ; Pottier, E. ; Lee, J.S.
Author_Institution :
A. R. T. Lab., Univ. of Rennes, France
Abstract :
In this paper is introduced a classification approach for polarimetric interferometric SAR data sets, based on the analysis of an interferometric (6×6) polarimetric coherency matrix properties. From the Wishart probability density function of this polarimetric representation, is defined a maximum likelihood decision rule to perform an iterative adaptive classification. Another classification scheme based on the derivation of the conditional probability of the cross-correlation between both data sets is presented
Keywords :
adaptive signal processing; geophysical signal processing; geophysical techniques; image classification; radar imaging; radar polarimetry; remote sensing by radar; synthetic aperture radar; terrain mapping; InSAR; Wishart probability density function; geophysical measurement technique; image classification; interferometric polarimetric coherency matrix; iterative adaptive classification; land surface; maximum likelihood decision rule; natural scene; polarimetric interferometric SAR; polarimetric representation; radar imaging; radar remote sensing; synthetic aperture radar; terrain mapping; unsupervised classification; Anisotropic magnetoresistance; Eigenvalues and eigenfunctions; Entropy; Image analysis; Layout; Matrix decomposition; Polarization; Radar scattering; Remote sensing; Scattering parameters;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-7031-7
DOI :
10.1109/IGARSS.2001.978139
