DocumentCode :
814178
Title :
Unsupervised segmentation of polarimetric SAR data using the covariance matrix
Author :
Rignot, Eric ; Chellappa, Rama ; Dubois, Pascale
Author_Institution :
Jet Propulsion Lab., California Inst. of Technol., Pasadena, CA, USA
Volume :
30
Issue :
4
fYear :
1992
fDate :
7/1/1992 12:00:00 AM
Firstpage :
697
Lastpage :
705
Abstract :
A method for unsupervised segmentation of polarimetric synthetic aperture radar (SAR) data into classes of homogeneous microwave polarimetric backscatter characteristics is presented. Classes of polarimetric backscatter are selected on the basis of a multidimensional fuzzy clustering of the logarithm of the parameters composing the polarimetric covariance matrix. The clustering procedure uses both polarimetric amplitude and phase information, is adapted to the presence of image speckle, and does not require an arbitrary weighting of the different polarimetric channels; it also provides a partitioning of each data sample used for clustering into multiple clusters. Given the classes of polarimetric backscatter, the entire image is classified using a maximum a posteriori polarimetric classifier. Four-look polarimetric SAR complex data of lava flows and of sea ice acquired by the NASA/JPL airborne polarimetric radar (AIRSAR) are segmented using this technique
Keywords :
geophysical techniques; image segmentation; microwave imaging; polarimetry; remote sensing by radar; speckle; synthetic aperture radar; SAR; a posteriori polarimetric classifier; amplitude; covariance matrix; geophysics; homogeneous microwave polarimetric backscatter characteristics; image speckle; land surface imaging; measurement; method; multidimensional fuzzy clustering; ocean; phase information; remote sensing; sea ice; synthetic aperture radar; technique; unsupervised segmentation; Airborne radar; Backscatter; Covariance matrix; Microwave theory and techniques; Multidimensional systems; NASA; Polarimetric synthetic aperture radar; Sea ice; Speckle; Synthetic aperture radar;
fLanguage :
English
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
Publisher :
ieee
ISSN :
0196-2892
Type :
jour
DOI :
10.1109/36.158863
Filename :
158863
Link To Document :
بازگشت