Title :
An entropy based classification scheme for polarimetric SAR data
Author_Institution :
IRESTE, Nantes Univ., France
Abstract :
Considers a new unsupervised classification scheme for polarimetric SAR data. This scheme makes use of a local estimate of the scattering entropy in the scene to determine the number of discernible classes in the data. Examples are presented of application of the scheme to AIRSAR data provided by NASA/JPL
Keywords :
electromagnetic wave scattering; entropy; geophysical signal processing; image classification; polarimetry; radar cross-sections; radar imaging; radar polarimetry; remote sensing by radar; synthetic aperture radar; unsupervised learning; AIRSAR data; discernible classes; entropy based classification scheme; polarimetric SAR data; scattering entropy; scene; unsupervised classification scheme; Additive noise; Eigenvalues and eigenfunctions; Entropy; Equations; Image analysis; Layout; Radar imaging; Radar scattering; Scattering parameters; USA Councils;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 1995. IGARSS '95. 'Quantitative Remote Sensing for Science and Applications', International
Conference_Location :
Firenze
Print_ISBN :
0-7803-2567-2
DOI :
10.1109/IGARSS.1995.524090
