For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Unsupervised Polarimetric SAR Image Classification
Junyi XU Jian YANG Yingning PENG Chao WANG
IEICE TRANSACTIONS on Communications
Publication Date: 2004/04/01
Print ISSN: 0916-8516
Type of Manuscript: LETTER
polarimetry, radar remote sensing, terrain classification, cross-entropy,
Full Text: PDF(698.9KB)>>
In this letter, the concept of cross-entropy is introduced for unsupervised polarimetric synthetic aperture radar (SAR) image classification. The difference between two scatterers is decomposed into three parts, i.e., the difference of average scattering characteristic, the difference of scattering randomness and the difference of scattering matrix span. All these three parts are expressed in cross-entropy formats. The minimum cross-entropy principle is adopted to make classification decision. It works well in unsupervised terrain classification with a NASA/JPL AIRSAR image.