摘要
A novel method is proposed for the supervised classification of multifrequency polarimetric synthetic aperture radar (PoISAR) images. The coherency matrices in P-, L-, and C-bands are mapped onto a 9 x 9 matrix Omega based on the eigenvalue decomposition of the coherency matrix of each band. A boxcar filter is then performed on the matrix Omega. The filtered data are put into a complex Wishart classifier. Finally, the effectiveness of the proposed method is demonstrated with JPL/AIRSAR multifrequency PoISAR data acquired over the Flevoland area.
- 出版日期2015-12
- 单位清华大学; 北京无线电计量测试研究所