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.
Supervised SOM Based ATR Method with Circular Polarization Basis of Full Polarimetric Data
Shouhei OHNO Shouhei KIDERA Tetsuo KIRIMOTO
IEICE TRANSACTIONS on Communications
Publication Date: 2015/12/01
Online ISSN: 1745-1345
Type of Manuscript: PAPER
synthetic aperture radar (SAR), polarimetric SAR, automatic target recognition (ATR), target area extraction, circular polarization basis,
Full Text: PDF(4.2MB)>>
Satellite-borne or aircraft-borne synthetic aperture radar (SAR) is useful for high resolution imaging analysis for terrain surface monitoring or surveillance, particularly in optically harsh environments. For surveillance application, there are various approaches for automatic target recognition (ATR) of SAR images aiming at monitoring unidentified ships or aircraft. In addition, various types of analyses for full polarimetric data have been developed recently because it can provide significant information to identify structure of targets, such as vegetation, urban, sea surface areas. ATR generally consists of two processes, one is target feature extraction including target area determination, and the other is classification. In this paper, we propose novel methods for these two processes that suit full polarimetric exploitation. As the target area extraction method, we introduce a peak signal-to noise ratio (PSNR) based synthesis with full polarimetric SAR images. As the classification method, the circular polarization basis conversion is adopted to improve the robustness especially to variation of target rotation angles. Experiments on a 1/100 scale model of X-band SAR, demonstrate that our proposed method significantly improves the accuracy of target area extraction and classification, even in noisy or target rotating situations.