A Binary Tree Structured Terrain Classifier for Pol-SAR Images

Guangyi ZHOU  Yi CUI  Yumeng LIU  Jian YANG  

IEICE TRANSACTIONS on Communications   Vol.E94-B   No.5   pp.1515-1518
Publication Date: 2011/05/01
Online ISSN: 1745-1345
DOI: 10.1587/transcom.E94.B.1515
Print ISSN: 0916-8516
Type of Manuscript: LETTER
Category: Sensing
Synthetic Aperture Radar (SAR),  polarimetry,  classification,  texture,  binary tree,  Support Vector Machine (SVM),  

Full Text: PDF(370.8KB)>>
Buy this Article

In this letter, a new terrain type classifier is proposed for polarimetric Synthetic Aperture Radar (Pol-SAR) images. This classifier uses the binary tree structure. The homogenous and inhomogeneous areas are first classified by the support vector machine (SVM) classifier based on the texture features extracted from the span image. Then the homogenous and inhomogeneous areas are, respectively, classified by the traditional Wishart classifier and the SVM classifier based on the texture features. Using a NASA/JPL AIRSAR image, the authors achieve the classification accuracy of up to 98%, demonstrating the effectiveness of the proposed method.