A Binary Tree Structured Terrain Classifier for Pol-SAR Images

Guangyi ZHOU; Yi CUI; Yumeng LIU; Jian YANG

doi:10.1587/transcom.E94.B.1515

A Binary Tree Structured Terrain Classifier for Pol-SAR Images

Guangyi ZHOU, Yi CUI, Yumeng LIU, Jian YANG

Full Text Views

0

Share
Cite this

Summary :

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.

Publication: IEICE TRANSACTIONS on Communications Vol.E94-B No.5 pp.1515-1518

Publication Date: 2011/05/01

Publicized

Online ISSN: 1745-1345

DOI: 10.1587/transcom.E94.B.1515

Type of Manuscript: LETTER

Category: Sensing

Cite this

Copy

Guangyi ZHOU, Yi CUI, Yumeng LIU, Jian YANG, "A Binary Tree Structured Terrain Classifier for Pol-SAR Images" in IEICE TRANSACTIONS on Communications, vol. E94-B, no. 5, pp. 1515-1518, May 2011, doi: 10.1587/transcom.E94.B.1515.
Abstract: 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.
URL: https://globals.ieice.org/en_transactions/communications/10.1587/transcom.E94.B.1515/_p

Copy

@ARTICLE{e94-b_5_1515,
author={Guangyi ZHOU, Yi CUI, Yumeng LIU, Jian YANG, },
journal={IEICE TRANSACTIONS on Communications},
title={A Binary Tree Structured Terrain Classifier for Pol-SAR Images},
year={2011},
volume={E94-B},
number={5},
pages={1515-1518},
abstract={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.},
keywords={},
doi={10.1587/transcom.E94.B.1515},
ISSN={1745-1345},
month={May},}

Copy

TY - JOUR
TI - A Binary Tree Structured Terrain Classifier for Pol-SAR Images
T2 - IEICE TRANSACTIONS on Communications
SP - 1515
EP - 1518
AU - Guangyi ZHOU
AU - Yi CUI
AU - Yumeng LIU
AU - Jian YANG
PY - 2011
DO - 10.1587/transcom.E94.B.1515
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E94-B
IS - 5
JA - IEICE TRANSACTIONS on Communications
Y1 - May 2011
AB - 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.
ER -