Improving the Accuracy of Land Cover Classification Using Fusion of Polarimetric SAR and Hyperspectral Images

被引：10

作者：

Shokrollahi, Mahin ^{[1
]}

Ebadi, Hamid ^{[1
]}

机构：

[1] KN Toosi Univ Technol, Geomat Engn Fac, Photogrammetry & Remote Sensing Dept, Tehran, Iran

来源：

JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING | 2016年 / 44卷 / 06期

关键词：

Feature-level fusion; Decision-level fusion; PolSAR data; Hyperspectral images; Classification; SUPPORT VECTOR MACHINES; FEATURE-SELECTION; MULTISOURCE;

D O I：

10.1007/s12524-016-0559-4

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

In this study, various fusion methods based on feature-level and decision-level fusion of Polarimetric SAR (PolSAR) and hyperspectral images are investigated for the classification. In feature fusion, parallel feature combination method is used for classification. In decision fusion, first the individual data sources are classified separately and then several decision fusion methods are applied to fuse the classified images from each data. The results show that feature fusion has a better performance than the various decision fusion methods. The overall accuracy of feature fusion was 98.92 % which has illustrated improvement of 8 % compared to the obtained using hyperspectral data and 10 % compared to the acquired using PolSAR data.

引用

页码：1017 / 1024

页数：8

共 27 条

[1]

Al-Wassai F. A., 2011, INT J LATEST TECHNOL, VI, P124

[2]

[Anonymous], 2004, INFORM FUSION, DOI DOI 10.1016/J.INFFUS.2003.10.005

[3] HYPERSPECTRAL IMAGE CLASSIFICATION BASED ON ITERATIVE SUPPORT VECTOR MACHINE BY INTEGRATING SPATIAL-SPECTRAL INFORMATION [J].

Belkacem, Baassou ;

He, Mingyi ;

Imran, Farid Muhammad ;

Mei, Shaohui .

2013 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2013, :1023-1026

[4] Classification of multisource and hyperspectral data based on decision fusion [J].

Benediktsson, JA ;

Kanellopoulos, I .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1999, 37 (03) :1367-1377

[5]

Borghys D., 2007, 5 EARSEL SIG IS WORK

[6] Hyperspectral and SAR imagery data fusion with positive Boolean function [J].

Chang, YL ;

Chen, CT ;

Han, CC ;

Fan, KC ;

Chen, KS ;

Chang, JH .

ALGORITHMS AND TECHNOLOGIES FOR MULTISPECTRAL, HYPERSPECTRAL AND ULTRASPECTRAL IMAGERY IX, 2003, 5093 :765-776

[7] A review of target decomposition theorems in radar polarimetry [J].

Cloude, SR ;

Pottier, E .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1996, 34 (02) :498-518

[8] LAND COVER CLASSIFICATION BY SUPPORT VECTOR MACHINES USING MULTI-TEMPORAL POLARIMETRIC SAR DATA [J].

Feng, Qi ;

Chen, Er-xue ;

Li, Zengyuan ;

Guo, Ying ;

Zhou, Wei ;

Li, Weimei ;

Xu, Guangcai .

2012 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2012, :6244-6246

[9] Feature selection for support vector machines by means of genetic algorithms [J].

Fröhlich, H ;

Chapelle, O ;

Schölkopf, B .

15TH IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2003, :142-148

[10]

Fukuda S, 2001, INT GEOSCI REMOTE SE, P187, DOI 10.1109/IGARSS.2001.976097

← 1 2 3 →