利用多特征融合和集成学习的极化SAR图像分类

孙勋; 黄平平; 涂尚坦; 杨祥立

doi:10.12000/JR15132

利用多特征融合和集成学习的极化SAR图像分类

DOI: 10.12000/JR15132

1.
(武汉大学电子信息学院武汉 430072)
2.
(内蒙古工业大学雷达技术研究所呼和浩特 010051)
3.
(上海卫星工程研究所上海 200240)

基金项目:

内蒙古自治区科技计划项目（20131108，20140155），国家自然科学基金（61271401，41501414），复旦大学电磁波信息科学教育部重点实验室开放基金项目（EMW201504）

详细信息

作者简介:
孙勋(1992-),男,2014年获得武汉科技大学工学学士学位,现于武汉大学电子信息学院信号处理实验室攻读硕士学位。主要研究方向为极化合成孔径雷达图像解译。E-mail:sxun@whu.edu.cn;涂尚坦(1985-),男,2012年获武汉大学工学博士学位,现任上海卫星工程研究所微波载荷主管设计师。主要研究方向为SAR系统总体设计、极化SAR图像处理与解译、机器视觉与数据挖掘。E-mail:tsttu@126.com黄平平(1978-),男,2010年获中国科学院电子学研究所博士学位,现任内蒙古自治区雷达技术与应用重点实验室主任,内蒙古工业大学雷达技术研究所所长,副教授。主要研究方向为合成孔径雷达信号处理和微波遥感应用。E-mail:cimhwangpp@163.com;杨祥立(1991-),男,2014年获得中南民族大学工学学士学位,现于武汉大学电子信息学院信号处理实验室攻读硕士学位。主要研究方向为极化合成孔径雷达图像变化检测。E-mail:xiangliyang@whu.edu.cn

通讯作者:
黄平平cimhwangpp@163.com

计量
- 文章访问数: 3541
- HTML全文浏览量: 581
- PDF下载量: 1540
- 被引次数: 0
出版历程
- 收稿日期: 2015-12-27
- 修回日期: 2016-04-07
- 网络出版日期: 2016-12-28

Polarimetric SAR Image Classification Using Multiple-feature Fusion and Ensemble Learning

1.
(School of Electronic Information, Wuhan University, Wuhan 430072, China)
2.
(Radar Research Institute, Inner Mongolia University of Technology, Hohhot 010051, China)
3.
(Shanghai Institute of Satellite Engineering, Shanghai 200240, China)

Funds:

The Inner Mongolia Autonomous Region Science and Technology Project (20131108,20140155),TheNational Natural Science Foundation of China (61271401,41501414),The Fudan University Key Laboratory of EMWInformation Open Fund Project (EMW201504)

摘要

摘要: 该文提出了一种利用多特征融合和集成学习的极化SAR图像监督分类算法。该算法首先提取极化SAR图像的多重特征，包括EPFS特征，Hoekman分解特征，Huynen分解特征，H/alpha/A分解特征以及扩展四分量分解特征。为保证集成学习中基本分类器的差异性与准确性，算法从5组特征集中每次随机选取两组不同的特征进行串联融合，作为SVM分类器的输入。最后，利用随机森林学习算法将所有基本分类器的预测概率集成输出最终分类结果。像素级和区域级的分类实验表明了该文算法的有效性。
- 极化合成孔径雷达 /
- 集成学习 /
- 监督分类
Abstract: In this paper, we propose a supervised classification algorithm for Polarimetric Synthetic Aperture Radar (PolSAR) images using multiple-feature fusion and ensemble learning.First, we extract different polarimetric features, including extended polarimetric feature space, Hoekman, Huynen, H/alpha/A, and fourcomponent scattering features of PolSAR images.Next, we randomly select two types of features each time from all feature sets to guarantee the reliability and diversity of later ensembles and use a support vector machine as the basic classifier for predicting classification results.Finally, we concatenate all prediction probabilities of basic classifiers as the final feature representation and employ the random forest method to obtain final classification results.Experimental results at the pixel and region levels show the effectiveness of the proposed algorithm.
- Polarimetric Synthetic Aperture Radar(PolSAR) /
- Ensemble learning /
- Supervised classification

HTML全文

参考文献(21)

[1]	李春升,杨威,王鹏波.星载SAR成像处理算法综述[J].雷达学报,2013,2(1):111-122.Li Chun-sheng,Yang Wei,and Wang Peng-bo.A review of spaceborne SAR algorithm for image formation[J].Journal of Radars,2013,2(1):111-122.
[2]	田维,徐旭,卞小林,等.环境一号C卫星SAR图像典型环境遥感应用初探[J].雷达学报,2014,3(3):339-351.Tian Wei,Xu Xu,Bian Xiao-lin,et al..Applications of environmental remote sensing by HJ-1C SAR imagery[J].Journal of Radars,2014,3(3):339-351.
[3]	Yang Wen,Yin Xiao-shuang,Song Hui,et al..Extraction of built-up areas from fully polarimetric SAR imagery via PU learning[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(4):1207-1216.
[4]	Banerjee B,Bhattacharya A,and Buddhiraju K M.A generic land-cover classification framework for polarimetric SAR images using the optimum Touzi decomposition parameter subset-An insight on mutual information-based feature selection techniques[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(4):1167-1176.
[5]	Hariharan S,Tirodkar S,De S,et al..Variable importance and random forest classification using RADARSAT-2 PolSAR data[C].IEEE International Geoscience and Remote Sensing Symposium (IGARSS),Quebec,2014:1210-1213.
[6]	滑文强,王爽,侯彪.基于半监督学习的SVM-Wishart极化SAR图像分类方法[J].雷达学报,2015,4(1):93-98.Hua Wen-qiang,Wang Shuang,and Hou Biao.Semi-supervised Learning for classification of polarimetric SAR images based on SVM-Wishart[J].Journal of Radars,2015,4(1):93-98.
[7]	Yang Wen,Yin Xiao-shuang,and Xia Gui-song.Learning high-level features for satellite image classification with limited training samples[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(8):4472-4482.
[8]	Yuan Han-ning,Fang Meng,and Zhu Xing-quan.Hierarchical sampling for multi-instance ensemble learning[J].Knowledge and Data Engineering,2013,25(12):2900-2905.
[9]	Zhang La-mei,Wang Xiao,Li Meng,et al..Classification of fully polarimetric SAR images based on ensemble learning and feature integration[C].IEEE International Geoscience and Remote Sensing Symposium (IGARSS),Quebec,2014:2758-2761.
[10]	刘培,杜培军,谭琨.一种基于集成学习和特征融合的遥感影像分类新方法[J].红外与毫米波学报,2014,33(3):311-317.Liu Pei,Du Pei-jun,and Tan Kun.A novel remotely sensed image classification based on ensemble learning and feature integration[J].Journal of Infrared and Millimeter Waves,2014,33(3):311-317.
[11]	Samat A,Du P,Baig M H A,et al..Ensemble learning with multiple classifiers and polarimetric features for polarized SAR image classification[J].Photogrammetric EngineeringRemote Sensing,2014,80(3):239-251.
[12]	Wang Y,Zhang Y,Zhuo T,et al..Ensemble learning based on multi-features fusion and selection for polarimetric SAR image classification[C].International Conference on Signal Processing (ICSP),Hangzhou,2014:734-737.
[13]	Doulgeris A P.A simple and extendable segmentation method for multi-polarisation SAR images[C].6th International Workshop on Science and Applications of SAR Polarimetry and Polarimetric Interferometry,2013.
[14]	Yang J,Peng Y N,Yamaguchi Y,et al..On Huynen's decomposition of a Kennaugh matrix[J].IEEE Geoscience and Remote Sensing Letters,2006,3(3):369-372.
[15]	Hoekman D H and Vissers M A M.A new polarimetric classification approach evaluated for agricultural crops[J].IEEE Transactions on Geoscience and Remote Sensing,2003,41(12):2881-2889.
[16]	Cloude S R and Pottier E.An entropy based classification scheme for land applications of polarimetric SAR[J].IEEE Transactions on Geoscience and Remote Sensing,1997,35(1):68-78.
[17]	Yamaguchi Y,Sato A,Boerner W,et al..Four-component scattering power decomposition with rotation of coherency matrix[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(6):2251-2258.
[18]	Sato A,Yamaguchi Y,Singh G,et al..Four-component scattering power decomposition with extended volume scattering model[J].IEEE Geoscience and Remote Sensing Letters,2012,9(2):166-170.
[19]	Zhang Cha and Ma Yun-qian.Ensemble Machine Learning[M].Springer US,2012:1-34.
[20]	陈博,王爽,焦李成,等.利用0-1矩阵分解集成的极化SAR图像分类[J].电子与信息学报,2015,37(6):1495-1501.Chen Bo,Wang Shuang,Jiao Li-cheng,et al..Polarimetric SAR image classification via weighted ensemble based on 0-1 matrix decomposition[J].Journal of ElectronicsInformation Technology,2015,37(6):1495-1501.
[21]	Chang Chih-Chung and Lin Chih-Jen.Libsvm:A library for support vector machines[J].ACM Transactions on Intelligent Systems and Technology,2011,2(3):27.