引入商空间粒度计算的全极化SAR影像分类

刘利敏; 余洁; 李小娟; 李平湘; 杨杰

doi:10.13203/j.whugis20150324

引入商空间粒度计算的全极化SAR影像分类

刘利敏^1,,
余洁^{2, 1, ,},
李小娟²,
李平湘³,
杨杰³

1.
武汉大学遥感信息工程学院, 湖北武汉, 430079
2.
首都师范大学资源环境与地理信息系统北京市重点实验室, 北京, 100048
3.
武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉, 430079

基金项目:

国家自然科学基金 41130744

国家自然科学基金 41171335

详细信息

作者简介:
刘利敏, 博士, 讲师, 主要从事SAR/INSAR影像处理分析研究。xiaoliulimin@163.com

通讯作者:
余洁, 博士, 教授。yuj2011@whu.edu.cn

中图分类号: TP722
计量
- 文章访问数: 1471
- HTML全文浏览量: 153
- PDF下载量: 341
出版历程
- 收稿日期: 2016-01-19
- 发布日期: 2018-01-04

An Improved Full Polarimetric SAR Image Classification Method Combining with Granularity Computing of Quotient Space Theory

LIU Limin^1,,
YU Jie^{2, 1, ,},
LI Xiaojuan²,
LI Pingxiang³,
YANG Jie³

1.
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
2.
College of Resources Environment and Tourism, Capital Normal University, Beijing 100048, China
3.
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China

Funds:

The National Natural Science Foundation of China 41130744

The National Natural Science Foundation of China 41171335

More Information

Author Bio:
LIU Limin, PhD, lecturer, specializes in SAR and InSAR image processing. E-mail: xiaoliulimin@163.com

Corresponding author:
YU Jie, PhD, professor. E-mail: yuj2011@whu.edu.cn

摘要

摘要: 为了充分利用不同极化特征信息，并将其有效地结合，提出一种结合粒度计算的全极化合成孔径雷达（synthetic aperture radar，SAR）影像分类方法。在不同极化目标分解特征组合的基础上引入影像纹理信息，利用光滑支持向量机（smooth support vector machine，SSVM）对不同特征组合进行类别划分获得粗粒度空间，采用商空间对粗粒度进行合并；根据全极化SAR影像分布特性，以相干矩阵作为新的特征矢量，利用Wishart测度代替传统欧氏距离对差异粒度进行推理，通过合并推理结果与合成论域，获得精细分类结果。采用L波段San Francisco地区和荷兰Flevoland地区的全极化SAR影像进行分类试验，结果表明：利用SSVM算法对全极化SAR影像进行粗粒度划分，并采用Wishart距离对差异粒度推理综合，总体分类效果优于结合纹理信息的Cloude及Yamaguchi4分类结果，且优于基于线性特征融合进行监督分类方法。
- 极化目标分解 /
- 纹理特征 /
- 光滑支持向量机 /
- 商空间粒度 /
- 粒度计算
Abstract: A new Full Polarimetric Synthetic Aperture Radar (SAR) image classification method is proposed that combines quotient space granularity computing and the texture information to carry out comprehensive classification. Firstly, we classify the Cloude and Yamaguchi4 decomposition characteristics with texture features using Smooth Support Vector Machine (SSVM) algorithm, to get two classification results, which are the quotient spaces. According to quotient space theory, the two particle size layer are synthesized and in accordance with SAR data distribution polarization characteristics, we use the Wishart measure instead of the traditional Euclidean distance to infer the granularity difference and calculate its category, and combine the results of this reasoning with the synthetic domain in order to get exact classification results. To validate the proposed method, polarimetric SAR data acquired by AIRSAR for San Francisco and Flevoland were employed in classification experiments. The results indicate that the classification results obtained by the proposed method arenot only better than the combination of texture information of the Cloude and Yamaguchi4 supervised classification results, but superior to all the features as a feature vector based on a simple feature fusion for supervised classification results.
- target decomposition /
- texture information /
- SSVM algorithm /
- quotient space theory /
- granularity computing

HTML全文

图 1 本文方法分类流程图

Figure 1. Flowchart of Proposed Method

下载: 全尺寸图片幻灯片

图 2 美国San Francisco海湾地物不同方法分类结果

Figure 2. Classification Results of San Francisco

下载: 全尺寸图片幻灯片

图 3 Pauli合成图及调绘图

Figure 3. Pauli and Survey Maps

下载: 全尺寸图片幻灯片

图 4 Flevoland分类结果

Figure 4. Claasification Results of Flevoland

下载: 全尺寸图片幻灯片

表 1 4种分类方法分类结果精度对比

Table 1 Classification Accuracy by Different Methods

地物	测试样本数/个	Cloude和纹理特征组合分类		Yamaguchi4和纹理特征组合分类		本文方法分类		线性特征融合分类
地物	测试样本数/个	正确分类数/个	分类精度/%	正确分类数/个	分类精度/%	正确分类数/个	分类精度/%	正确分类数/个	分类精度/%
草地	453	340	75.06	320	70.64	362	79.91	355	78.37
土豆	808	752	93.07	745	92.20	761	94.18	755	93.44
苜蓿	123	56	45.53	41	33.33	77	62.60	72	58.54
大麦	150	105	70.00	69	46.00	114	76.00	108	72.00
裸地	357	293	82.07	284	79.55	296	82.91	295	82.63
甜菜	789	715	90.62	657	83.27	732	92.78	721	91.38
油菜	450	357	79.33	419	93.11	431	95.78	366	81.33
总精度			83.64		80.99		88.59		85.36

下载: 导出CSV

参考文献(15)

[1]	周晓光, 匡纲要, 万建伟.极化SAR图像分类综述[J].信号处理, 2008, 24(5), 806-812 http://d.old.wanfangdata.com.cn/Periodical/xhcl200805023 Zhou Xiaoguang, Kuang Gangyao, Wan Jianwei.A Review of Polarimetric SAR Image Classification[J].Signal Processing, 2008, 5(24), 806-812 http://d.old.wanfangdata.com.cn/Periodical/xhcl200805023
[2]	郎丰铠, 杨杰, 赵伶俐, 等.基于Freeman散射熵和各向异性度的极化SAR影像分类算法研究[J].测绘学报, 2012, 41(4):556-562 http://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201204017.htm Lang Fengkai, Yang Jie, Zhao Lingli, et al. Polarimetric SAR Data Classifation with Freeman Entropy and Anisotropy Analysis[J].Acta Geodaetica et Cartographica Sinica, 2012, 41(4):556-562 http://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201204017.htm
[3]	陈博, 王爽, 焦李成, 等.贝叶斯集成框架下的极化SAR图像分类[J].西安电子科技大学学报(自然科学版), 2015, 42(2):51-58 http://www.wenkuxiazai.com/doc/904651a80b1c59eef9c7b432.html Chen Bo, Wang Shuang, Jiao Licheng, et al. Polarimetric SAR Image Classification Via Naive Bayes Combination[J].Journal of Xidian University, 2015, 42(2):51-58 http://www.wenkuxiazai.com/doc/904651a80b1c59eef9c7b432.html
[4]	刘修国, 姜萍, 陈启浩, 等.利用改进三分量分解与Wishart分类的极化SAR图像建筑物提取方法[J].测绘学报, 2015, 44(2):206-213 doi: 10.11947/j.AGCS.2015.20130535 Liu Xiuguo, Jiang Ping, Chen Qihao, et al.Buildings Extraction from Polarimetric SAR Image Using Improved Three Component Decoposition and WishartClassification[J].Acta Geodaetica et Cartographica Sinica, 2015, 44(2):206-213 doi: 10.11947/j.AGCS.2015.20130535
[5]	付海强, 汪长城, 朱建军, 等.Neumann分解理论在极化SAR植被分类中的应用[J].武汉大学学报·信息科学版, 2015, 40(5):607-611 http://ch.whu.edu.cn/CN/abstract/abstract3253.shtml Fu Haiqiang, Wang Changcheng, Zhu Jianjun, et al. A Polarimetric Classification Method Based on Neumann Decomposition[J]. Geomatics and Information Science of Wuhan University, 2015, 40(5):607-611 http://ch.whu.edu.cn/CN/abstract/abstract3253.shtml
[6]	王云艳, 何楚, 涂峰, 等.特征选择双层SVM的融合算法用于极化SAR图像分类[J].武汉大学学报·信息科学版, 2015, 40(9):1158-1162 http://ch.whu.edu.cn/CN/abstract/abstract3314.shtml Wang Yunyan, He Chu, Tu Feng, et al.PolSAR Image Classification Using Feature Fusion Algorithm Based on Feature Selection and Bilayer SVM[J].Geomatics and Information Science of Wuhan University, 2015, 40(9):1158-1162 http://ch.whu.edu.cn/CN/abstract/abstract3314.shtml
[7]	李刚, 万幼川.商空间理论下面向对象的遥感影像分类[J].光电工程, 2011, 38(2):108-114 http://www.cqvip.com/QK/90982A/201102/36745713.html Li Gang, Wan Youchuan. Object-oriented Classification Method Based on Quotient Space Theory[J].Optoelectronic Engineering, 2011, 2(38):108-114 http://www.cqvip.com/QK/90982A/201102/36745713.html
[8]	张铃, 张钹.模糊商空间理论(模糊粒度计算方法)[J].软件学报, 2003, 14(4):770-775 http://www.wenkuxiazai.com/doc/aa2caaed998fcc22bcd10d10.html Zhang Ling, Zhang Bo. Theory of Fuzzy Quotient Space (Methods of Fuzzy Granular Computing)[J]. Journal of Software, 2003, 14(4):770-775 http://www.wenkuxiazai.com/doc/aa2caaed998fcc22bcd10d10.html
[9]	刘仁金, 黄贤武.图像分割的商空间粒度原理[J].计算机学报, 2005, 28(10):1680-1686 doi: 10.3321/j.issn:0254-4164.2005.10.014 Liu Renjin, Huang Xianwu.The Granular Theorem of Quotient Space in Image Segmentation[J].ChineseJournal of Computers, 2005, 28(10):1680-1686 doi: 10.3321/j.issn:0254-4164.2005.10.014
[10]	张向荣, 谭山, 焦李成.基于商空间粒度计算的SAR图像分类[J].计算学报, 2007, 3(30):483-490 https://www.wenkuxiazai.com/doc/6fb32e34b90d6c85ec3ac6ad.html Zhang Xiangrong, Tan Shan, Jiao Licheng.SAR Image Classification Based on Granularity Computing of Quotient Space Theory[J].Chinese Journal of Computers, 2007, 3(30):483-490 https://www.wenkuxiazai.com/doc/6fb32e34b90d6c85ec3ac6ad.html
[11]	陈杰, 邓敏, 肖鹏峰, 等.结合支持向量机与粒度计算的高分辨率遥感影像面向对象分类[J].测绘学报, 2011, 40(2):135-141 http://www.cqvip.com/QK/90069X/201102/37425529.html Chen Jie, Deng Min, Xiao Pengfeng, et al.Object-Oriented Classification of High Resolution Imagery Combining Support Vector Machine With Granular Computing[J]. Acta Geodaetica et Cartographical Sinica, 2011, 40(2):135-141 http://www.cqvip.com/QK/90069X/201102/37425529.html
[12]	Longshu Li, Yingxia Cui, Sheng Yao.Application of Quotient Space Theory in Input-Output Relationship Based Combinatorial Testing[J].Lecture Notes in Computer Science, 2010:735-742 doi: 10.1007/978-3-642-16248-0_99
[13]	何吟, 程建.基于商空间粒度的极化SAR图像分类[J].计算机应用, 2013, 33(8):2351-2354 http://www.cnki.com.cn/Article/CJFDTotal-JSJY201308066.htm He Yin, Cheng Jian.Classification of Polarimetric SAR Images Based on Quotient Space Granularity Composition Theory[J].Journal of Computer Applications, 2013, 33(8):2351-2354 http://www.cnki.com.cn/Article/CJFDTotal-JSJY201308066.htm
[14]	Lee Y.J, Mangasarian O.L.SSVM:A Smooth Support Vector Machine for Classification[J].Computation Optimization and Applications, 2001, 22(1):5-21 https://www.researchgate.net/publication/226514122_SSVM_A_Smooth_Support_Vector_Machine_for_Classification
[15]	Zadeh L A.Fuzzy Logic Computing with Words[J].IEEE Transactions on Fuzzy Systems, 1996, 4(1):103~111 https://www.researchgate.net/publication/290616211_Fuzzy_Logic_Computing_with_Words

施引文献(27)

期刊类型引用(10)

1.	曾广泉，马韬，张孟希，戴妍，陈凯文，丁继辉，俞双恩，王中文. 基于无人机多光谱影像的不同施氮量水稻LAI反演方法研究. 江苏农业科学. 2024(20): 41-48 . 百度学术
2.	高钰琪，许桂玲，冯跃华，王晓珂，任红军，由晓璇，韩志丽，李家乐. 基于冠层高光谱植被指数的水稻产量预测模型研究. 中国稻米. 2023(05): 38-44 . 百度学术
3.	彭晓伟，张爱军，王楠，赵丽，杨晓楠. 高光谱技术在土壤及适种作物的研究进展. 遥感信息. 2022(01): 32-39 . 百度学术
4.	王晓珂，刘婷婷，许桂玲，冯跃华，彭金凤，李杰，罗强鑫，韩志丽，卢苇，PHONENASAY Somsana. 基于冠层高光谱遥感的杂交水稻植被指数氮素营养诊断模型. 中国稻米. 2021(03): 21-29 . 百度学术
5.	王浩淼，宋苗语，李翔，扈朝阳，鲁任翔，王翔，马会勤. 无人机高光谱遥感监测葡萄长势与缺株定位. 园艺学报. 2021(08): 1626-1634 . 百度学术
6.	刘雅婷，龚龑，段博，方圣辉，彭漪. 多时相NDVI与丰度综合分析的油菜无人机遥感长势监测. 武汉大学学报(信息科学版). 2020(02): 265-272 . 百度学术
7.	陈晓凯，李粉玲，王玉娜，史博太，侯玉昊，常庆瑞. 无人机高光谱遥感估算冬小麦叶面积指数. 农业工程学报. 2020(22): 40-49 . 百度学术
8.	落莉莉，常庆瑞，武旭梅，杨景，李粉玲，王琦. 夏玉米叶片光合色素含量高光谱估算. 干旱地区农业研究. 2019(04): 178-183 . 百度学术
9.	张良培，刘蓉，杜博. 使用量子优化算法进行高光谱遥感影像处理综述. 武汉大学学报(信息科学版). 2018(12): 1811-1818 . 百度学术
10.	李亚妮，鲁蕾，刘勇. 基于PROSAIL模型的水稻田缨帽三角-叶面积指数模型及其应用. 应用生态学报. 2017(12): 3976-3984 . 百度学术