Please wait a minute...
img

官方微信

遥感技术与应用  2016, Vol. 31 Issue (1): 177-185    DOI: 10.11873/j.issn.1004-0323.2016.1.0177
数据与图像处理     
高光谱影像的BDT-SVM地物分类算法与应用
林志垒,晏路明
(福建师范大学地理科学学院,福建 福州350007)
The Object Classification Algorithm and Application for Hyperspectral Imagery based on BDT-SVM
Lin Zhilei,Yan Luming
(College of Geographical Sciences,Fujian Normal University,Fuzhou 350007,China)
 全文: PDF(3440 KB)  
摘要:

面对海量数据的特征空间高维性及训练样本的有限性,高光谱遥感影像若采用常规统计模式的分类方法难以获得较好的分类结果。因此探讨支持向量机(SVM)分类器的基本原理,针对EO-1 Hyperion高光谱影像的分类特点及现有多类SVM算法所存在的训练时间长及分类精度低等问题,引入二叉决策树SVM(BDT-SVM)分类算法,并提出一种新的类间分离度定义方法及相应的客观确定二叉树结构的策略,由此生成改进的BDT\|SVM算法。实验结果表明:与其他多类分类方法相比,基于改进的BDT-SVM算法的高光谱影像地物分类效果更好,总体精度达到90.96%,Kappa系数为0.89,该算法还解决了经典SVM多类分类可能存在的不可分区域问题。

关键词: 高光谱影像支持向量机(SVM)二叉决策树(BDT)分类算法    
Abstract:

Hyperspectral remote sensing is a cutting edge field in remote sensing.It offers the fine detection of objects by its spectral response characteristics in various spectral bands,and has superiority to multispectral remote sensing in fine extraction.However,due to high\|dimensional feature space and limited training samples of the huge data of hyperspectral images,it is difficult for conventional statistical pattern identification methods to classify hyperspectral images.Thus this paper explores the basic principle of support vector machine classifier and employs Binary Decision Tree Support Vector Machine (BDT\|SVM) classification algorithm based on EO\|1 Hyperion hyperspectral imagery.And this study proposes a new definition of the class separation against the long training time and low classification efficiency of existing multi\|class SVM algorithm and generates a modified BDT\|SVM algorithm.On the basis of theoretical analysis,this paper completes the object classification experiments on Hyperion hyperspectral imagery of the test area and verifies the high classification accuracy of the method.Experimental results show that the effect of hyperspectral image classification based on the modified BDT\|SVM algorithm is apparently better than other multi\|class classification methods,which total classification accuracy is up to 90.96% and kappa coefficient is 0.89.The algorithm also solves the problem of non\|separable region,which may be present in the classic SVM multi\|class classification methods.

Key words: Hyperspectral imagery    Support Vector Machine(SVM)    Binary Decision Tree(BDT)    Classification algorithm
收稿日期: 2014-11-30 出版日期: 2016-04-05
:  TP 751.1  
基金资助:

欧盟第七框架项目(IGIT:247608)和福建省自然科学基金项目(2011J01265)共同资助。

作者简介: 林志垒(1976-),女,福建长乐人,博士,副教授,主要从事高光谱遥感原理与应用研究。Email:zllin99@163.com。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
林志垒
晏路明

引用本文:

林志垒,晏路明. 高光谱影像的BDT-SVM地物分类算法与应用[J]. 遥感技术与应用, 2016, 31(1): 177-185.

Lin Zhilei,Yan Luming. The Object Classification Algorithm and Application for Hyperspectral Imagery based on BDT-SVM. Remote Sensing Technology and Application, 2016, 31(1): 177-185.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2016.1.0177        http://www.rsta.ac.cn/CN/Y2016/V31/I1/177

[1]Pignatti S,Cavalli R M,Cuomo V,et al.Evaluating Hyperion Capability for Land Cover Mapping in a Fragmented Ecosystem:Pollino National Park,Italy[J].Remote Sensing of Environment,2009,113(3):622-634.

[2]Chi M M,Feng R,Bruzzone L.Classification of Hyper-spectral Remote Sensing Data with Primal SVM for Small-sized Training Dataset Problem[J].Advances in Space Research,2008,41(11):1793-1799.

[3]Mountrakis G,Im J,Ogole C.Support Vector Machines in Remote Sensing:A Review[J].ISPRS Journal of Photogrammetry and Remote Sensing,2011,66(3):247- 259.

[4]Zhou L G,Lai K K,Yu L.Least Squares Support Vector Machines Ensemble Models for Ccredit Scoring[J].Expert System with Application,2010,37(1):127-133.

[5]Sengur A.Multiclass Least-squares Support Vector Machines for Analog Modulation Classification[J].Expert Systems with Applications,2009,36(3):6681-6685.

[6]Melgani F,Bruzzone L.Classification of Hyperspectral Remote Sensing Images with Support Vector Machines[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(8):1778-1790.

[7]Camps-Valls G,Gomez-Chova L,Galpe-Maravilla J,et al.Robust Support Vector Method for Hyperspectral Data Classification and Knowledge Discovery[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(7):1530-1542.

[8]Dalponte M,Bruzzone L,Gianelle D.Fusion of Hyperspectral and LIDAR Remote Sensing Data for Classification of Complex Forest Areas[J].IEEE Transactions on Geoscience and Remote Sensing,2008,46(5):1416-1427.

[9]Hu Gensheng,Chen Changchun,Liang Dong.Cloud Detection for Landsat Images by Combination of ACCA with WSVM[J].Acta Geodaetica et Cartographica Sinica,2014,43(8):848-854.[胡根生,陈长春,梁栋.联合云量自动评估和加权支持向量机的Landsat影像云检测[J].测绘学报,2014,43(8):848-854.]

[10]He Lingmin,Shen Zhangquan,Kong Fansheng,et al.Study on Multi-source Remote Sensing Classification with SVM[J].Journal of Image and Graphics,2007,12(4):648-654.[何灵敏,沈掌泉,孔繁胜,等.SVM在多源遥感影像分类中的应用研究[J].中国图象图形学报,2007,12(4):648-654.]

[11]Feng Xiao,Xiao Pengfeng,Li Qi,et al.Hyperspectral Image Classification based on 3-D Gabor Filter and Support Vector Machines[J].Spectrocopy and Spectral Analysis,2014,34(8):2218-2224.[冯逍,肖鹏峰,李琦,等.三维Gabor滤波器与支持向量机的高光谱遥感图像分类[J].光谱学与光谱分析,2014,34(8):2218-2224.]

[12]Li Xiaorun,Zhu Jieer,Wang Jing,et al.Hyperspectral Image Classification based on Compsite Kernels Support Vector Machine[J].Journal of Zhejiang University (Engineering Science),2013,47(8):1403-1410.[厉小润,朱洁尔,王晶,等.组合核支持向量机高光谱图像分类[J].浙江大学学报(工学版),2013,47(8):1403-1410.]

[13]Chen Wei,Yu Xuchu,Zhang Pengqiang,et al.Object Recognition based on One-class Support Vector Machine in Hyperspectral Image[J].Journal of Computer Applications,2011,31(8):2092-2100.[陈伟,余旭初,张鹏强,等.基于一类支持向量机的高光谱影像地物识别[J].计算机应用,2011,31(8):2092-2100.]

[14]Cortes C,Vapnik V.Support-vector Networks[J].Machine Learning,1995,20(3):273-297.

[15]Cristianini N,Shawe-Taylor J.An Introduction to Support Vector Machines and other Kenel-based Learning Methods[M].Cambridge:Cambridge University Press,2000.[16]Liu Mengmeng,Liu Yalan,Sun Guoqing,et al.SVM Land Cover Classification based on Spectral and Textural Features Using Seratified Samples[J].Remote Sensing Technology and Application,2014,29(2):315-323.[刘萌萌,刘亚岚,孙国庆,等.结合纹理特征的SVM样本分层土地覆盖分类[J].遥感技术与应用,2014,29(2):315-323.]

[17]Jian Yanhuang,Zhao Qiangli.Machine Learning Techniques[M].Beijing:Publishing House of Electronics Industry,2009.[蒋艳凰,赵强利.机器学习方法[M].北京:电子工业出版社,2009.]

[18]Bai Peng,Zhang Xibin,Zhang Bin,et al.Support Vector Machines and Its Application in Mixed Gas Infrared Spectrum Analysis[M].Xian:Xidian University Publisher,2008.[白鹏,张喜斌,张斌,等.支持向量机理论及工程应用实例[M].西安:西安电子科技大学出版社,2008.]

[19]Tooke T R,Coops N C,Goodwin N R,et al.Extracting Urban Vegetation Characteristics Using Spectral Mixture Analysis and Decision Tree Classifications[J].Remote Sensing of Environment,2009,113(2):398-407.

[20]Yoav F,Robert E S.A Decision-theoretic Generalization of on-line Learning and an Application to Boosting[J].Journal of Computer and System Sciences,1997,55(1):119-139.

[21]Friedl M A,Brodley C E.Decision Tree Classification of Land Cover from Remotely Sensed Data[J].Remote Sensing of Environment,1997,61(3):399-409.

[22]Xu Ranran,Ju Haolin,Li Chaofeng.Non-balanced Binary Tree with Active Learning Support Vector Machine[J].Microelectronics & Computer,2013,30(5):55-58.[徐冉冉,琚昊霖,李朝锋.非平衡二叉树主动学习支持向量机[J].微电子学与计算机,2013,30(5):55-58.]

[23]Wang Xiaofeng,Qin Yuping.Research on SVM Multi-class Classification based on Binary Tree[J].Journal of Hunan Institute of Engineering,2008,18(3):68-70.[王晓锋,秦玉平.基于二叉树的SVM多类分类算法研究[J].湖南工程学院学报,2008,18(3):68-70.]

[24]Goodenough D G,Dyk A,Niemann K O,et al.Processing Hyperion and ALI for Forest Classification[J].IEEE Transactions on Geoscience Remote Sensing,2003,41(6):1321-1331.

[1] 肖昊,王杰. 基于IDL和MATLAB混合编程的两种光谱混合分析方法比较[J]. 遥感技术与应用, 2017, 32(5): 858-865.
[2] 李恒凯,欧彬,刘雨婷,邱玉宝. 基于混合像元分解的高光谱影像柑橘识别方法[J]. 遥感技术与应用, 2017, 32(4): 743-750.
[3] 鲍蕊,夏俊士,薛朝辉,杜培军,车美琴. 基于形态学属性剖面的高光谱影像集成分类[J]. 遥感技术与应用, 2016, 31(4): 731-738.
[4] 胡俊,谭琨,吴立新. 一种基于多项式逻辑回归高光谱影像分类方法的改进[J]. 遥感技术与应用, 2015, 30(1): 135-139.
[5] 李茜楠,苏红军. 基于萤火虫算法的高光谱遥感波段选择方法[J]. 遥感技术与应用, 2014, 29(5): 761-770.
[6] 苏俊英. 基于光谱曲线小波系数分维测度的高光谱影像高效分割方法[J]. 遥感技术与应用, 2012, 27(4): 555-559.
[7] 宋翠玉,李培军,杨锋杰. 基于多元局部二值模式的遥感图像纹理提取与分类[J]. 遥感技术与应用, 2011, 26(3): 322-327.
[8] 张飞,塔西甫拉提?特依拜,丁建丽,依力亚斯江.努尔麦麦提,田源. 新疆干旱区绿洲土壤盐渍化信息提取对比研究[J]. 遥感技术与应用, 2008, 23(4): 398-404.
[9] 苏俊英,舒宁. 一种基于非线性增益小波滤波的高光谱影像去噪技术研究[J]. 遥感技术与应用, 2008, 23(4): 434-439.