Please wait a minute...
img

官方微信

遥感技术与应用  2014, Vol. 29 Issue (5): 761-770    DOI: 10.11873/j.issn.1004-0323.2014.5.0761
模型与反演     
基于萤火虫算法的高光谱遥感波段选择方法
李茜楠,苏红军
(河海大学地球科学与工程学院,江苏 南京210098)
A Novel Hyperspectral Band Selection Method  Using Improved Firefly Algorithm
Li Qiannan,Su Hongjun
(School of Earth Sciences and Engineering,Hohai University,Nanjing 210098,China)
 全文: PDF(8664 KB)  
摘要:

高光谱图像在遥感领域中的应用越来越广泛,但由于自身的高数据维、波段间的高冗余度等特性给图像处理带来了一定困难,针对这个问题,提出一种基于类间可分性准则的改进萤火虫仿生算法,进行高光谱遥感波段选择。在分析萤火虫算法机理的基础上,阐述了利用该算法进行高光谱波段选择的思路,并构造波段相似性矩阵,选择欧氏距离、JM距离、光谱信息散度和离散度作为可分性准则来设置目标函数,根据目标函数值的优劣选择优势波段。最后,使用HYDICE Washington DC Mall和 HyMap Purdue Campus两个高光谱遥感影像数据进行实验验证,并利用支持向量机分类器对最佳波段组合进行精度评价,证明该算法的可行性和有效性。

关键词: 高光谱影像萤火虫算法波段选择距离函数图像分类    
Abstract:

Hyperspectral image has increasingly wide applications in remote sensing field.However,its own high dimension data and high redundant in inter\|band takes certain difficulties.For this issue,the paper put forward a novel algorithm by improving the firefly algorithm based on between\|class separability criteria to precede band selection.Specifically,motivated by firefly algorithm,the idea and framework using bio\|inspired algorithm for hyperspectral band selection are described,similarity matrix in inter\|band is designed,Euclidean distance,J\|M distance,spectral information divergence as between\|class separability criterion are used for objective function,and the discriminant bands based on the merits of target value are chosen.In addition,the experiments and performance assessment were conducted by HYDICE Washington DC Mall and HyMap Purdue Campus data.The experiment results have proved the promising ability of the proposed method for hyperspectral band selection.

Key words: Hyperspectral image    Firefly algorithm    Band selection    Distance functions    Image classification
收稿日期: 2013-09-27 出版日期: 2014-11-10
:  TP 751  
基金资助:

国家自然科学基金项目(41201341),测绘遥感信息工程国家重点实验室(武汉大学)开放基金(12R02),江苏省光谱成像与智能感知重点实验室(南京理工大学)开放基金项目(11301006)资助。

通讯作者: 苏红军(1985-),男,河南永城人,博士,硕导,主要从事高光谱遥感和资源环境遥感方面的研究。Email:hjsurs@163.com。   
作者简介: 李茜楠(1989-),女,河南新乡人,硕士研究生,主要从事高光谱遥感降维研究。Email:zuozhull@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  
李茜楠
苏红军

引用本文:

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.

Li Qiannan,Su Hongjun. A Novel Hyperspectral Band Selection Method  Using Improved Firefly Algorithm. Remote Sensing Technology and Application, 2014, 29(5): 761-770.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2014.5.0761        http://www.rsta.ac.cn/CN/Y2014/V29/I5/761

[1]Pu Ruiliang,Gong Peng.Hyperspectral Remote Sensing and Its Application[M].Beijing:Higher Education Press,2000.[蒲瑞良,宫鹏.高光谱遥感及其应用[M].北京:高等教育出版社,2000.]

[2]Zhang Xiaocan,Huang Zhicai,Zhao Yuanhong.Remote Sensing Digital Image Processing[M].Hangzhou:Zhejiang Univercity Press,2003:174-175.[章孝灿,黄智才,赵元洪.遥感数字图像处理[M].杭州:浙江大学出版社,2003:174-175.]

[3]Sheffield C.Selecting Band Combination from Multispectral Data[J].Photogrammetric Engineering and Remote Sensing,1985,51(6):681-687.

[4]Lu Dengsheng,You Xianxiang,Cui Saihua.Analysis and Study Characteristics of TM Iimage Information Extraction[J].Environment of Remote Sensing,1991,6(4):267-274.[陆灯盛,游先祥,崔赛华.TM图像的信息量分析及特征信息提取的研究[J].环境遥感,1991,6(4):267-274.]

[5]Warner T,Shank M.Spatial Autocorrelation Analysis of Hyperspectral Imagery for Feature Selection[J].Remote Sensing of Environment,1997,60:58-70.

[6]Chavez P S,Berlin G L,Sowers L B.Statistical Method for Selecting Landsat MSS Ratios[J].Journal of Applied Photographic Engineering,1982,8:23-30.

[7]Liu Chunhong,Zhao Chunhui,Zhang Lingyan.A New Method of Hyperspectral Remote Sensing Image Dimensional Reduction[J].Journal of China Image and Graphics,2005,10(2):218-222.[刘春红,赵春晖,张凌雁.一种新的高光谱遥感图像降维方法[J].中国图象图形学报,2005,10(2):218-222.]

[8]Liu Jianping.Design and Iimplementation of Hyperspectral Remote Sensing Data Processing and Analysis Software System[D].Hefei:University of Science and Technology of China,2001:22-23.[刘建平.高光谱遥感数据处理分析软件系统设计与实现[D].合肥:中国科学技术大学,2001:22-23.]

[9]Zhao Dong,Zhao Guangheng.Band Selection of Hypersp-ectral Image based on Improved Genetical Gorithm[J].Journal of Chinese Academy of Sciences,2009,26(6):795-802.[赵冬,赵光恒.基于改进遗传算法的高光谱图像波段选择[J].中国科学院研究生院学报,2009,26(6):795-802.]

[10]Wang Liguo,Gu Yanfeng,Zhang Ye.Band Selection Method based on Combination of Supportvect or Machines and Subspatial Partition[J].Systems Engineering and Electronics,2005,27(6):974-977.[王立国,谷延锋,张晔.基于支持向量机和子空间划分的波段选择方法[J].系统工程与电子技术,2005,27(6):974-977.]

[11]Yang X S.Firefly Algorithms for Multimodal Optimization[C]//Proceedings of the 5th International Conference on Stochastic Algorithms:Foundations and Applications.Berlin,Springer-Verlag,2009:169-178.

[12]Li Li,Yao Ye,Li Tie.Study of Cloud Computing Resources based on Improved Firefly Algorithm[J].Application Research of Computers,2013,30(8):2298-2300.[李逦,姚晔,李铁.基于改进型人工萤火虫算法的云计算资源研究[J].计算机应用研究,2013,30(8):2298-2300.]

[13]Liu Peng,Liu Hong,Zheng Xiangwei,et al.Approachfor Dynamic Group Automatic Aggregation Path Planning based on Improved FA[J].Application Research of Computers,2011,28(11):4146-4149.[刘鹏,刘弘,郑向伟,等.基于改进萤火虫算法的动态自动聚集路径规划方法[J].计算机应用研究,2011,28(11):4146-4149.]

[14]Zhou Jihua,Ye Chunming.Using Firefly Algorithm to Solve Permutation Flow-shop Scheduling Problem[J].Application Research of Computers,2013,30(1):152-154.[周季华,叶春明.应用萤火虫算法求解置换流水线问题[J].计算机应用研究,2013,30(1):152-154.]

[15]Liu Changping,Ye Chunming.Novel Bioinspired Swarm Intelligence Optimization Algorithm:Firefly Algorithm[J].Application Research of Computers,2011,28(9):3295-3297.[刘长平,叶春明.一种新颖的仿生群智能优化算法:萤火虫算法[J].计算机应用研究,2011,28(9):3295-3297.]

[16]Yang H,Du Q,Su H,et al.An Efficient Method for Supervised Hyperspectral Band Selection[J].IEEE Geoscience and Remote Sensing Letters,2011,8(1):138-142.

[17]Huang Fenggang,Song Keou.Pattern Recognition[M].Haerbin:Harbin Engineering University Press,1998:5-314.[黄凤岗,宋克欧.模式识别[M].哈尔滨:哈尔滨工程大学出版社,1998:5-314.]

[18]Landgrebe D.Signal Theory Methods in Multispeetral Remote Sensing[M].Hoboken:John Wiley,Sons,2003.

[19]Tong Qingxi,Zhang Bing,Zheng Lanfen.Hyperspectral Remote Sensing-Theory,Technology and Application[M].Beijing:Higher Education Press,2006.[童庆禧,张兵,郑兰芬.高光谱遥感——原理、技术与应用[M].北京:高等教育出版社,2006.]

[20]Rousseeuw P J,Ruts I,Tukey J W.The Bagplot:A Bivariate Boxplot[J].The American Statistician,1999,53(4):382-387.

[1] 陈伟民,张凌,宋冬梅,王斌,丁亚雄,许明明,崔建勇. 基于AdaBoost改进随机森林的高光谱图像地物分类方法研究[J]. 遥感技术与应用, 2018, 33(4): 612-620.
[2] 刘慧珺,苏红军,赵-波. 基于改进萤火虫算法的高光谱遥感多特征优化方法[J]. 遥感技术与应用, 2018, 33(1): 110-118.
[3] 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.
[4] 秦俊,冷寒冰,赵广琦,景军,周坚华. 物候和波谱—位置分析在城镇绿化植物群分类中的应用[J]. 遥感技术与应用, 2017, 32(5): 948-957.
[5] 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.
[6] 苏红军,赵波. 基于共形几何代数的高光谱遥感波段选择方法[J]. 遥感技术与应用, 2017, 32(3): 539-545.
[7] 袁春琦,徐佳,程圆娥,陈媛媛,许康. 基于协同训练与集成学习的极化SAR图像半监督分类[J]. 遥感技术与应用, 2017, 32(2): 380-385.
[8] 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.
[9] 张路,刘良云,高建威,焦全军,贾建华. 基于蚁群优化算法的遥感器波段设置探究[J]. 遥感技术与应用, 2016, 31(3): 488-496.
[10] 丁小辉,李华朋,张树清. 基于多态蚁群算法的高光谱遥感影像最优波段选择[J]. 遥感技术与应用, 2016, 31(2): 275-284.
[11] 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.
[12] 王晶,王丽姣,崔建涛,厉小润. 基于信噪比估计的波段选择与高光谱异常检测[J]. 遥感技术与应用, 2015, 30(2): 292-297.
[13] 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.
[14] 袁宗泽,孙浩,计科峰,邹焕新. 基于Fisher字典学习稀疏表示的高光谱图像分类[J]. 遥感技术与应用, 2014, 29(4): 646-652.
[15] 张汉奎,黄 波,俞 乐. SVM-RFE高光谱数据波段选择中核函数的研究[J]. 遥感技术与应用, 2013, 28(5): 747-752.