Please wait a minute...
img

官方微信

遥感技术与应用  2019, Vol. 34 Issue (1): 115-124    DOI: 10.11873/j.issn.1004-0323.2019.1.0115
数据与图像处理     
ELM与SVM在高光谱遥感图像监督分类中的比较研究
牟多铎,刘磊
(长安大学地球科学与资源学院,陕西 西安 710064)
Comparative Study of ELM and SVM in Hyperspectral Image Supervision Classification
Mou Duoduo,Liu Lei
(School of Earth Science and Resources,Chang'an University,Xi’an,710064,China)
 全文: PDF(11740 KB)  
摘要: 在高光谱遥感图像监督分类过程中加入空间特征信息,可有效提高分类的速度与精度。将空间信息提取方法分水岭法与极限学习机(ELM)和支持向量机(SVM)相结合,对两种分类方法加入空间特征信息前后的分类结果进行时间与精度的综合评价与比较分析。以意大利帕维亚大学(PaviaU)ROSIS和博茨瓦纳(Botswana)奥卡瓦纳三角洲Hyperion高光谱遥感数据进行试验,首先对原始图像数据进行预处理,对不同地物类别选取适当的训练样本作为分类的参考区域,然后对各类别的光谱特征进行分析,并分别运用两种分类方法对数据集进行分类实验;之后将光谱特征与空间特征结合对数据进行分类试验。实验结果表明:在分类时间及精度方面,极限学习机(ELM)均优于支持向量机(SVM);在分类过程中引入空间特征信息,可有效提高分类精度。
关键词: 高光谱遥感监督分类极限学习机支持向量机时间与精度    
Abstract: Combining the spatial features and spectral feature of hyperspectral remote sensing image in supervised classification can effectively improve the classification time and accuracy.In this study,the spatial information extraction method,named watershed transform,was combined with the Extreme Learning Machine(ELM)and Support Vector Machine(SVM)methods.The classification results of the datasets with the spatial features and without the spatial features were synthetically evaluated and compared.Two hyperspectral datasets,the ROSIS data of Pavia university and the Hyperion data of Okavango Delta(Botswana),were selected to test the methods.After preprocessing,the training samples were selected from the images as the reference areas for each type,and the spectral features of each type were analyzed.The two classification methods were utilized to classify the hyperspectral datasets and relevant classification results were obtained.based on the validation samples selected from the images,the classification results were evaluated using the confusion matrix and the execution times.After that,the spectral features and spatial features were combined to classify the data.The results show that the Extreme Learning Machine(ELM) is superior to the Support Vector Machine(SVM)in the classification time and precision,and the spatial features are introduced in the classification process,which can effectively improve the classification accuracy.
Key words: Hyperspectral remote sensing    Supervised classification    Extreme learning machine    Support vector machine    Classification time and accuracy
收稿日期: 2018-04-11 出版日期: 2019-04-02
ZTFLH:  P237  
基金资助: 陕西省创新能力支撑计划(2018KJXX-062),中央高校基本科研业务费专项资金(300102278303)。
作者简介: 牟多铎(1991-),男,辽宁大连人,硕士研究生,主要从事遥感与GIS应用研究。E-mail:2488545866@qq.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  

引用本文:

牟多铎, 刘磊. ELM与SVM在高光谱遥感图像监督分类中的比较研究[J]. 遥感技术与应用, 2019, 34(1): 115-124.

Mou Duoduo, Liu Lei. Comparative Study of ELM and SVM in Hyperspectral Image Supervision Classification. Remote Sensing Technology and Application, 2019, 34(1): 115-124.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2019.1.0115        http://www.rsta.ac.cn/CN/Y2019/V34/I1/115

[1]Cheng F,Thiel K H.Delimiting the Building Heights in a City from the Shadow in Panchromatic SPOT-image-part 1-test of Forty Two Buildings[J].International Journal of Remote Sensing,1995,16(3):409-415. [2]Hartl P H,Cheng F.Delimiting the Building Heights in a City from the Shadow in Panchromatic SPOT-image-part1-test of a Complete City[J].International Journal Remote Sensing,1995,16(15):2829-2842. [3]Shettigara V K,Sumerling G M.Height Determination of Extended Objects Using Shadows in SPOT Images[J].PE & RS,1998,64(1):35-44. [4]He Guojin,Chen Gang,He Xiaoyun,et al.Extracting Buildings Distribution Information of Different Heights in a City from the Shadows in a Panchromatic SPOT Image[J].Journal of Image and Graphics,2001,6(5):426-428.[何国金,陈刚,何晓云,等.用SPOT图像阴影提取城市建筑物高度及其分布信息[J].中国图象图形学报,2001,6(5):426~428.] [5]Tian Feng,Chen Donghua,Huang Xinli,et al.Building Height Estimation from GF-2 Image based on Morphological Shadow Index[J].Remote Sensing Technology and Application,2017,32(5):844-850.[田峰,陈冬花,黄新利,等.基于形态学阴影指数的高分二号影像建筑物高度估计[J].遥感技术与应用,2017,32(5):844-850.] [6]Huang Rong,Li Dan,Qiao Xiangfei.The Extraction of Building Heights from the Shadows in a QuickBird Image[J].Bulletin of Surveying and Mapping,2012,Sup.:281-283.[黄蓉,李丹,乔相飞.基于QuickBird卫星影像阴影的青岛市建筑物高度提取[J],测绘通报,2012,增刊:281-283.] [7]Zhang Xiaomei,He Guojin,Wang Wei,et al.Extracting Buildings Height and Distribution Information in Tianjin City from the Shadows in ALOS Images[J].Spectroscopy and Spectral Analysis,2011,31(7):2003-2006.[张晓美,何国金,王威,等.基于ALOS卫星图像阴影的天津市建筑物高度及分布信息提取[J].光谱学与光谱分析,2011,31(7):2003-2006.] [8]Chen T,Zhu S Y,Zhang G X,et al.A Comparative Study on Building Height Extraction based on the Shadow Information in High Resolution Remote Sensing Image and Stereo Images[J].Journal of Geo-information Science,2016,18(7):1267-1175.[陈亭,祝善友,张桂欣,等.高分辨率遥感影像阴影与立体像对提取建筑物高度比较研究[J].地球信息科学学报,2016,18(9):1267-1175.] [9]Wang Yonggang,Liu Huipign.The Calculation of Building Shadow Length Using Statistical Average Method based on Corner Shortest Distance[J].Remote Sensing for Land & Resource,2008,3(77):31-36.[王永刚,刘慧平.利用角点最近距离统计平均法计算建筑物阴影长度[J].国土资源遥感,2008,3(77):31-36.] [10]Ding Zhe,Wang Xiaoqin,Wu Qunyong,et al.Effects of Different Spatial Resolution of Remote Sensing Images on Estimation Accuracy of Urban Building Height[J].Remote Sensing Technology and Application.2018,33(3):418-427.[丁哲,汪小钦,邬群勇,等.遥感影像空间分辨率对城市建筑物高度估算精度的影响[J].遥感技术与应用,2018,33(3):418-427.] [11]Xie Junfei,Li Yanming.The Extraction of Building Distribution Information of Different Heights in a City from the Shadows in a IKONOS Image[J].Remote Sensing for Land & Resources,2004,(4):4-6.[谢军飞,李延明.利用IKONOS卫星图像阴影提取城市建筑物高度信息[J].国土资源遥感,2004,(4):4-6.] [12]Ran Qiong,Chi Yaobin,Wang Zhiyong,et al.Research on Building Height Estimation Using Shadow Information Using Beijing-1 Small Satellite Images[J].Remote Sensing Information,2008,(4):18-21.[冉琼,迟耀斌,王智勇,等.基于“北京一号”小卫星影像阴影的建筑物高度测算研究[J].遥感信息,2008,(4):18-21.] [13]Tian Xinguang,Zhang Jixian,Zhang Yonghong.Extraction of Heights of Buildings in City from Shadows in QuickBird Image[J].Science of Surveying and Mapping,2008,32(2):88-89.[田新光,张继贤,张永红.利用QuickBird 影像的阴影提取建筑物高度[J].测绘科学,2008,32(2):88-89.] [14]Liu Longfei,Wang Ruijun,Dong Weiping,et al.A Fast Method Extracting Building Height Using High Resolution Satellite Image[J].Remote Sensing Technology and Application,2009,24(5):631-634.[刘龙飞,王锐君,懂卫平,等.一种快速提取建筑物高度的方法研究[J],遥感技术与应用,2009,24(5):631-634.] [15]Wang Jingwei,Guo Qiuying,Zheng Guoqiang.Research on Urban Building Height Extraction from Single Satellite Image[J].Bulletin of Surveying and Mapping,2012(4):15-17.[王京卫,郭秋英,郑国强.基于单张遥感影像的城市建筑物高度提取研究[J].测绘通报,2012(4):15-17.] [16]Shi Yifang,Wang Xiaoqin,Sun Zhenhai,et al.Urban Building Heights Estimation from the Shadow Information on ZY-3 Images[J].Journal of Geo-information Science,2015,17(2):236-243.[石义方,汪小钦,孙振海,等.基于阴影的资源三号卫星数据城市建筑物高度估算[J],地球信息科学,2015,17(2):236-243.] [17]Li Cong,Chen Yang,Xu Zuying,et al.Research of Building Height Inversion based on High-resolution Satellite Images Shadow[J].Journal of Heilongjiang Institute of Technology,2018,32(3):11-14.[李聪,陈阳,徐祖英,等.基于高分辨率卫星影像阴影的建筑物高度反演研究[J].黑龙江工程学院学报,2018,32(3):11-14.] [18]Zhang Guifang,Shan Xinjian,Yin Jingyuan,et al.The Method to Extract Urban Building’s Height and Location from Single High Resolution Aerial Imagery[J].Seismology and Geology,2007,29(1):180-187.[张桂芳,单新建,尹京苑,等.单幅高空间分辨率卫星图像提取建筑物三维信息的方法研究[J].地震地质,2007,29(1):186-187.]
[1] 谷晓天, 高小红, 马慧娟, 史飞飞, 刘雪梅, 曹晓敏. 复杂地形区土地利用/土地覆被分类机器学习方法比较研究[J]. 遥感技术与应用, 2019, 34(1): 57-67.
[2] 苏阳,祁元,王建华,徐菲楠,张金龙. 基于航空高光谱影像的额济纳绿洲土地覆被提取[J]. 遥感技术与应用, 2018, 33(2): 202-211.
[3] 秦振涛,杨茹,张靖,杨武年. 基于聚类结构自适应稀疏表示的高光谱遥感图像修复研究[J]. 遥感技术与应用, 2018, 33(2): 212-215.
[4] 郭宇柏,卓莉,陶海燕,曹晶晶,王芳. 基于空谱初始化的非负矩阵光谱混合像元盲分解[J]. 遥感技术与应用, 2018, 33(2): 216-226.
[5] 吴兴,张霞,孙雪剑,张立福,戚文超. SPARK卫星高光谱数据辐射质量评价[J]. 遥感技术与应用, 2018, 33(2): 233-240.
[6] 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.
[7] 熊伟,徐永力,姚力波,崔亚奇. 基于SVM的高分辨率SAR图像舰船目标检测算法[J]. 遥感技术与应用, 2018, 33(1): 119-127.
[8] 陈洋波,张涛,窦鹏,董礼明,陈华. 基于SVM的东莞市土地利用/覆被自动分类误差来源与后处理[J]. 遥感技术与应用, 2017, 32(5): 893-903.
[9] 唐超,邵龙义. 高光谱遥感地物目标识别算法及其在岩性特征提取中的应用[J]. 遥感技术与应用, 2017, 32(4): 691-697.
[10] 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.
[11] 史飞飞,高小红,杨灵玉,何林华,贾伟. 基于HJ-1A高光谱遥感数据的湟水流域典型农作物分类研究[J]. 遥感技术与应用, 2017, 32(2): 206-217.
[12] 胡根生,吴问天,黄文江,梁栋,黄林生. 粒子群优化的最小二乘支持向量机在小麦白粉病监测中的应用[J]. 遥感技术与应用, 2017, 32(2): 299-304.
[13] 朱济帅,尹作霞,谭琨,王雪,李二珠,杜培军. 基于空间邻域信息的高光谱遥感影像半监督协同训练[J]. 遥感技术与应用, 2016, 31(6): 1122-1130.
[14] 张霞,戚文超,孙伟超. 基于数学形态滤波的植被光谱去噪方法研究[J]. 遥感技术与应用, 2016, 31(5): 846-854.
[15] 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.