Please wait a minute...
img

官方微信

遥感技术与应用  2013, Vol. 28 Issue (4): 655-658    DOI: 10.11873/j.issn.1004-0323.2013.4.655
图像与数据处理     
利用专题指数改善沙漠化土地遥感分类精度
孙建国1,2,姜烨1,颜长珍2
(1.兰州交通大学测绘与地理信息学院,甘肃 兰州 730070;
2.中国科学院寒区旱区环境与工程研究所,甘肃 兰州 730000)
Improving Desertification Land Classification Accuracy Using Thematic Index Extracted from Spectral Transformation
Sun Jianguo1,2,Jiang Ye1,Yan Changzhen2
(1.Faculty of Geomatics,Lanzhou Jiaotong University,Lanzhou 730070,China;
2.Cold and Arid Regions Environmental and Engineering Research Institute,
Chinese Academy of Sciences,Lanzhou 730000,China)
 全文: PDF(1406 KB)  
摘要:

以民勤绿洲及周边区域ETM+数据为例,分析光谱变换专题指数和纹理特征变量的参与对沙漠化土地分类精度的影响,以及不同分类器对两者的响应。原始数据中单独加入专题指数,并不一定直接提高总体分类精度,在同时加入纹理变量的情况下,专题指数的作用才得以充分体现;最大似然法和人工神经网络法分类器对输入变量的响应有所不同,前者在3类数据同时参与时效果最佳,而后者在剔除原始数据时取得最高总体分类精度。实验表明:光谱变换专题指数能够提高沙漠化土地分类精度,但必须慎重选择分类器和分类变量。

关键词: 专题指数纹理特征沙漠化土地分类ETM+民勤绿洲    
Abstract:

Taking the ETM+ data of Minqin oasis and the surrounding area as example,this paper analyses the roles of the spectral thematic index and texture characteristics in land cover classification,as well as the responses of different classifiers.It is not necessary that adding thematic index into the original band data can improve the overall classification accuracy.While adding texture variables at the same time the thematic index is able to fully play their roles.Maximum Likelihood Classifier(MLC) and Artificial Neural Network(ANN) response to the input variables differently.The former obtains the best results when three types of data all be involved and the latter obtains the highest overall classification accuracy when the original band be removed.The study shows that the spectral thematic index can improve land cover classification accuracy,but classifiers and variables (bands) combinations must be carefully chosen.

Key words: Thematic index    Texture feature    Desertification land classification    ETM+    Minqin oasis
收稿日期: 2012-05-08 出版日期: 2013-08-14
:  TP 75  
基金资助:

中国科学院重点部署项目“黄土高原及周边沙地近代生态环境的演变与可持续发展性”(KZZD-EW-04-04),中国博士后科学基金项目(20110490861),兰州交通大学科技支撑基金(ZC2012006)资助。

作者简介: 孙建国(1974-),男,甘肃会宁人,副教授,博士,主要从事荒漠化遥感和GIS应用研究。E-mail:sunjguo@mail.lzjtu.cn。
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  
孙建国
姜烨
颜长珍

引用本文:

孙建国,姜烨,颜长珍. 利用专题指数改善沙漠化土地遥感分类精度[J]. 遥感技术与应用, 2013, 28(4): 655-658.

Sun Jianguo,Jiang Ye,Yan Changzhen. Improving Desertification Land Classification Accuracy Using Thematic Index Extracted from Spectral Transformation. Remote Sensing Technology and Application, 2013, 28(4): 655-658.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2013.4.655        http://www.rsta.ac.cn/CN/Y2013/V28/I4/655

[1]Koc-San D,Turker M.A Model-based Approach for Automatic Building Database Updating from High-resolution Space Imagery[J].International Journal of Remote Sensing,2012,33(13):4193-4218.

[2]Heinl M,Walde J,Tappeiner G,et al.Classifiers vs.Input Variables-the Drivers in Image Classification for Land Cover Mapping[J].International Journal of Applied Earth Observation and Geoinformation,2009,11(6):423-430.

[3]Dos S,Jefersson A,Gosselin P.Multiscale Classification of Remote Sensing Images[J].IEEE Transactions on Geoscience and Remote Sensing,2012,50(10):3764-3775.

[4]Yang Yongchun.The Analysis of the Oasis Environmental Change and Its Reason of the Lower Reaches of the Arid Region——A Case Study of Minqin County in the Lower Reaches of Shiyang River in Hexi Corridor,Gansu Province[J].Human Geography,2003,18(4):42-47.[杨永春.干旱区流域下游绿洲环境变化及其成因分析——以甘肃省河西地区石羊河流域下游民勤为例[J].人文地理,2003,18(4):42-47.]

[5]Xu Hanqiu.A Study on Information Extraction of Water Body with the Modified Normalized Difference Water Index (MNDWI)[J].Journal of Remote Sensing,2005,9(5):589-595.[徐涵秋.利用改进的归一化差异水体指数(MNDWI)提取水体信息的研究[J].遥感学报,2005,9(5):589-595.]

[6]Xu H Q.Analysis of Impervious Surface and Its Impact on Urban Heat Environment using the Normalized Difference Impervious Surface Index (NDISI)[J].Photogrammetric Engineering and Remote Sensing,2010,76(5):557-565.

[7]Wu Hongan,Jiang Jianjun,Zhou Jie,et al.Dynamics of Urban Expansion in Xi’an City Using Landsat TM/ETM+ Data[J].Acta Geographic Sinica,2005,60(1):143-150.[吴宏安,蒋建军,周杰,等.西安城市扩张及其驱动力分析[J].地理学报,2005,60(1):143-150.]

[8]Khan N M,Rastoskuev V V.Assessment of Hydrosaline Land Degradation by Using a Simple Approach of Remote Sensing Indicators[J].Agricultural Water Management,2005,77(1-3):96-109.

[9]Xiao J,Shen Y,Tateishi R,et al.Development of Topsoil Grain Size Index for Monitoring Desertification in Arid Land Using Remote Sensing[J].International Journal of Remote Sensing,2006,27(12):2411-2422.

[10]Haralick R,Shanmugam K,Dinstein I.Textural Features for Image Classification[C]//IEEE Transaction on Systems,Man,Cybernetics,1973,3(6):610-621.

[11]Yan Meichun.Research and Contrast on Several Vegetation-Classification Methods of High-resolution Satellite Image Data[J].Journal of Remote Sensing,2007,11(2):235-240.[颜梅春.高分辨率影像的植被分类方法对比研究[J].遥感学报,2007,11(2):235-240.]

[12]Chen Yanli,Mo Weihua,Mo Jianfei,et al.Object Oriented Classification for the Extraction of Rice Planting Area in South[J].Remote Sensing Technology and Application,2011,26(2):163-168.[陈燕丽,莫伟华,莫建飞,等.基于面向对像分类的南方水稻种植面积提取方法[J].遥感技术与应用,2011,26(2):163-168.][13]Robertson L D,Douglas K J.Comparison Of Pixel-and Object-Based Classification in Land Cover Change Mapping[J].International Journal of Remote Sensing,2011,32(6):1505-1529.

[1] 翟玮,沈焕锋,黄春林. 结合PolSAR影像纹理特征分析提取倒塌建筑物[J]. 遥感技术与应用, 2016, 31(5): 975-982.
[2] 邓滢,张红,王超,刘萌. 结合纹理与极化分解的面向对象极化SAR水体提取方法[J]. 遥感技术与应用, 2016, 31(4): 714-723.
[3] 管小彬,沈焕锋,甘文霞,张良培. 基于Landsat TM/ETM+影像的武汉市冬季NPP估算及其时空变化分析[J]. 遥感技术与应用, 2015, 30(5): 884-890.
[4] 邹亚荣,黄磊,张治平. 结合纹理特征的SVM岛礁信息提取分析[J]. 遥感技术与应用, 2014, 29(5): 812-817.
[5] 尹芳,张建超,周军,李昱星,牛涛,李盼. 基于ETM+和CBERS数据的甘肃北山音凹峡地区镁铁超镁铁岩体识别[J]. 遥感技术与应用, 2014, 29(3): 457-462.
[6] 刘萌萌,刘亚岚,孙国庆,彭立. 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.
[7] 陈劲松. 基于ETM+影像的矿化蚀变区植被信息提取研究[J]. 遥感技术与应用, 2013, 28(6): 1083-1087.
[8] 赵小星,钱建平,覃顺桥,黄克宸,韩 帅. 云南江城大团包铜矿及外围高植被区遥感找矿预测[J]. 遥感技术与应用, 2013, 28(5): 879-889.
[9] 赵凯,徐剑波,赵之重,宋立生,肖科. HJ-1A/B CCD与Landsat TM/ETM+植被指数的交互比较[J]. 遥感技术与应用, 2013, 28(4): 674-680.
[10] 郝利娜,张志,张翠芬. 山东省寿光市滨海地区盐田信息提取方法研究[J]. 遥感技术与应用, 2013, 28(3): 526-532.
[11] 徐 佳,陈媛媛,黄其欢,何秀凤. 综合灰度与纹理特征的高分辨率星载SAR图像建筑区提取方法研究[J]. 遥感技术与应用, 2012, 27(5): 692-698.
[12] 刘友山,吕成文,祝凤霞,高 超. 基于PCA和多尺度纹理特征提取的高分辨率遥感影像分类[J]. 遥感技术与应用, 2012, 27(5): 706-711.
[13] 许领,杨馨蕊,陈剑. 地质灾害调查中ETM+与SPOT-5 Pan融合方法比较[J]. 遥感技术与应用, 2008, 23(5): 551-555.
[14] 刘庆生,刘高焕,姚玲. 利用Landsat ETM+数据检测人工刺槐林冠健康[J]. 遥感技术与应用, 2008, 23(2): 142-146.
[15] 邹斌, 张腊梅, 裴彩红, 张晔. 基于SVM的POL-SAR图像分类研究[J]. 遥感技术与应用, 2007, 22(5): 633-636.