收藏 ｜ 设为首页 广告服务 ｜ 联系我们 ｜ 在线留言
高级检索

干旱区地理 >

2019 , Vol. 42 >Issue 5: 1133 - 1140

DOI: https://doi.org/10.12118/j.issn.1000-6060.2019.05.19

地球信息科学

基于CART决策树的沙地信息提取方法研究

展开
  • 1 宁夏大学物理与电子电气工程学院，宁夏 银川 750021； 2 西北土地退化与生态恢复省部共建国家重点实验室培育基地，宁夏银川750021；3宁夏回族自治区沙漠信息智能感知重点实验室，宁夏 银川 750021
张睎伟（1993-），男，硕士，研究方向为遥感图像处理研究. E-mail：zhang_xiwei@163.com

收稿日期: 2019-02-10

  修回日期: 2019-05-24

  网络出版日期: 2019-09-19

基金资助

国家自然基金（41561087）

收起

Sand information extraction method based on CART decision tree

Expand
  • 1 School of Physics and ElectronicElectrical Engineering,Ningxia University,Yinchuan 750021,Ningxia,China;

    2 Breeding Base for State Key Laboratory of Land Degradation and Ecological Restoration in Northwest China, Yinchuan 750021,Ningxia,China;3Ningxia Hui Autonomous Region Desert Information Intellisense Key Laboratory,Ningxia University,Yinchuan 750021,Ningxia,China

Received date: 2019-02-10

  Revised date: 2019-05-24

  Online published: 2019-09-19

Fold

摘要

为研究沙地信息提取的方法，采用基于CART决策树的面向对象方法，提取中卫市沙坡头区的沙地信息。首先对研究区进行多尺度分割和光谱差异分割得到对象层，然后选择合适的提取特征和训练样本点，最后输入选择的提取特征和样本点生成CART规则树，并对地物进行分类，提取出沙地信息。结果表明：采用面向对象的CART决策树方法提取沙地信息具有较高自动化程度和精确度，依此构建的CART决策树总体分类精度可达到77%，是最近邻分类结果的1.12倍，支持向量机分类结果的1.57倍，此外，NDBI（归一化裸露指数）、GSI（粒度指数）和SWIR 2（第七波段）均值可以成功的将沙地、戈壁和裸岩石砾地三个易混地物区分开来，是沙地提取过程中三个重要的特征指数。

关键词： ; font-size:10.5pt; ">面向对象; 多尺度; 光谱差异; CART决策树; 沙地提取

本文引用格式

张睎伟, 王磊, 汪西原 . 基于CART决策树的沙地信息提取方法研究[J]. 干旱区地理, 2019 , 42(5) : 1133 -1140 . DOI: 10.12118/j.issn.1000-6060.2019.05.19

Abstract

 

This paper used the object-oriented method and CART decision tree method to extract the sand information with high degree of automation and comprehensive extraction features.The main research process is as follows: (1) Select the study area and preprocess the image of the study area. (2) Use multi-scale segmentation and spectral difference segmentation to obtain the object layer. (3) Select rich extraction features and training sample objects. (4) Training features and sample objects to get the CART rule tree. (5) Apply all objects to the rule tree to get the classification result. (6) Compare the Nearest neighbor and Support vector machine classification results.Finally,Compared with the current research on extracting sand information by CART decision tree.The overall classification accuracy reached 77%,which is 1.12 times of the Nearest neighbor classification result,1.57 times of the support vector machine classification result.In addition,normalized diffevence bare index (NDBI), granularity size index (GSI) and the seventh band (SWIR 2) can successfully distinguish three easily mixed objects of sand, Gobi and bare rock,which are three important characteristic indexes in the process of sand extraction.The experiment has proven this method is a feasible sand extraction method for actual desertification monitoring.

Key words： ; font-size:10.5pt; ">object; font-size:10.5pt; ">-; font-size:10.5pt; ">oriented; multi; font-size:10.5pt; ">-; font-size:10.5pt; ">scale; spectral differences; CART decision tree; sand extraction

参考文献

［1］王梅梅,朱志玲,吴咏梅.宁夏中部干旱带土地沙漠化评价［J］.中国沙漠,2013,33(2):320-324.［WANG Meimei,ZHU Zhiling,WU Yongmei.Assessment on the sensitivity to aeolian desertification and importance of controlling aeolian desertification in the middle arid region of Ningxia［J］.Journal of Desert Research,2013,33(2):320-324.］ ［2］李元科,全志杰,吕恒,等.GIS支持下的盐池县土地沙漠化动态遥感监测与预估［J］.干旱环境监测,1998,(4):213-217+252.［LI Yuanke,QUAN Zhijie,LV Heng,et al.Remute sensing monitoring and forecast of the desertification trends of Yanchi County by GIS［J］.Arid Environmental Moitoring,1998,(4):213-217,252.］ ［3］李晓琴,张振德,张佩民.格尔木土地荒漠化遥感动态监测研究［J］.国土资源遥感,2006,(2):61-63,78.［LI Xiaoqin,ZHANG Zhende,ZHANG Peimin.Remote sensing survey and monitoring of desertification in Golmud area［J］.Remote Sensing for Land & Resources,2006,(2):61-63,78.］ ［4］乔平林,张继贤,林宗坚.基于神经网络的土地荒漠化信息提取方法研究［J］.测绘学报,2004,33(1):58-62.［QIAO Pinglin,ZHANG Jixian,LIN Zongjian.An artificial neural network method for the information of desertification extraction［J］.Acta Geodaetica et Cartographica Sinica,2004,33(1):58-62.］ ［5］王志波,高志海,王琫瑜,等.基于面向对象方法的沙化土地遥感信息提取技术研究［J］.遥感技术与应用,2012,27(5):770-777.［WANG Zhibo,GAO Zhihai,WANG Bengyu,et al.The study of extracting sandy lands information from remote sensing image based on object-oriented method［J］.Remote Sensing Technology and Application,2012,27(5):770-777.］ ［6］冯益明,郑冬梅,智长贵,等.面向对象的沙化土地信息提取［J］.林业科学,2013,49(1):126-133.［FENG Yiming,ZHENG Dongmei,ZHI Changgui,et al.Desertification land information extraction based on object-oriented classification method［J］.Scientia Silvae Sinicae,2013,49(1):126-133.］ ［7］孙建伟,王超,王娜,等.基于CART决策树的ZY-3卫星遥感数据土地利用分类监测［J］.华中师范大学学报(自然科学版),2016,50(6):937-943.［SUN Jianwei,WANG Chao,WANG Na,et al.Research on land use classification monitoring though the remote sensing data of ZY-3 satellite based on CART decision tree［J］.Journal of Central China Normal University (Natural Science Edition),2016,50(6):937-943.］ ［8］段英杰,何政伟,王永前,等.基于遥感数据的西藏自治区土地沙漠化监测分析研究［J］.干旱区资源与环境,2014,28(1):55-61.［DUAN Yingjie,HE Zhengwei,WANG Yongqian,et al.Monitoring land desertification of Tibet Autonomous Region based on remote sensing［J］.Journal of Arid Land Resources and Environment,2014,28(1):55-61.］ ［9］康文平,刘树林,段翰晨.基于MODIS时间序列数据的沙漠化遥感监测及沙漠化土地图谱分析——以内蒙古中西部地区为例［J］.中国沙漠,2016,36(2):307-318.［KANG Wenping,LIU Shulin,DUAN Hanchen.Monitoring and spatial-temporal changes analysis of aeolian desertified lands based on MODIS data［J］.Journal of Desert Research,2016,36(2):307-318.］ ［10］吕利利,颉耀文,黄晓君,等.基于CART决策树分类的沙漠化信息提取方法研究［J］.遥感技术与应用,2017,32(3):499-506.［LYU Lili,XIE Yaowen,HUANG Xiaojun,et al.Desertification information extraction method research based on the CART decision tree classification［J］.Remote Sensing Technology and Application,2017,32(3):499-506.］ ［11］黄慧萍.面向对象影像分析中的尺度问题研究［D］.北京:中国科学院遥感应用研究所,2003.［HUANG Huiping.Scale issues in object-oriented image analysis［D］.Beijing: Institute of Remote Sensing Applications, Chinese Academy of Sciences,2003.］ ［12］文斯.遥感影像数据的面向对象分类与模糊逻辑分类研究［D］.昆明:昆明理工大学,2011.［WEN Si.Remote sensing image data object-oriented classification and fuzzy logic classification research［D］.Kunming: Kunming University of Science and Technology,2011.］ ［13］张晓娟,杨英健,盖利亚,等.基于CART决策树与最大似然比法的植被分类方法研究［J］.遥感信息,2010,(2):88-92.［ZHANG Xiaojuan,YANG Yingjian,GAI Liya,et,al.Research on vegetation classification method based on CART decision tree algorithm and maximum likelihood ratio［J］.Remote Sensing Information,2010,(2):88-92.］ ［14］齐乐,岳彩荣.基于CART决策树方法的遥感影像分类［J］.林业调查规划,2011,36(2):62-66.［QI Le,YUE Cairong.Remote sensing image classification based on CART decision tree method［J］.Forest Inventory and Planning,2011,36(2):62-66.］ ［15］ROUSE J W,HAAS R H,SCHELL J A,et al.Monitoring vegetation systems in the great plains with ERTS［C］∥Proceeding of 3rd ERTS-1 Symposium.NASA: Goddard Space Flight Center,1974:309-317. ［16］徐涵秋.基于谱间特征和归一化指数分析的城市建筑用地信息提取［J］.地理研究,2005,24(2):311-320,324.［XU Hanqiu.Fast information extraction of urban built-up land based on the analysis of spectral signature and normalized difference index［J］.Geographical Research,2005,24(2):311-320,324.］ ［17］查勇,倪绍祥,杨山.一种利用TM图像自动提取城镇用地信息的有效方法［J］.遥感学报,2003,7(1):37-40,82.［ZHA Yong,NI Shaoxiang,YANG Shan.An effective approach to automatically extract urban land-use from TM imagery［J］.Journal of Remote Sensing,2003,7(1):37-40,82.］ ［18］XIAO J,SHEN Y,RYUTARO T,et al.Detection of land desertification and topsoil grain size using remote sensing［J］.IEEE,2005,3(2):581-589. ［19］吴宏安,蒋建军,张海龙,等.比值居民地指数在城镇信息提取中的应用［J］.南京师大学报(自然科学版),2006,29(3):118-121.［WU Hong'an,JIANG Jianjun,ZHANG Hailong,et al.Application of ratio resident area Index to retrieve urban residential areas based on Landsat TM data［J］.Journal of NanJing Normal University (Natural Science),2006,29(3):118-121.］ ［20］苏晓玉,甘甫平,万里飞,等.辅以波谱分析的高分辨率影像面向对象分类研究［J］.图学学报,2012,3(1):73-79.［SU Xiaoyu,GAN Fuping,WAN Lifei,et al.The object-oriented classification of high resolution images with spectrum analysis［J］.Journal of Graphics,2012,3(1):73-79.］
Options
文章导航

/

〈 〉