[1]李雪冬,杨广斌,张旭亚,等.利用影像尺度响应进行城市扩张变化检测[J].山地学报,2014,(03):293.
　LI Xuedong,YANG Guangbin,ZHANG Xuya,et al.Application of Multiscal Segmentation to the Detection of Urban Expansion[J].Mountain Research,2014,(03):293.
点击复制

利用影像尺度响应进行城市扩张变化检测()
分享到：

《山地学报》[ISSN:1008-2186/CN:51-1516]

卷:
期数:
2014年03期
页码:
293
栏目:
山地研究
出版日期:
2014-03-01

文章信息/Info

Title:
Application of Multiscal Segmentation to the Detection of Urban Expansion
作者:
李雪冬; 杨广斌; 张旭亚; 杨兴栋; 伍 静
1.贵州师范大学地理与环境科学学院，贵州 贵阳 550001;
2.贵州山地资源与环境遥感重点实验室，贵州 贵阳 550000；
3.首都师范大学资源环境与旅游学院，北京 100100
Author(s):
LI Xuedong; YANG Guangbin; ZHANG Xuya; YANG Xingdong; WU Jing（299）
1.School of Geogray and Enviroment Sciences，Guizhou Normal University，Guiyang 550000，China；
2. Key Laboratory of Remote Sensing Application Mountain Resources and Environment，Guiyang 550000，China；
3.College of Resource Environment and Tourism，Capital Normal University，Beijing 100048，China
关键词:
尺度响应; 向量分析; ROC曲线; 隶属度函数
Keywords:
multiscal segmentation; CVA; ROC curve; Membership function
分类号:
TP75，TP79
文献标志码:
A
摘要:
在光谱直接比较的变化向量分析基础上，提出一种利用景观类型的尺度响应特征进行城市扩张的变化检测方法，该方法充分挖掘了对象的几何特征与纹理特征。首先，利用基准期与检测期影像中不同景观对象的各自拟合特征对数据进行分割，获取子对象，根据每个对象内象元光谱具有同质性的原则，对景观类型发生变化的对象通过规则进行识别，以初步提取变化范围。进而，利用ROC曲线确定最佳分界点与可疑区间范围，以对象为基本单元采用模糊函数的思想对变化区域进行精确提取。最后，以山地城市——贵阳市主城区Landsat-5 2001年和2008年的多光谱影像为数据源，对方法进行了检验。结果表明，该方法可以准确、迅速的提取城市变化范围。
Abstract:
A use of the scale of the landscape type response characteristics of urban expansion change detection method is proposed based on direct comparison of the changes in the spectral vector analysis. This method had full used geometry and texture features. First，the use of different landscape objects contemplated and features in the base period and the detection of image segmentation，crossnested and presplits get the child object，and then according to the homogeneity of the spectral clustering standard initial extraction range. Finally，use the ROC curve to determine the best cutoff point and suspicious interval range，base on member ship and the basic unit of change vector analysis method for accurate extraction of the change detection area. Use the Landsat-5 2001 and 2008 multispectral image of the main city in Guiyang City，Guizhou Province of China as data source，to do experiments to prove the feasibility of the method. The result show this method can exactly and rapidly find urban of change.

参考文献/References:

[1] Liu Zhifang，Zhang Jiping. Chang detection methods and their application in city[J]. Bulletin of Surveying and Mapping，2002，(9)：25-27 [刘直芳，张继平.变化检测方法及其在城市中的应用[J]. 测绘通报，2002，(9)：25-27]
[2] Song Cuiyu，Li Peijun，Yang Fengjie. The application of multiscale image texture to the detection of urban expansion[J]. Remote Sensing for Land & Resources 2006，9(3)：37-42[宋翠玉，李培军，杨锋杰.运用多尺度图像纹理进行城市扩展变化检测[J].国土资源遥感 2006，9(3)：37-42]
[3] Tapas R Martha，Norman Kerle，Victor Jetten，et al.Characterizing spectral，spatial and morphometric properties of landslides for semiautomatic detection using objectoriented methods[J] Geomorphology，2010，116：24-36
[4] Yashon O Oumaa，S S Josaphatb，Ryutaro Tateishib. Multiscale remote sensing data segmentation and postsegmentation change detection based on logical modeling：Theoretical exposition and experimental results for forestland cover change analysis. Computers & Geosciences，2008，34：715-737
[5] Volker Walter. Objectbased classification of remote sensing data for change detection[J].ISPRS Journal of Photogrammetry & Remote Sensing，2004，58：225-238
[6] Jesus Aguirre-Gutiérrez，Arie C Seijmonsbergen，Joost F. Duivenvoorden optimizing land cover classification accuracy for change detection，a combined pixelbased and objectbased approach in a mountainous area in Mexico[J].Applied Geography，2012，34：29-37
[7] Han Shanshan，Li Haitao，Guhaiyan. The study on land use change detection based on objectoriented analysis[J]. Remote Sensing Information，2009，(3)：23-29[韩闪闪，李海涛，顾海燕.面向对象的土地利用变化检测方法研究[J].遥感信息，2009，(3)：23-29]
[8] Wang Yan，Shu Ning，Gong Yan. A study of land use change detection based on high resolution remote sensing imanges[J]. Remote Sensing for Land & Resources，2012，(1)：43-47[王琰，舒宁，龚羹，高分辨率遥感影像土地利用变化检测方法研究[J]，国土资源遥感，2012，(1)：43-47]
[9] Jungho Im，John R Jensen.A change detection model based on neighborhood correlation image analysis and decision tree classification [J] .Remote Sensing of Environment，2005，99：326-340
[10] R V Platt a，T Schoennagel b. An objectoriented approach to assessing changes in tree cover in the Colorado Front Range 1938-1999[J].Forest Ecology and Management，2009，258：1342-1349
[11] Masroor Hussain，Dongmei Chen，Angela Cheng，et al . Change detection from remotely sensed images：from pixelbased to objectbased approaches [J]. ISPRS Journal of Photogrammetry and Remote Sensing，2013，80：91-106
[12] Chen Jin，He Chunyang，Zhou Li，Land use/cover change detection with change vector analysis (CVA)：change type determining[J]. Journal of Remote Sensing，2011，5(5)：346-352 [陈晋，何春阳，卓莉. 基于变化向量分析(CVA)的土地利用覆盖变化动态监测——变化类型的确定方法[J].遥感学报，2011，5(5)：346-352]
[13] Li Xue，Shu Ning，Wang Yan. Segmentbased land use change detection using the similarity of vector[J]. Remote Sensing Information，2009，(6)：7-11[李雪，舒宁，王琰. 利用向量相似性进行基于像斑的土地利用变化检测[J]，遥感信息，2009，(6)：7-11]
[14] Yu Huan，Zhang Shuqing，Kong Bo，et al，Optimal segmentation scale selection for objectoriented Remote Sensing Image classification[J]. Journal of Image and Graphics，2010，(2)：352-360 [于欢，张树清，孔博，等.面向对象遥感影像分类的最优分割尺度选择研究[J].中国图形图像学，2010，（2）：352-360]
[15] Chen Weizhong，Ni Zongzan，Pan Xiaoping，et al. Receiver Operating Characteristic Curves to determine the optimal operating point and doubtable value Interval[J]. Modern Preventive Medicine，2005，32(7)，729-731 [陈卫中，倪宗瓒，潘晓平，等. 用ROC 曲线确定最佳临界点和可疑值范围[J]. 现代预防医学，2005，32(7)，729-731]
[16] Goncalves H，Corte-Real L，Goncalves J A. Automatic Image Registration through image segmentation and SIFT[J]. Geoscience and remote sensing，IEEE Transactions on，2011，49：2589-2600
[17] Chen Qiuxiao，Luo JIancheng，Zhou Chenghu，et al，Classification of remotely sensed imagery using multifeatuers based approach[J]，Journal of Remote Sensing，2004,(3)：239-245 [陈秋晓，骆剑承，周成虎,等.基于多特征的遥感影像分类方法[J].遥感学报，2004，(3)：239-245]
[18] André Stumpf，Norman Kerle. Objectoriented mapping of landslides using Random Forests[J]. Remote Sensing of Environment，2011，115：2564-2577

备注/Memo

备注/Memo:
收稿日期(Received date)：2013-06-23；改回日期(Accepted): 2013-10-21。
基金项目（Foundation item）：贵州省重大专项项目（黔科合重大专项字
[2012]6007号），国家自然科学
基金项目（41361091），贵州省优秀青年科技人才培养对象专项资金项目（黔科合人字
[2013]39号）。[Guizhou Province Major Project (QJK Major Project
[2012]NO.6007)；the project of National Natural Science Fund(41361091)；the project of Guizhou Province Outstanding Youth Science and Technology Talent（QKHR
[2013]NO.39).]
作者简介（Biography）：李雪冬（1988-），男（汉），黑龙江省绥化市人，硕士研究生，主要从事地理信息系统与遥感影像分类方面的研究。[Li Xuedong(1988- ),male(Han),born in Suihua，Heilongjiang Province, master candidate, research on GIS and remote sensing image classification.] E-mail: li.xuedong.1988@163.com *
通信作者(Corresponding author)：杨广斌（1973-），男，山东聊城人，博士，教授，主要从事地理信息系统开发与应用研究。[Yang Guangbin(1973-), male(Han),born in Liaocheng, Shandong Province, Ph D，professor, research on GIS exploit and application.] E-mail: ygbyln@163.com
更新日期/Last Update: 1900-01-01