地理国情监测数据变化信息自动识别方法研究  

Research on Automatic Identification of Change Information in Geographic National Condition Data

作　　者：王玮[1] WANG Wei(Jiangsu Geomatics Center,Nanjing 210013,China)

机构地区：[1]江苏省基础地理信息中心

出　　处：《测绘与空间地理信息》2019年第11期42-45,共4页Geomatics & Spatial Information Technology

基　　金：江苏省测绘科研项目(JSCHKY201813)资助

摘　　要：变化信息识别是地理国情监测数据处理中的一项重要内容,为提高其识别效率,降低人工误判率,本文提出了一种基于叠置分析和几何约束的变化信息自动识别方法。首先,对本底数据和监测数据进行数据预处理;然后,根据设定的检测容差进行叠置分析;最后根据空间数据的类型,结合变化信息填写规则,分别进行点、线、面要素变化信息的自动识别。本项技术成果已成功应用于2017年基础性地理国情监测的实际生产中,地表覆盖分类数据变化信息自动识别正确率达99%以上,地理国情要素数据变化信息自动识别正确率达85%以上。Identifying in change information is an important content in the processing of geographic condition national monitoring data.In order to improve its filing efficiency and reduce the false positive rate,this paper proposed a method of automatically identifying change information based on overlay analysis and geometric constraint.First,the background data and monitoring data was used for data preprocessing.Then according to the pre-determined test tolerance,it needed to overlay analysis.On this basis,the automatic change detection of point,line and surface element was carried out according to the type of spatial data and the rules of changing information.This technical achievement has been successfully applied to the actual production of basic geographical national conditions in 2017.The results show that the accuracy of identifying the change information of land cover classification automatically is more than 99%,and the accuracy of identifying the information of geographical national conditions is more than 85%.

关 键 词：地理国情 变化信息 检测容差 叠置分析 

分 类 号：P208[天文地球—地图制图学与地理信息工程]