基于CRITIC算法的开放街道地图面实体匹配方法  

OpenStreetMap Polygon Entity Matching Method Based on CRITIC Algorithm

作　　者：刘波[1,2,3] 吴昊雄 张子厚 张黔龙 刘媛媛 廖明[3] LIU Bo;WU Haoxiong;ZHANG Zihou;ZHANG Qianlong;LIU Yuanyuan;LIAO Ming(School of Surveying,Mapping and Spatial Information Engineering,East China University of Technology,330013,Nanchang,PRC;Key Laboratory of Mine Environmental Monitoring and Control in the Ring Poyang Lake Region,Ministry of Natural Resources,330013,Nanchang,PRC;Jiangxi Province Engineering Research Center of Surveying,Mapping and Geographic Information,330209,Nanchang,PRC)

机构地区：[1]东华理工大学测绘与空间信息工程学院,南昌330013 [2]自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室,南昌330013 [3]江西省测绘地理信息工程技术研究中心,南昌330209

出　　处：《江西科学》2025年第2期363-368,共6页Jiangxi Science

基　　金：国家自然科学基金项目(42161064,42104030,42101209);江西省自然科学基金项目(20232ACB204032)。

摘　　要：为了克服开放街道地图数据的空间异质性特征对其在数据匹配、更新等方面应用所造成的影响,提出一种基于指标相关性的指标权重确定算法(Criteria Importan ce Through Inter-criteria Correlation,简称CRITIC)的开放街道地图面实体匹配方法。该方法充分考虑开放街道地图数据的空间异质性,在开放街道地图中面实体与其他数据进行匹配时,引入CRITIC算法计算开放街道地图数据中每个面要素几何相似因子的权重,避免了对匹配数据集中的所有面实体采用相同的相似因子权重,减少了人为定权方法所带来的主观性及局限性,提高了开放街道地图面实体与其他数据集的匹配精度。实验结果表明,该方法有效地克服了开放街道地图数据的空间异质性特点对匹配精度的影响,提升了开放街道地图中面实体与其他面实体数据的匹配精度,匹配的准确率、召回率和F1分数分别达到97.56%、98.04%和97.80%,均优于对比方法。In order to overcome the impact of spatial heterogeneity of developed street map data on its application in data matching and updating,the authors proposes an OpenStreetMap(OSM)surface entity matching method based on Criteria Importance Through Inter-criteria Correlation(CRITIC)algorithm.In this study,the spatial heterogeneity of OSM data is fully considered.When matching OSM surface entities with other data,the CRITIC algorithm is introduced to calculate the weight of geometric similarity factor of each surface element in OSM data,which avoids the same similarity factor weight for all surface entities in the matching data set.The subjectivity and limitation of traditional artificial weighting methods are reduced,and the matching accuracy of OSM surface entities with other data sets is improved.The experimental results show that the proposed method can effectively overcome the influence of spatial heterogeneity of OSM data on the matching accuracy,and improve the matching accuracy of OSM surface entities with other data.The matching accuracy,recall rate and F1 score reached 97.56%,98.04%and 97.80%,respectively,which were better than the comparison method.

关 键 词：CRITIC算法 开放街道地图 面实体 匹配方法 

分 类 号：P283.5[天文地球—地图制图学与地理信息工程]