多源点要素的全局一致性自动匹配  

Automated Matching of Point Features from Different Sources Based on Global Consistent Optimization

作　　者：刘继宝 赵东保[2] 

机构地区：[1]西安煤航信息产业有限公司测绘工程分公司,西安陕西710054 [2]华北水利水电学院资源与环境学院,郑州河南450011

出　　处：《测绘与空间地理信息》2011年第3期27-29,32,共4页Geomatics & Spatial Information Technology

基　　金：国家自然科学基金(40901200);华北水利水电学院引进高层次人才科研启动项目(001320)资助

摘　　要：多源点要素的自动匹配是空间数据集成与融合的重要基础性工作。本文通过计算点要素的匹配可信度指标,建立点要素的一致性优化匹配模型,并转化为二分图最大带权匹配问题,从而实现了多源点要素的全局一致性匹配,其匹配结果更好地顾及了所有匹配要素相互之间的一致性和相似性。实验表明:相比传统方法,本文方法具有较高的匹配准确率,能够适应更为复杂的情况。Automated matching of point features from different sources plays an important role in spatial data integration and fusion.Aiming at the problem that existing methods match homonymous features by means of strategy of finding optimal solution locally,which will cause mismatch often occurs when homonymous road features differ greatly in their locations,so in order to solve such a problem,this paper constructs global optimization model of matching road network through analyzing matching confidence of point features and the optimal solution is found by solving perfect matching with weights of bipartite graph.Many experiments indicate that our method can ensure that matching results agree with each other globally,and has a higher accuracy as a result.

关 键 词：点要素匹配 地图合并 空间数据集成 

分 类 号：TP311.12[自动化与计算机技术—计算机软件与理论]