基于聚类算法的交叉口拓扑数据建库  

Intersection topology database constructing based on clustering algorithm

作　　者：黄敏 张汉林 张旭 张小兰[3] HUANG Min;ZHANG Han-lin;ZHANG Xu;ZHANG Xiao-lan(Guangdong Provincial Key Laboratory of Intelligent Transportation System(ITS),School of Engineering,Sun Yat-sen University,Guangzhou 510006,China;China Southern Airlines,Guangzhou 510405,China;Computer Engineering Department,Guangdong Polytechnic of Industry and Commerce,Guangzhou 510510,China)

机构地区：[1]中山大学工学院广东省智能交通系统(ITS)重点实验室,广东广州510006 [2]中国南方航空股份有限公司,广东广州510405 [3]广东工贸职业技术学院计算机工程系,广东广州510510

出　　处：《计算机工程与设计》2018年第9期2985-2991,共7页Computer Engineering and Design

基　　金：国家自然科学基金项目(11574407);广东省科技计划基金项目(2016A020223006;2016B090918038;2015B010110005)

摘　　要：为智能化提取CAD平面交叉口的拓扑数据,提出基于聚类算法的CAD平面交叉口工程图拓扑数据建库方法。对交叉口拓扑数据模型进行描述,梳理出CAD图元与拓扑数据之间的关系,通过基于密度的聚类算法进行路面标线聚类、路面标线辨识,实现拓扑数据的建库。以广州大学城某平面交叉口为例,用可视化的形式在CAD平台上展示拓扑数据建库的结果。该方法适用于平面、非渠化交叉口的拓扑数据建库。To extract the topology data from CAD planar intersections intelligently,a method of constructing topology database from CAD planar intersections based on clustering algorithm was proposed.The topology data model of intersection was described,and the relationship between CAD primitives and topology data was sorted out.DBSCAN was used to cluster marking lines and identify them.Topology database was constructed.Taking the intersection in Guangzhou Higher Education Mega Center as an example,the results of topology database constructing were shown on the platform of CAD.The proposed method is applicable to the topology database constructing of planar and non-channelized intersections.

关 键 词：聚类算法 拓扑数据 平面交叉口 计算机辅助设计 智能交通 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]