基于浮动车轨迹数据的城市路网提取  

Urban road network extraction based on floating car data

作　　者：王冬[1] 张焱 姜俊奎 WANG Dong;ZHANG Yan;JIANG Junkui(College of Geomatics,Shandong University of Science and Technology,Qingdao,Shandong 266590,China)

机构地区：[1]山东科技大学测绘科学与工程学院,山东青岛266590

出　　处：《中国科技论文》2019年第2期226-231,共6页China Sciencepaper

基　　金：国家自然科学基金资助项目(41271451;41371425);山东省优秀中青年科学家科研奖励基金资助项目(BS2012DX033)

摘　　要：为满足数字道路信息的及时获取和快速更新,提出了一种基于浮动车轨迹数据的城市路网提取方法。首先通过去冗、滤波等轨迹数据预处理算法优化轨迹信息,然后近似计算轨迹点对应时刻的车辆航向角,通过航向角提取出处于转向状态的浮动车轨迹点,利用改进的DBSCAN聚类算法对转向点聚类提取道路交叉口,最后以交叉口之间的轨迹点为数据源,利用多元自适应回归样条算法拟合道路中心线。以成都市1d内的出租车GPS轨迹数据作为数据源进行了实验,结果显示路网提取效果良好,验证了本文方法的有效性。With the development of infrastructure construction,the road network structure of our country is rapidly and dynamically changing.In order to timely obtain and update the digital road information,a method of urban road network extraction based on floating car data was proposed.Firstly,the trajectory information was optimized by preprocessing the GPS trajectory data,such as redundant data processing and noise filtering.Then the vehicle heading angle corresponded to trajectory point can be approximately calculated.The floating car track point in the steering state can also be extracted and the improved DBSCAN clustering algorithm can be used to extract road intersections.Finally,the trajectory points between the intersections were used as the data sources and the road centerline was fitted by multiple adaptive regression spline algorithms.In order to verify the effectiveness of the method,the data of GPS vehicle trajectories of 1 day in Chengdu were used as the data source.The road network extraction effect was proved to be good,which verified the effectiveness of the method.

关 键 词：工程测量技术 浮动车数据 GPS轨迹 路网提取 轨迹点滤波 多元自适应回归样条 DBSCAN聚类 

分 类 号：P208[天文地球—地图制图学与地理信息工程]