基于浮动车轨迹数据的城市路网提取
|
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.
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.
引文
[1]吴涛,向隆刚,龚健雅.路网更新的轨迹-地图匹配方法[J].测绘学报,2017,46(4):507-515.WU Tao,XIANG Longgang,GONG Jianya.Renewal of road networks using map-matching technique of trajectories[J].Acta Geodaetica et Cartographica Sinica,2017,46(4):507-515.(in Chinese)
[2]GUO Tao,IWAMURA K,KOGA M.Towards high accuracy road maps generation from massive GPS traces date[C]∥Proceedings of IEEE International Geoscience and Remote Sensing Symposium.Barcelona:IEEE,2007:667-670.
[3]SCHROEDL S,WAGSTAFF K,ROGERS S,et al.Mining GPS traces for map refinement[J].Data Mining and Knowledge Discovery,2004,9(1):59-87.
[4]ZHANG Lijuan,THIEMANN F,SESTER M.Integration of GPS traces with road map[C]∥Proceedings of the 3rd International workshop on Computational Transportation Science.New York:ACM,2010:17-22.
[5]蒋益娟,李响,李小杰,等.利用车辆轨迹数据提取道路网络的几何特征与精度分析[J].地球信息科学学报,2012,14(2):165-170.JIANG Yijuan,LI Xiang,LI Xiaojie,et al.Geometrical characteristics extraction and accuracy analysis of road network based on vehicle trajectory data[J].Journal of Geo-Information Science,2012,14(2):165-170.(in Chinese)
[6]毕硕本,万蕾,杨树亮,等.基于GPS数据的南京出租车上下客时间特征及热点时空分布[J].中国科技论文,2018,13(9):1023-1028.BI Shuoben,WAN Lei,YANG Shuliang,et al.Spatial-temporal distribution of the pick-up and drop-off of taxi passengers in Nanjing based on GPS data[J].China Sciencepaper,2018,13(9):1023-1028.(in Chinese)
[7]欧阳鸿,刘建勋,刘毅志,等.基于步行GPS轨迹的路网提取方法[J].计算机与现代化,2014(2):124-128.OUYANG Hong,LIU Jianxun,LIU Yizhi,et al.An extraction method of road network based on walking GPS trajectories[J].Computer and Modernization,2014(2):124-128.(in Chinese)
[8]王德浩.基于低频出租车GPS轨迹数据的路网信息提取[D].武汉:武汉大学,2017.WANG Dehao.Generation of road network information from massive less frequent GPS vehicle trajectories[D].Wuhan:Wuhan University,2017.(in Chinese)
[9]李清泉,黄练.基于GPS轨迹数据的地图匹配算法[J].测绘学报,2010,39(2):207-212.LI Qingquan,HUANG Lian.A map matching algorithm for GPS tracking data[J].Acta Geodaetica et Cartographica Sinica,2010,39(2):207-212.(in Chinese)
[10]唐炉亮,牛乐,杨雪,等.利用轨迹大数据进行城市道路交叉口识别及结构提取[J].测绘学报,2017,46(6):770-779.TANG Luliang,NIU Le,YANG Xue.Urban intersection recognition and construction based on big trace data[J].Acta Geodaetica et Cartographica Sinica,2017,46(6):770-779.(in Chinese)
[11]LI Pengfei,SOULEYRETTE R R.A generic approach to estimate freeway traffic time using vehicle ID-matching technologies[J].Computer-Aided Civil and Infrastructure Engineering,2016,31(5):351-365.
[12]ESTER M,KRIEGEL H P,SANDER J,et al.A density-based algorithm for discovering clusters in large spatial databases with noise[C]∥Proceeding of the second International Conference on Knowledge Discovery and Date Mining.Portland:AAAI Press,1996:226-231.
[13]韩利钊,钱雪忠,罗倩,等.基于区域划分的DBSCAN多密度聚类算法[J].计算机应用研究,2018,35(6):1668-1671.HAN Lizhao,QIAN Xuezhong,LUO Qian,et al.Multi-density clustering algorithm DBSCAN based on region division[J].Application Research of Computers,2018,35(6):1668-1671.(in Chinese)
[14]FRIEDMAN J H.Multivariate adaptive regression splines[J].The Annals of Statistics,1991,19(1):1-67.
[15]张秀敏,南卓铜,吴吉春,等.基于多元自适应回归样条的青藏高原温泉冻土分布制图[J].冰川冻土,2011,33(5):1088-1097.ZHANG Xiumin,NAN Zhuotong,WU Jichun,et al.Modeling permafrost distribution in wenquan area over Qinghai-Tibet plateau by using multivariate adaptive regression splines[J].Journal of Glaciology and Geocryology,2011,33(5):1088-1097.(in Chinese)
[16]中华人民共和国住房和城乡建设部.CJJ 37-2012.城市道路工程设计规范[S].北京:中国建筑工业出版社,2012.Ministry of Housing and Urban and Rural Construction in People’s Republic of China.CJJ 37-2012.Code for design of urban road engineering[S].Beijing:China Architecture&Building Press,2012.(in Chinese)
[2]GUO Tao,IWAMURA K,KOGA M.Towards high accuracy road maps generation from massive GPS traces date[C]∥Proceedings of IEEE International Geoscience and Remote Sensing Symposium.Barcelona:IEEE,2007:667-670.
[3]SCHROEDL S,WAGSTAFF K,ROGERS S,et al.Mining GPS traces for map refinement[J].Data Mining and Knowledge Discovery,2004,9(1):59-87.
[4]ZHANG Lijuan,THIEMANN F,SESTER M.Integration of GPS traces with road map[C]∥Proceedings of the 3rd International workshop on Computational Transportation Science.New York:ACM,2010:17-22.
[5]蒋益娟,李响,李小杰,等.利用车辆轨迹数据提取道路网络的几何特征与精度分析[J].地球信息科学学报,2012,14(2):165-170.JIANG Yijuan,LI Xiang,LI Xiaojie,et al.Geometrical characteristics extraction and accuracy analysis of road network based on vehicle trajectory data[J].Journal of Geo-Information Science,2012,14(2):165-170.(in Chinese)
[6]毕硕本,万蕾,杨树亮,等.基于GPS数据的南京出租车上下客时间特征及热点时空分布[J].中国科技论文,2018,13(9):1023-1028.BI Shuoben,WAN Lei,YANG Shuliang,et al.Spatial-temporal distribution of the pick-up and drop-off of taxi passengers in Nanjing based on GPS data[J].China Sciencepaper,2018,13(9):1023-1028.(in Chinese)
[7]欧阳鸿,刘建勋,刘毅志,等.基于步行GPS轨迹的路网提取方法[J].计算机与现代化,2014(2):124-128.OUYANG Hong,LIU Jianxun,LIU Yizhi,et al.An extraction method of road network based on walking GPS trajectories[J].Computer and Modernization,2014(2):124-128.(in Chinese)
[8]王德浩.基于低频出租车GPS轨迹数据的路网信息提取[D].武汉:武汉大学,2017.WANG Dehao.Generation of road network information from massive less frequent GPS vehicle trajectories[D].Wuhan:Wuhan University,2017.(in Chinese)
[9]李清泉,黄练.基于GPS轨迹数据的地图匹配算法[J].测绘学报,2010,39(2):207-212.LI Qingquan,HUANG Lian.A map matching algorithm for GPS tracking data[J].Acta Geodaetica et Cartographica Sinica,2010,39(2):207-212.(in Chinese)
[10]唐炉亮,牛乐,杨雪,等.利用轨迹大数据进行城市道路交叉口识别及结构提取[J].测绘学报,2017,46(6):770-779.TANG Luliang,NIU Le,YANG Xue.Urban intersection recognition and construction based on big trace data[J].Acta Geodaetica et Cartographica Sinica,2017,46(6):770-779.(in Chinese)
[11]LI Pengfei,SOULEYRETTE R R.A generic approach to estimate freeway traffic time using vehicle ID-matching technologies[J].Computer-Aided Civil and Infrastructure Engineering,2016,31(5):351-365.
[12]ESTER M,KRIEGEL H P,SANDER J,et al.A density-based algorithm for discovering clusters in large spatial databases with noise[C]∥Proceeding of the second International Conference on Knowledge Discovery and Date Mining.Portland:AAAI Press,1996:226-231.
[13]韩利钊,钱雪忠,罗倩,等.基于区域划分的DBSCAN多密度聚类算法[J].计算机应用研究,2018,35(6):1668-1671.HAN Lizhao,QIAN Xuezhong,LUO Qian,et al.Multi-density clustering algorithm DBSCAN based on region division[J].Application Research of Computers,2018,35(6):1668-1671.(in Chinese)
[14]FRIEDMAN J H.Multivariate adaptive regression splines[J].The Annals of Statistics,1991,19(1):1-67.
[15]张秀敏,南卓铜,吴吉春,等.基于多元自适应回归样条的青藏高原温泉冻土分布制图[J].冰川冻土,2011,33(5):1088-1097.ZHANG Xiumin,NAN Zhuotong,WU Jichun,et al.Modeling permafrost distribution in wenquan area over Qinghai-Tibet plateau by using multivariate adaptive regression splines[J].Journal of Glaciology and Geocryology,2011,33(5):1088-1097.(in Chinese)
[16]中华人民共和国住房和城乡建设部.CJJ 37-2012.城市道路工程设计规范[S].北京:中国建筑工业出版社,2012.Ministry of Housing and Urban and Rural Construction in People’s Republic of China.CJJ 37-2012.Code for design of urban road engineering[S].Beijing:China Architecture&Building Press,2012.(in Chinese)