基于浮动车轨迹数据的路网快速提取
|
摘要
浮动车轨迹数据包含丰富的路网信息,随着浮动车轨迹数据的逐渐公开,从中提取路网信息已成为可能。目前,大多数算法提取路网时,使用统一的阈值忽略了轨迹数据的密度差异,且只考虑了轨迹的形态没有考虑轨迹的方向,严重影响了提取结果的几何精确度和拓扑正确度。为此,该文提出了一种自适应半径质心漂移聚类方法,能根据轨迹密度、道路宽度自动调整聚类参数和利用轨迹方向实现道路拓扑连接。首先,通过自适应半径质心漂移聚类方法计算路网骨架点,采用小波聚类算法获取路网骨架点的方向集;然后,根据聚类半径和方向对骨架点进行递归连接,生成路网数据。利用深圳市福田区一天的浮动车轨迹数据进行了算法实验验证,将实验结果与栅格化方法、约束三角网方法的结果进行了定性定量评价分析。实验结果表明,该文算法提取的路网数据在几何精确度及拓扑正确度上都有明显的提高,且算法适合大数据处理。
Floating vehicle trajectory data contains abundant road network information.With the gradual opening of floating vehicle trajectory data,it is possible to extract road network information from it.Currently,most road network extraction algorithms use unified thresholds to ignore the density difference of trajectory data,and only consider the trajectory shape without considering the direction of the trajectory,which seriously affects the geometric precision and topological accuracy of their results.Therefore,an adaptive radius centroid drift clustering method is proposed in this paper,which can automatically adjust clustering parameters according to the track density and the road width,using trajectory direction to complete the topological connection of roads.Firstly,the skeleton points of road network are calculated by adaptive radius centroid drift clustering method,and the direction sets of skeleton points are obtained by wavecluster algorithm.Then,the skeleton points are recursively connected based on clustering radius and direction to generate road network data.The algorithm is verified by the floating vehicle trajectory data of a day in Futian District,Shenzhen.The experimental results are qualitatively and quantitatively analyzed with ones of the raster method and the constrained triangulation method.It indicates that the road network data extracted by this algorithm has a significant improvement in geometric precision and topological accuracy,and which is suitable for large data processing.
Floating vehicle trajectory data contains abundant road network information.With the gradual opening of floating vehicle trajectory data,it is possible to extract road network information from it.Currently,most road network extraction algorithms use unified thresholds to ignore the density difference of trajectory data,and only consider the trajectory shape without considering the direction of the trajectory,which seriously affects the geometric precision and topological accuracy of their results.Therefore,an adaptive radius centroid drift clustering method is proposed in this paper,which can automatically adjust clustering parameters according to the track density and the road width,using trajectory direction to complete the topological connection of roads.Firstly,the skeleton points of road network are calculated by adaptive radius centroid drift clustering method,and the direction sets of skeleton points are obtained by wavecluster algorithm.Then,the skeleton points are recursively connected based on clustering radius and direction to generate road network data.The algorithm is verified by the floating vehicle trajectory data of a day in Futian District,Shenzhen.The experimental results are qualitatively and quantitatively analyzed with ones of the raster method and the constrained triangulation method.It indicates that the road network data extracted by this algorithm has a significant improvement in geometric precision and topological accuracy,and which is suitable for large data processing.
引文
[1] EDELKAMP S,SCHRDL S.Route planning and map inference with global positioning traces[J].Lecture Notes in Computer Science,2003,2598(1):128-151.
[2]WORRALL S,NEBOT E.Automated process for generating digitised maps through GPS data compression[A].Proceedings of the 2007 Australasian Conference on Robotics&Automation[C].Brisbane:ACRA,2007.106-111.
[3] GUO T,IWAMURA K,KOGA M.Towards high accuracy road maps generation from massive GPS traces data[A].2007IEEE International Geoscience and Remote Sensing Symposium[C].Barcelona:IEEE,2007.667-670.
[4] ZHANG L,THIEMANN F,SESTER M.Integration of GPS traces with road map[A].IWCTS′10Proceedings of the Third International Workshop on Computational Transportation Science[C].New York,USA:ACM,2010.17-22.
[5] DAVIES J J,BERESFORD A R,HOPPER A.Scalable,distributed,real-time map generation[J].Ieee Pervas Comput,2006,5(4):47-54.
[6] CHEN C,CHENG Y H.Roads digital map generation with multitrack GPS data[A].Education Technology and Training,2008and 2008International Workshop on Geoscience and Remote Sensing[C].Shanghai:IEEE,2008.508-511.
[7] STEINER A,LEONHARDT A.Map-Generation Algorithm Using Low-Frequency Vehicle Position Data[R].Washington DC:The National Academies of Sciences,Engineering,and Medicine,2011.486-503.
[8] JIANG Y J,LI X,LI X J,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.
[9] KUNTZSCH C,SESTER M,BRENNER C.Generative models for road network reconstruction[J].International Journal of Geographical Information Science,2016,30(5):1012-1039.
[10]赵东保,刘雪梅,张弘弢.基于大规模浮动车轨迹点数据的道路网变化检测与更新方法研究[J].地理与地理信息科学,2016,32(2):1-5.
[11] WU J W,ZHU Y L,KU T,et al.Detecting road intersections from coarse-gained GPS traces based on clustering[J].Journal of Computers,2013,8(11):2959-2965.
[12] WANG J,RUI X P,SONG X F,et al.A novel approach for generating routable road maps from vehicle GPS traces[J].International Journal of Geographical Information Science,2015,29(1):69-91.
[13]唐炉亮,刘章,杨雪,等.符合认知规律的时空轨迹融合与路网生成方法[J].测绘学报,2015,44(11):1271-1276.
[14]杨伟,艾廷华.基于众源轨迹数据的道路中心线提取[J].地理与地理信息科学,2016,32(3):1-7.
[15]杨伟,艾廷华.运用约束Delaunay三角网从众源轨迹线提取道路边界[J].测绘学报,2017,46(2):237-245.
[16] TANG L L,REN C,LIU Z,et al.A road map refinement method using Delaunay triangulation for big trace data[J].International Journal of Geo-Information,2017,6(2):45.
[17] CAO L L,KRUMM J.From GPS traces to a routable road map[A].17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems[C].New York,USA:ACM,2009.3-12.
[18] AHMED M,WENK C.Constructing street networks from GPS trajectories[A].Algorithms-ESA 2012-20th Annual European Symposium[C].Ljubljana,Slovenia:Springer,2012.60-71.
[19] KARAGIORGOU S,PFOSER D.On vehicle tracking data-based road network generation[A].Proceedings of the 20th International Conference on Advances in Geographic Information Systems[C].New York,USA:ACM,2012.89-98.
[20] KARAGIORGOU S,PFOSER D,SKOUTAS D.Segmentationbased road network construction[A].21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems[C].New York,USA:ACM,2013.460-463.
[21] LI J,QIN Q M,HAN J W,et al.Mining trajectory data and geotagged data in social media for road map inference[J].Transactions in GIS,2015,19(1):1-18.
[22] SHEIKHOLESLAMI G,CHATTERJEE S,ZHANG A.WaveCluster:A multi-resolution clustering approach for very large spatial databases[A].Proceedings of the 24th VLDB Conference[C].New York,USA:Springer-Verlag,1998.428-439.
[2]WORRALL S,NEBOT E.Automated process for generating digitised maps through GPS data compression[A].Proceedings of the 2007 Australasian Conference on Robotics&Automation[C].Brisbane:ACRA,2007.106-111.
[3] GUO T,IWAMURA K,KOGA M.Towards high accuracy road maps generation from massive GPS traces data[A].2007IEEE International Geoscience and Remote Sensing Symposium[C].Barcelona:IEEE,2007.667-670.
[4] ZHANG L,THIEMANN F,SESTER M.Integration of GPS traces with road map[A].IWCTS′10Proceedings of the Third International Workshop on Computational Transportation Science[C].New York,USA:ACM,2010.17-22.
[5] DAVIES J J,BERESFORD A R,HOPPER A.Scalable,distributed,real-time map generation[J].Ieee Pervas Comput,2006,5(4):47-54.
[6] CHEN C,CHENG Y H.Roads digital map generation with multitrack GPS data[A].Education Technology and Training,2008and 2008International Workshop on Geoscience and Remote Sensing[C].Shanghai:IEEE,2008.508-511.
[7] STEINER A,LEONHARDT A.Map-Generation Algorithm Using Low-Frequency Vehicle Position Data[R].Washington DC:The National Academies of Sciences,Engineering,and Medicine,2011.486-503.
[8] JIANG Y J,LI X,LI X J,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.
[9] KUNTZSCH C,SESTER M,BRENNER C.Generative models for road network reconstruction[J].International Journal of Geographical Information Science,2016,30(5):1012-1039.
[10]赵东保,刘雪梅,张弘弢.基于大规模浮动车轨迹点数据的道路网变化检测与更新方法研究[J].地理与地理信息科学,2016,32(2):1-5.
[11] WU J W,ZHU Y L,KU T,et al.Detecting road intersections from coarse-gained GPS traces based on clustering[J].Journal of Computers,2013,8(11):2959-2965.
[12] WANG J,RUI X P,SONG X F,et al.A novel approach for generating routable road maps from vehicle GPS traces[J].International Journal of Geographical Information Science,2015,29(1):69-91.
[13]唐炉亮,刘章,杨雪,等.符合认知规律的时空轨迹融合与路网生成方法[J].测绘学报,2015,44(11):1271-1276.
[14]杨伟,艾廷华.基于众源轨迹数据的道路中心线提取[J].地理与地理信息科学,2016,32(3):1-7.
[15]杨伟,艾廷华.运用约束Delaunay三角网从众源轨迹线提取道路边界[J].测绘学报,2017,46(2):237-245.
[16] TANG L L,REN C,LIU Z,et al.A road map refinement method using Delaunay triangulation for big trace data[J].International Journal of Geo-Information,2017,6(2):45.
[17] CAO L L,KRUMM J.From GPS traces to a routable road map[A].17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems[C].New York,USA:ACM,2009.3-12.
[18] AHMED M,WENK C.Constructing street networks from GPS trajectories[A].Algorithms-ESA 2012-20th Annual European Symposium[C].Ljubljana,Slovenia:Springer,2012.60-71.
[19] KARAGIORGOU S,PFOSER D.On vehicle tracking data-based road network generation[A].Proceedings of the 20th International Conference on Advances in Geographic Information Systems[C].New York,USA:ACM,2012.89-98.
[20] KARAGIORGOU S,PFOSER D,SKOUTAS D.Segmentationbased road network construction[A].21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems[C].New York,USA:ACM,2013.460-463.
[21] LI J,QIN Q M,HAN J W,et al.Mining trajectory data and geotagged data in social media for road map inference[J].Transactions in GIS,2015,19(1):1-18.
[22] SHEIKHOLESLAMI G,CHATTERJEE S,ZHANG A.WaveCluster:A multi-resolution clustering approach for very large spatial databases[A].Proceedings of the 24th VLDB Conference[C].New York,USA:Springer-Verlag,1998.428-439.