A method of extracting road intersections using low frequency trajectory data

doi:10.13474/j.cnki.11-2246.2023.0021

Abstract

Abstract: In order to extract urban road intersections using low-frequency trajectory data, this paper designs a precise identification method of road intersections based on data preprocessing and clustering algorithm. Firstly, combined with the characteristics of the trajectory data, a heuristic filtering algorithm is used to clean the original data and eliminate redundant points and abnormal points. Then, according to the running rules of vehicles, a step by step algorithm for extracting road intersections is proposed to calculate the characteristic points of suspected road intersections. Finally, hierarchical density clustering algorithm (HDBSCAN) is used to cluster the selected track points and extract the centroid, which is the intersection of the road. Based on the data source of taxi driving track in Chengdu, the results show that,the algorithm can extract the intersection with an accuracy of 95.33%, a recall of 82.11% and F value of 88.46%. It can effectively and accurately identify the urban road intersection information, and has a certain application value in urban administration and traffic planning.

Key words: road intersection, turning point, convergence point, HDBSCAN, kernel density estimation, heuristic filtering

CLC Number:

P208

CHEN Weiliang, DU Jiusheng. A method of extracting road intersections using low frequency trajectory data[J]. Bulletin of Surveying and Mapping, 2023, 0(1): 127-133.

References

[1] 傅罡. 多源遥感数据的道路提取方法研究[D]. 北京:清华大学, 2014.
[2] HU Xiangyun,LI Yijing,SHAN Jie,et al. Road centerline extraction in complex urban scenes from LiDAR data based on multiple features[J]. IEEE Transactions on Geoscience and Remote Sensing,2014,52(11):7448-7456.
[3] 郭风成,李参海,李宗春,等. 高分辨率SAR影像道路交叉口自动提取方法[J]. 测绘科学技术学报,2017,34(2):199-203.
[4] WORRALL S,NEBOT E. Automated process for generating digitised maps through GPS data compression[C]//Proceedings of Australasian Conference on Robotics and Automation.Brisbane:[s.n.],2007:1-6.
[5] 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.
[6] ZHANG Yongchuan,LIU Jiping,QIAN Xinlin,et al. An Automatic Road Network Construction Method Using Massive GPS Trajectory Data[J]. ISPRS International Journal of Geo-Information,2017,6(12):400.
[7] 胡瀚,向隆刚,王德浩. 出租车轨迹数据的道路提取[J]. 测绘通报,2018(7):53-57.
[8] 李思宇,向隆刚,张彩丽,等. 基于低频出租车轨迹的城市路网交叉口提取研究[J]. 地球信息科学学报,2019,21(12):1845-1854.
[9] CHEN Chen,CHENG Yinhang. Roads digital map generation with multi-track GPS data[C]//Proceedings of 2008 International Workshop on Education Technology and Training & 2008 International Workshop on Geoscience and Remote Sensing. Shanghai:IEEE,2008:508-511.
[10] DAVIES J J,BERESFORD A R,HOPPER A. Scalable,distributed,real-time map generation[J]. IEEE Pervasive Computing,2006,5(4):47-54.
[11] 吴仁哲,蔡嘉伦,刘国祥,等.针对高分影像的RDU-Net乡村路网提取方法[J].遥感信息,2021,36(1):29-36.
[12] CAO Lili,KRUMM J. From GPS traces to a routable road map[C]//Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Seattle,Washington. New York:ACM,2009:3-12.
[13] BRUNTRUP R,EDELKAMP S,JABBAR S,et al. Incremental map generation with GPS traces[C]//Proceedings of 2005 IEEE Intelligent Transportation Systems. Vienna:IEEE,2005:574-579.
[14] 刘纪平,张用川,徐胜华,等.一种顾及道路复杂度的增量路网构建方法[J].测绘学报,2019,48(4):480-488.
[15] 陆晓燕.基于公交车大数据挖掘的城市路网自动生成与实时更新算法研究[D].济南:山东大学,2015.
[16] FATHI A,KRUMM J. Detecting Road intersections from GPS traces[C]//Proceedings of the 6th International Conference on Geographic Information Science. New York:ACM Press,2010:56-69.
[17] WU Junwei,ZHU Yunlong,KU Tao,et al. Detecting Road intersections from coarse-gained GPS traces based on clustering[J]. Journal of Computers,2013,8(11):2959-2965.
[18] AHMED M,WENK C. Constructing street networks from GPStrajectories[M]//Algorithms-ESA 2012. Berlin,Heidelberg:Springer,2012:60-71.