行车模式的公交站点识别方法  

A bus-stop identification method based on driving pattern

作　　者：周艳 耿二辉 李妍羲 王伟生 ZHOU Yan;GENG Erhui;LI Yanxi;WANG Weisheng(School of Resources and Environ-ment,University of Electronic Science and Technology of China,Chengdu 611731,Chinai;Big Data Research Center,University of Electronic Science and Technology of China,Chengdu 611731,China)

机构地区：[1]电子科技大学资源与环境学院,成都611731 [2]电子科技大学大数据研究中心,成都611731

出　　处：《测绘科学》2018年第10期163-167,174,共6页Science of Surveying and Mapping

基　　金：国家自然科学基金项目(41471332;41101354);国家重点研发计划项目(2016YFB0502300);中央高校基本科研业务费专项资金资助项目(ZYGX2015J113)

摘　　要：针对公交车全球定位系统(GPS)数据的公交站点识别问题,该文基于公交车辆运行状态,将公交车辆的运行划分为终点站待命模式、正常行驶模式、站点停车上/下客模式,提出了一种基于这3种行车模式的公交站点识别方法,通过行车模式判定、轨迹方向分割和DBSCAN密度聚类,提取各个方向的公交站点。该文使用深圳市公交车GPS数据展开验证,实验结果表明,该方法能有效地、准确地识别公交站点。Aiming at the problem of bus-stop identification using global position system（GPS）data,a bus-stop identification method based on driving pattern was proposed,in which three driving patterns of buses including terminal station pattern（T pattern）,normal movement pattern（N pattern）and stop for pick up or drop off passenger pattern（S pattern）were defined,and then bus-stops with different directions were identified by judging driving pattern based on the clustering features of GPS data,segmenting GPS trajectories into splits with uplink or downlink direction,and extracting bus-stops using density-based spatial clustering of application with noise（DBSCAN）clustering algorithm.Using GPS data from Shenzhen bus system to evaluate our method,the experimental results showed that the proposed method improved the effectiveness and accuracy of bus-stop identification.

关 键 词：公交车GPS数据 行车模式 公交站点识别 DBSCAN 

分 类 号：P208[天文地球—地图制图学与地理信息工程] U491[天文地球—测绘科学与技术]