摘要
提出并实现了一种基于手机定位轨迹数据的出行行程识别方法.通过速度对轨迹点进行划分,将低于一定速度阈值以下的轨迹点合并为候选停留位置,再利用距离阈值和时间阈值对候选停留位置进行合并,从而确定出真正的停留点,继而自动统计出行次数和出行时间.该方法解决了手机定位数据的定位漂移和抖动的问题,行程识别精度高,识别结果可为交通规划工作提供相关数据,并具有比传统交通调查方法更低的成本和更短的数据更新周期.
A method to identify trip based on the mobile phone positioning data is proposed and implemented.According to their speed the track points are divided into two types,and these lower than a certain speed are merged to candidate stay position.In order to determine these real stay point,the distance threshold and time threshold are used to merge stay position,and then automatic statistics of travel times and travel time is followed.The method resolve the drift and jitter problem of mobile phone positioning data,and has high identification accuracy.The recognition results can provide relevant data for transportation planning,and has lower cost and shorter data update cycle than traditional traffic survey methods.
出处
《武汉理工大学学报（交通科学与工程版）》
2013年第5期934-938,共5页
Journal of Wuhan University of Technology（Transportation Science & Engineering）
基金
现代城市测绘国家测绘地理信息局重点实验室开放基金项目(批准号:20111216N)
北京市教育委员会科技发展计划项目(批准号:KM201210016014)
北京市优秀人才培养资助个人项目(批准号:2011D005017000005)
北京建筑工程学院博士科研启动基金项目(批准号:Z10044
Z09074)资助
关键词
手机定位
时空数据挖掘
行程识别
出行调查
交通GIS
mobile phone positioning
spatial-time data mining
trip identification
traffic survey
GIS for transportation
