基于交通大数据的公交线路OD矩阵推断方法  

An Inference Method of Public Transit OD Matrix Based on Traffic Big Data

作　　者：胡继华[1,2] 高立晓[1,2] 梁嘉贤 

机构地区：[1]中山大学智能交通研究中心 [2]广东省智能交通系统重点实验室,广州510006

出　　处：《科学技术与工程》2017年第11期309-314,共6页Science Technology and Engineering

基　　金：国家自然科学基金(41271181);广东省科技计划项目(2015B010110005)资助

摘　　要：随着交通大数据的普及与广泛应用,提出了一种推断多模式交通网络线路OD矩阵的方法。首先,通过匹配乘客的刷卡数据和公交车辆报站数据获得乘客的上车站点,其次结合地铁刷卡数据准确分析乘客的下车站点,最后根据乘客的出行信息获得线路OD矩阵。利用广州一天近800万刷卡数据和600万公交报站数据进行了上车站点、下车站点以及OD矩阵的推断,结果表明:早高峰与全日出行规律一致;广州交通方式呈现多样化等。提出的方法可以更为准确地获得线路OD矩阵,揭示城市交通特点,具有较高的实用价值。With the popularity and broaden application of traffic big data, a method to infer the route OD matrix in multi-modal transit network is proposed. Firstly, the boarding stations of the passengers can be obtained by matching the IC card data with bus stop data recorded in the process of bus running. Then,the destination of the passengers can be analyzed combined with subway data. Finally, the route OD matrix are obtained according to the passengers’ travel information. The method was implemented to infer the boarding station, alighting station and the route OD matrix used eight million IC card data records and six million bus stop data records collected in Guangzhou, China. The results show that the travel rule in the day is in line with that in morning peak period; the modes of transportation are diversified in Guangzhou etc. The public transit route OD matrix of whole city can be obtained accurately and the urban traffic characteristics can be revealed by this method. The proposed method has high practical value.

关 键 词：智能交通 线路 OD 矩阵 出行链 交通大数据 多模式交通网络 

分 类 号：U491.1[交通运输工程—交通运输规划与管理]