基于点序列和要素加权法的地图匹配算法

摘要

浮动车数据(Floating Car Data,FCD)已广泛应用于城市规划、智能交通系统中,其中地图匹配一直以来都是浮动车数据应用的技术难点.本文在已有地图匹配算法的基础上,提出了基于点序列和要素加权法的地图匹配模型,不仅考虑了当前GPS点的信息,同时也考虑了GPS数据的历史信息和道路网的拓扑结构,从空间关系上分析车辆行驶轨迹和道路的相似性.作者通过上海市出租车轨迹数据对算法进行验证,结果表明:该匹配模型解决了已有地图匹配算法的一些弊端,并且提高了地图匹配的精度,具有高效、实用的特点.%Floating Car Data(FCD) has been widely used in urban planning and intelligent transportation systems.Map matching is a key problem of application of FCD.Based on the existing map matching algorithms,we propose a point-sequence and weight-based map matching model.The method not only takes the current information of GPS data into account, but also considers the prior information of GPS data and the topological structure of the road network, which allows us to analyze the similarity between vehicle trajectory and roads from the spatial relationship.The algorithm is validated by the taxi trajectory data in Shanghai.The results show that this method can improve the precision of map matching and is more effective and practical than current weight-based map matching algorithms.