面向复杂路网低频GPS采样数据新型地图匹配算法

Novel map-matching algorithm based on low-frequency GPS sampling data in complex road networks

大数据时代低频采样交通轨迹数据呈指数级增长,准确、高效地对复杂路网中产生的海量低频浮动车数据进行地图匹配对出租车载客热点和路线推荐具有重要意义。基于上述考虑,提出了一种基于曲线拟合的改进算法,对缺失的轨迹数据和路网数据分别使用插值和均值化的方法进行补全,利用Geohash技术对路网和轨迹数据进行存储和搜索,充分考虑车辆速度和道路限速因素,使用轨迹点后向向量和路段向量对路候选段进行分析,设计综合评价函数得到最优匹配结果。实验结果表明,与传统垂直投影算法和曲线拟合算法进行对比,所提曲线拟合算法准确率较高,时间效率得到显著提升。

The number of low-frequency sampling traffic trajectory data is growing explosively in big data era.Map matching techniques play an essential role in taxi pick-up hotspot and route recommendation,which can help accurately and efficiently matching low-frequency floating car data from complex road networks.In view of the aforementioned discussion,this paper proposed an improved algorithm based on curve fitting.This algorithm filled missing trajectory data and road network data by interpolation and mean methods,employed Geohash technology to store and search road network data and trajectory data,took into full consideration the factors of the speed of vehicles and road speed limit,used the backward vector of trajectory point and road segment vector to analyze the candidate road segments,and designed a comprehensive evaluation function to obtain the optimal matching results.The experimental results show that the proposed curve-fitting algorithm has a higher matching accuracy and faster time efficiency when compared with the traditional vertical projection and curve-fitting algorithms.