基于低频GNSS轨迹的转向级城市交通信息精细预测  

Fine-grained traffic information prediction at the turning-level based on low-frequency GNSS trajectory data

作　　者：方孟元 唐炉亮[1] 杨雪[2] 胡淳 FANG Mengyuan;TANG Luliang;YANG Xue;HU Chun(State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, China)

机构地区：[1]武汉大学测绘遥感信息工程国家重点实验室,湖北武汉430079 [2]中国地质大学(武汉)地理与信息工程学院,湖北武汉430074

出　　处：《测绘学报》2021年第11期1469-1477,共9页Acta Geodaetica et Cartographica Sinica

基　　金：国家重点研发计划(2017YFB0503604,2016YFE0200400);国家自然科学基金(41971405,41671442,41901394);武大-华为空间信息技术创新实验室资助项目。

摘　　要：利用浮动车GNSS轨迹数据可以实时获取和预测城市交通状态,且覆盖范围广、部署成本低,对自动驾驶路线决策、交通拥堵治理具有重要的支撑作用。现阶段,利用浮动车GNSS轨迹数据预测的信息仅包含路段上的交通速度、状态,而忽略了交叉口内不同行驶方向上的交通流差异;且交通信息准确性受到GNSS采样频率的限制。本文提出一种基于图卷积网络和低频GNSS轨迹数据的转向级交通预测方法:首先,顾及轨迹点间车辆运动模式提出一种排队起始点估计模型;然后,基于对偶图理论构建转向连通关系的图结构;最后,基于图卷积网络提出一种顾及转向时空模式的交通预测模型。试验结果显示,本文方法能准确地获取和预测转向级交通速度、排队长度信息,交通预测准确性全面优于基准方法。The floating-car GNSS trajectory data have been widely used to obtain and predict the urban traffic status in real time,with wide coverage and low deployment cost,and the result has an important supporting role for route decision-making of automatic driving and traffic management.However,the traffic information predicted by the floating-car GNSS data only contains the traffic information on each road segment,ignoring the difference of the traffic flow in different driving directions at the intersection;besides,the accuracy of the traffic information is limited by the GNSS sampling frequency.This paper proposes a turning-level traffic prediction method based on graph convolutional network and low-frequency GNSS trajectory data:first,a queuing-starting-point estimation model is proposed considering vehicle movement pattern;second,a Graph-structure of the turning connection relationship is constructed based on the dual graph theory;finally,to consider spatio-temporal pattern,a traffic prediction model is constructed based on the graph convolutional network.The experimental results show that our method can accurately obtain and predict the traffic speed and queue length at turning-level,and effectively improve the accuracy of traffic prediction by learning the spatio-temporal pattern within the Graph.

关 键 词：GNSS轨迹 图卷积网络 数据挖掘 短时交通预测 转向级 

分 类 号：P208[天文地球—地图制图学与地理信息工程]