The invention relates to a trajectory data-driven signal control intersection periodic flow estimation method. The method comprises the following steps of: 1) dividing periodic flow into a known partand an unknown part according to a parking position and expected arrival time of a last queuing sampling trajectory; 2) extracting known and unknown part flow-related parameters in each period, constructing a three-dimensional tensor comprising the flow of the unknown part in each period, and converting a period flow estimation problem into a data repair problem; and 3) repairing the constructed tensor based on a tensor decomposition method to obtain the flow of each period. Compared with the prior art, the method has the advantages of trajectory data driving, high effectiveness, wide applicability and the like.
本发明涉及一种轨迹数据驱动的信控交叉口周期流量估计方法,包括以下步骤:1)根据最后一辆排队抽样轨迹的停车位置和期望到达时间将周期流量划分为已知和未知两部分;2)提取各周期内已知和未知两部分与流量相关的参数,构建包括各周期未知部分流量的三维张量,将周期流量估计问题转化为数据修补问题;3)基于张量分解方法修补构建的张量,获得各周期的流量。与现有技术相比,本发明具有轨迹数据驱动、有效性高、适用性广等优点。
Trajectory data-driven signal control intersection periodic flow estimation method
一种轨迹数据驱动的信控交叉口周期流量估计方法
2021-01-08
Patent
Elektronische Ressource
Chinesisch
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Intersection arrival rate estimation method based on sampling trajectory data
Europäisches Patentamt | 2021
|Europäisches Patentamt | 2020
|Intersection signal control and vehicle trajectory collaborative optimization method and system
Europäisches Patentamt | 2023
|Signal control intersection vehicle trajectory reconstruction method based on particle filtering
Europäisches Patentamt | 2024
|Intersection inductive signal control method based on real-time vehicle trajectory
Europäisches Patentamt | 2015
|