Arterial road path flow estimation method based on fusion of electric police data and sampled trajectory data

Abstract

The invention relates to a method for estimating the path flow of a trunk road by combining electric police data and sampling trajectory data, comprising the following steps: 1) obtaining the sampling trajectory data on the trunk road and the electric police data at the intersections at both ends of the trunk road, and dividing the trunk road path into three Classes: the first class is the vehicle route with completely known route information, the second class is the vehicle route with partially known information, and the third class is the vehicle route with completely unknown route information; 2) Estimating the missed detection rate of electric police and sampling trajectory Data penetration rate; 3) Establish a particle filter model to reconstruct the routes of the second and third types of vehicles from the micro level and obtain the path flow; 4) Establish a generalized least squares model to estimate the second and third types of vehicles from the macro level The path flow of the vehicle path; 5) Construct a hybrid model, and iteratively optimize the particle filter sub-model and the generalized least squares sub-model to obtain the optimal estimated value. Compared with the prior art, the present invention has the advantages of low scene requirement, high effectiveness, wide applicability and the like.

Description

technical field [0001] The invention relates to the field of traffic information, in particular to a method for estimating the path flow of an arterial road by fusing electric police data and sampled trajectory data. Background technique [0002] Urban arterial roads are the backbone of the urban road network, which undertake most of the long-distance and rapid traffic in the city, which will significantly affect the traffic operation efficiency of the city. Arterial path flow reveals the dynamic travel demand of travelers, thus providing input for traffic simulation system, traffic demand management, dynamic traffic management and even signal coordination control. With the rapid development of information technology, the detection equipment in the urban road network is increasing day by day, which provides more and more data sources for the research of urban traffic. Therefore, it is a feasible method to reversely deduce the path flow of arterial roads based on the data in...

AI Technical Summary

Problems solved by technology

Among them, the analytical model cannot truly reflect the driver's route selection behavior in the road network, and this type of model is highly dependent on prior information, which limits the portability of this type of model; the probability model aims to Identify the real path of the vehicle from some data with high uncertainty, so it has a high requirement for detector coverage; the machine learning model is a model that has received attention in recent years, and the model requires a large number of training samples and real paths traffic, but these data are difficult to obtain, so this type of model also has certain limitations

In terms of data conditions, some studies discuss the method of path flow estimation using a single data source such as coil data, electric police data, or traditional taxi floating car trajectory data. Path flow estimation methods based on multi-source data sources such as vehicle trajectory data, but there are few existing studies on the fusion of electric police data and vehicle trajectory data

Images