Intersection vehicle trajectory reconstruction method based on fixed-point detection and electric police data fusion

Abstract

The invention provides an intersection vehicle trajectory reconstruction method based on data fusion from the electric police and a fixed-point detector. The method comprises: long queuing identification is carried out, wherein the long queuing means that the queuing length exceeds the detector position; upstream-downstream lane flow mapping is carried out; and intersection vehicle trajectory reconstruction is carried out based on a traffic wave theory. When the queuing length is close to the detector, the detector occupancy rate increases and the passing vehicle number is reduced; and the long queue is identified based on fixed-point detection data of the section based on changing characteristics of the flow and occupation rate. According to the invention, the intersection vehicle trajectory reconstruction method has the following beneficial effects: the method is based on detection conditions of most of cities in the country and the 60s-aggregate flowing density and speed data and detection frequency are provided, so that the dependence on the high-frequency floating car trajectory data is eliminated.

Description

technical field [0001] The invention belongs to the field of traffic information, and in particular relates to a vehicle track reconstruction method at an intersection based on data fusion of electric police and fixed-point detectors. Background technique [0002] Vehicle trajectories are the most comprehensive and complete expression of traffic flow operation status, and contain rich traffic flow information. The vehicle trajectory at the intersection refers to the complete physical trajectory of the vehicle in the process of driving at the intersection, which can reflect the characteristics of vehicle speed and acceleration with time and space. Reconstructing vehicle trajectories near intersections can comprehensively and accurately reproduce the running rules of vehicles passing through intersections, thereby improving the accuracy of estimation and prediction of traffic state parameters (such as travel speed, travel time, queue length, delay, etc.) and traffic signals c...

AI Technical Summary

Problems solved by technology

[0003] In recent years, my country's traffic informatization has developed rapidly, and the urban road data environment has become more and more perfect; but at the current stage, most cities still have problems such as very limited penetration of floating vehicles and low sampling frequency (generally 30-120s)

Images