Lane Group Traffic Demand Forecasting Method Based on Data from Automatic Red Light Recording System

Abstract

The invention discloses a lane group traffic demand prediction method based on automatic red light recording system data. The method firstly obtains the road travel time by the license plate matching,secondly determines the change rate of the travel time of each cycle, then determines the duration of the virtual cycle corresponding to each cycle, and finally measures the number of pull-out vehicles of each cycle and calculates the traffic demand of the lane group. The method overcomes two types of defects based on coil detection: the inability to detect the supersaturated traffic demand or the inability to distinguish the differences between different lane groups, and provides a technical basis for the refined optimization of the signal control.

Description

technical field [0001] The invention relates to a traffic demand prediction method for a lane group, in particular to a traffic demand prediction method for a lane group based on data from an automatic recording system for running a red light, and belongs to the field of intelligent traffic research. Background technique [0002] Traffic demand is one of the basic parameters of traffic management and control. Accurate and reliable traffic demand is the premise and basis for signal optimization, which directly determines the implementation effect of the signal scheme. Existing control systems are based on fixed detection equipment, such as coil detectors, microwave detectors, video detectors, etc., to count the number of vehicles passing through a specific detection section within a unit period of time, and regard the number of vehicles as traffic demand and then use them for traffic management with control. [0003] At present, there are two types of installation locations...

AI Technical Summary

Problems solved by technology

For the first type of deployment position, the detector can actually detect the number of vehicles passing through the section per unit time, which is the real traffic demand, but it cannot identify the steering properties of these vehicles at the downstream intersection, and cannot distinguish the traffic demand of the lanes; for the second However, in the supersaturated state, some vehicles that actually arrive cannot pass through the downstream intersection normally, and the number of vehicles that pass per unit time is less than the actual traffic demand, and the traffic demand is seriously underestimated. risk

Images