A PRACICAL SIMPLE TECHNIQUE TO DETECT ABNORMAL TRAFFIC FLOW IN FREEWAY

摘要

The problem addressed in this paper is the design of a simple and applicable approach with considering macroscopic model and stochastic discrete variables to detection of freeway abnormal traffic flow like incident, classified congestion, exit of congestion and so on. The goal is to design an algorithm that 1) directly use data from conventional presence detectors which provide binary information at each point in time, indicating the number of passed vehicles and mean time speed; and 2) minimize human operator requirement in detection, classification, and isolation of incident events. Using autocorrelation of the time series samples of density and flow which are collected from segments with predefined specifications is the main technique to detect the trend in flow and density changes if exist. A table of possibilities for flow and density changes in two sequential segments will help to detect congestion or any other abnormal traffic events.