Incident Detection in Freeway Based on Autocorrelation Factor of GPS Probe Data

摘要

This study proposes a statistical approach to incident detection in a section of the intercity freeway by applying GPS probe data toa GIS geofenced platform.We evaluated the proposed method using data sources from real traffic sensors of the intercity Tehran-Qom freeway in Iran. Through the SEPEHTAN project in Iran, intercity bus fleet equipped with an onboard unit that providesGPS data transferring to the central database. The main novelties in this paper are gathering density and speed time series fromGPS probe data in a GIS platform and using autocorrelation factor to detect the location of the incident. The method comparedwith three different AID algorithms and real terms as well. Although the penetration rate was 3%, the results were considerablymeet with the actual traffic condition. We reached 92.8% detection rate and 7.1% for the false alarm.