Automated Traffic Incident Detection with GPS Equipped Probe Vehicles

Traffic congestion can be broadly classified as recurrent and non-recurrent based on its relation with daily variation of traffic demand. The former is mainly the result of traffic incidents such as accidents, vehicle breakdowns or any other incident that impedes the normal flow of traffic. Furthermore, traffic incidents could increase the severity of recurrent congestion in terms of the impact area and the duration. Therefore, faster detection of traffic incidents is of extreme importance for maintaining a higher level of service for road users. Traffic Incident Detection Systems (IDS) use a variety of technologies to detect incidents so that bottlenecks created by incidents can be cleared quickly and appropriate alternative measures can be implemented. The use of probe vehicles in IDS has become an attractive alternative with the recent advancements in technology, especially in the field of Global Positioning System (GPS). GPS has become a reliable, accurate, and economically feasible positioning technology for probe vehicles. This paper discusses the results of a proof-of-concept study in which a transit vehicle fleet was used as the probe system for traffic incident detection. The system performance analysis was conducted using a combination of field experiments and traffic microsimulation tools. The latter was used for simulating traffic incidents under controlled conditions and to avoid the complications resulting from many environmental factors that influence traffic activity. The results indicate highly successful Detection Rate (DR) with low False Alarm Rate (FAR). The techniques also yield an average Time to Detect (TTD) of 30 seconds to 3 minutes depending on the probe vehicle population size, incident characteristics, and GPS performance.