This paper presents an incident detection algorithm based on the speed and acceleration profiles of probe vehicles as they travel along a freeway. It is based on the assumption that when a probe vehicle approaches a detectable incident, it will decelerate from its normal speed and then accelerate back to the normal speed after passing the incident. The incident detection performance of the algorithm, at various percentages of probe vehicles in the traffic stream, has been tested on a set of incident data generated by a calibrated microscopic traffic simulation model. The results are compared with a multi-layer feed-forward neural network incident detection techniques that uses volume, speed and occupancy measured at fixed locations as inputs. It is found that when there are 30% probe vehicles in the traffic stream, the new probe vehicle algorithm can achieve comparable detection rate and mean time to detection against the neural network model.
Abstract