Context aware Driver Behaviour Detection System in Intelligent Transportation Systems (ITS)

Vehicle Ad hoc Networks (VANET) emerged as an application of Mobile Ad hoc Networks (MANET), which use Dedicated Short Range Communication (DSRC) to allow vehicles in close proximity to communicate with each other, or to communicate with roadside equipment. Applying wireless access technology in vehicular environments has led to the improvement of road safety and a reduction in the number of fatalities caused by road accidents, through the development of road safety applications and facilitating information sharing between moving vehicles regarding the road. This paper focuses on developing a novel and non-intrusive driver behaviour detection system using a context-aware system in VANET to detect abnormal behaviours exhibited by drivers, and to warn other vehicles on the road so as to prevent accidents from happening. A five-layer contextaware architecture is proposed which is able to collect contextual information about the driving environment, perform reasoning about certain and uncertain contextual information and react upon that information. A probabilistic model based on Dynamic Bayesian Networks (DBN) for real time inferring four types of driving behaviour (normal, drunk, reckless and fatigue) by combining contextual information about the driver, vehicle and the environment is presented. The dynamic behaviour model can capture the static and the temporal aspects related to the behaviour of the driver, thus, leading to robust and accurate behaviour detection. The evaluation of behaviour detection using synthetic data proves the validity of our model and the importance of including contextual information about the driver, the vehicle and the environment.