摘要：An exact threat level assessment method is necessary to improve safety of vehicles, but the traffic environment is not taken into account adequately in existing approaches. This paper presents a Bayesian network based method to improve the effect of vehicles threat evaluation. In the method, various factors threatening vehicle safety are analyzed, and a Bayesian network model with environmental factors and vehicle factors is introduced to describe the threat level of vehicles. The local conditional probability tables of the method are given also. Then threat index of vehicles integrating multiple factors can be obtained by Message-passing algorithm. Experimental results show that the method can reflect the threat level of vehicles accurately, and calculational costs meet the requirement of real-time application.
