基于短时交通预测的公路交通异常判别方法

普通公路由于受到检测设施布设稀疏的制约,若沿用传统的交通事件自动识别方法,其判别率将低于高速公路或城市道路,而误判率也将高于高速公路或城市道路。为了便于公路管理者对普通公路发生交通异常时及时处理,以短时交通预测为基础,将交通异常的定义作为为判别标准,提出了1种新的交通异常判别方法,该方法能够排除由常发性交通拥挤和幽灵瓶颈现象引起的异常误判。试验表明,基于短时交通预测的公路异常判别方法精度误差在0.2以内,能够较好的实现对交通异常的判别。 

Short-term Traffic Prediction Theory-based Method for Discriminating Highway Abnormal Traffic Status

Because of the deficiency of monitoring facilities ,the efficiency of identifying traffic abnormal status of ordinary road is lower ,and the error is higher than that of highway using traditional auto-recognized method .This paper provides a new discriminated method to accelerate the processing time of traffic accidents ,which is based on the short-term traffic prediction theory and the general definition of abnormal traffic status .This method excludes self-healing situ-ations ,like recurrent congestion and Phantom traffic jams .Experiments indicate that the deviation of this method would be controlled within 0 .2 ,which means that it could identify abnormal traffic status efficiently and accurately .