Due to the cancellation of provincial toll stations, ETC gantries have been newly built on the highways. ETC gantry realizes non-stop charging, improves highway traffic efficiency, and alleviates traffic congestion at toll stations. Although ETC gantry data has high accuracy, there are abnormal data detection problems in some adverse driving environments such as night and bad weather. The accuracy of traffic flow data has a great impact on traffic control and billings. To improve the accuracy of gantry flow data, a multi-source data fusion model based on K-means RBF neural network was proposed in this paper. In this paper, multi-source data fusion was carried out by using traffic survey data (microwave radar detector and video detector) and ETC gantry data on the G50 highway. The fusion result was compared with the detection result of the ETC gantry and other fusion methods. It was found that the model has adaptive learning characteristics and realizes the high-precision correction of the running state of traffic flow in abnormal environments by learning the historical law of multi-source data. This method overcomes the problem of data detection of a single detector due to a bad driving environment and demonstrates the potential of multi-source data fusion in the transportation field.
 

暂无