Expressway section flow estimation is great significance for specifying traffic management measures and guiding public travel. In view of the sparse distribution of highway traffic detection equipment, it is difficult to collect traffic parameters. Therefore, in the paper, the flow transfer coefficient between toll stations is used to reflect the spatio-temporal variation in the flow of the expressway network. Second. the average travel time of the road section is estimated to restore the vehicle's operating state. Thirdly, an estimation method of cross-sectional flow is proposed based on data fusion. Finally, in order to further reduce the estimation error, the RBF neural network model is used to modify the estimated value of the cross-sectional flow and obtain the final flow estimation result. The experimental results show that the method proposed in the paper can effectively estimate the traffic flow of the main line section of the expressway, which has certain reliability and practicability.

CICTP