signaltimingparameters are essential components in traffic signal control (TSC). It affects not only traffic management, but also traffic safety. However, due to the confidential issues of the traffic management dep...
详细信息
signaltimingparameters are essential components in traffic signal control (TSC). It affects not only traffic management, but also traffic safety. However, due to the confidential issues of the traffic management department, or lack of data integration from different signal manufacturers, it is intractable to obtain the city-scale signaltiming data. In the previous studies, some existing estimation methods focused on a single parameter and fixed-timing scheme. To tackle this issue, this study attempts to develop an integrated parametersinferencemethod based on license plate recognition (LPR) data, considering phase weight, average phase duration information and the overall phases of the intersections. In particular, the proposed method includes phase sequence inference model, cycle length inference model and phase duration inference model. To testify the performance of the proposed method, a real-world LPR dataset from Guangzhou, China, is applied. Numerical results show that the proposed method performs more efficiently on parameter inferences than the state-of-the-art (SOTA) approach. For instance, in the given research time period, the mean absolute error (MAE) of each phase duration is 2 s averagely (6.32 s in the SOTA approach), and the mean relative error (MRE) of cycle length is 0.91% (11.67% in the SOTA approach).
暂无评论