Combined bridge-tunnel scenarios of driving on mountainous city expressways occur when bridges and tunnels frequently alternate during driving. The complex nature of these driving scenarios imposes crucial requirements on the drivers’ eye movement characteristics. This paper attempts to clarify these characteristics using descriptive statistics and the box graph method, registering the pupil diameter, blink duration, fixation, saccades, and fixation loci at different tunnel locations, bridges, and ramps. Realistic driving experiments were performed on the road segment spanning from the Nanchang tunnel to the Liujiatai tunnel freeway in Chongqing, China. Eye movement data were collected for 21 drivers. The experimental results showed that, while driving in the tunnel, the maximal pupil diameter of the participating drivers was approximately 4.0 mm as the driving mileage and the number of tunnels increased, and the maximal visual load on the drivers in the tunnel tended to be stable. At the second tunnel exit, the ramp, the middle section of the first bridge, and the third tunnel exit, the driving load was the highest, while the fixation duration was shorter for nighttime driving. The fixation duration was the longest for the diversion road of bridge B1 to the ramp during the day, and the fixation times were the longest at the beginning and end of the test road. The drivers more often paid attention to the speed dashboard while entering tunnels during daytime driving (compared with nighttime driving).
Signal timing parameters 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 signal timing 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 parameters inference method 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).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.