Department of Urban Planning and Engineering, Dong-A University, Busan 49315, Korea.
Department of Urban Planning and Engineering, Yeungnam University, Gyeungsan 38541, Korea.
Sensors (Basel). 2021 Mar 12;21(6):1996. doi: 10.3390/s21061996.
Traffic flow data, such as flow, density and speed, are crucial for transportation planning and traffic system operation. Recently, a novel traffic state estimating method was proposed using the distance to a leading vehicle measured by an advanced driver assistance system (ADAS) camera. This study examined the effect of an ADAS camera with enhanced capabilities on traffic state estimation using image-based vehicle identification technology. Considering the realistic distance error of the ADAS camera from the field experiment, a microscopic simulation model, VISSIM, was employed with multiple underlying parameters such as the number of lanes, traffic demand, the penetration rate of ADAS vehicles and the spatiotemporal range of the estimation area. Although the enhanced functions of the ADAS camera did not affect the accuracy of the traffic state estimates significantly, the ADAS camera can be used for traffic state estimation. Furthermore, the vehicle identification distance of the ADAS camera and traffic conditions with more lanes did not always ensure better accuracy of the estimates. Instead, it is recommended that transportation planners and traffic engineering practitioners carefully select the relevant parameters and their range to ensure a certain level of accuracy for traffic state estimates that suit their purposes.
交通流量数据（如流量、密度和速度）对于交通规划和交通系统运行至关重要。最近，提出了一种使用先进驾驶辅助系统（ADAS）相机测量到前车距离的新型交通状态估计方法。本研究使用基于图像的车辆识别技术，考察了增强功能的 ADAS 相机对交通状态估计的影响。考虑到 ADAS 相机从现场实验中的实际距离误差，使用微观模拟模型 VISSIM，并考虑了多个潜在参数，如车道数量、交通需求、ADAS 车辆的渗透率以及估计区域的时空范围。虽然 ADAS 相机的增强功能对交通状态估计的准确性没有显著影响，但 ADAS 相机可用于交通状态估计。此外，ADAS 相机的车辆识别距离和具有更多车道的交通条件并不总是能确保估计值具有更好的准确性。相反，建议交通规划者和交通工程从业人员仔细选择相关参数及其范围，以确保适合其目的的交通状态估计具有一定的准确性。
