Modeling safety-critical driver behavior at signalized intersections needs to account for the driver’s planned decision process, where a driver executes a plan to avoid collision in multiple time steps. Such a process can be embedded in the Optimal Velocity Model (OVM) that traditionally assumes that drivers base their “mental intention” on a distance gap only. We propose and evaluate a data-driven OVM based on real-time inference of roadside traffic video data. First, we extract vehicle trajectory data from roadside traffic footage through our advanced video processing algorithm (VT-Lane) for a study site in Blacksburg, VA, USA. Vehicles engaged in car-following episodes are then identified within the extracted vehicle trajectories database, and the real-time time-to-collision (TTC) is calculated for all car-following instances. Then, we analyze the driver behavior to predict the shape of the underlying TTC-based desired velocity function. A clustering approach is used to assess car-following behavior heterogeneity and understand the reasons behind outlying driving behaviors at the intersection to design our model accordingly. The results of this assessment show that the calibrated TTC-based OVM can replicate the observed driving behavior by capturing the acceleration pattern with an error 20% lower than the gap distance-based OVM.

中文翻译：

---

基于实时安全的最优速度模型

在信号交叉口对安全至关重要的驾驶员行为进行建模需要考虑驾驶员的计划决策过程，其中驾驶员执行计划以避免在多个时间步内发生碰撞。这样的过程可以嵌入到最佳速度模型 (OVM) 中，该模型传统上假设驾驶员的“心理意图”仅基于距离差距。我们提出并评估了一种基于路边交通视频数据实时推断的数据驱动 OVM。首先，我们通过我们的高级视频处理算法 (VT-Lane) 从路边交通镜头中提取车辆轨迹数据，用于美国弗吉尼亚州布莱克斯堡的一个研究地点。然后在提取的车辆轨迹数据库中识别参与跟车事件的车辆，并为所有跟车实例计算实时碰撞时间 (TTC)。然后，我们分析驾驶员行为以预测基于 TTC 的基础期望速度函数的形状。聚类方法用于评估跟车行为的异质性，并了解交叉路口偏远驾驶行为背后的原因，以相应地设计我们的模型。该评估的结果表明，校准的基于 TTC 的 OVM 可以通过捕获加速度模式来复制观察到的驾驶行为，其误差比基于间隙距离的 OVM 低 20%。