论文部分内容阅读
交叉口安全评价、信号方案设计等工作中必须考虑黄灯期间驾驶员的行为特性,为此需要构建合理的驾驶员行为模型。针对黄灯期间信号交叉口的驾驶员行为模型进行研究,利用视频采集驾驶员在黄灯期间的行为数据,经数据预处理后,考虑黄灯启亮时刻车辆位置、车速两个因素,运用Logistic回归构建了驾驶员行为模型,并利用受试者工作特征曲线(ROC曲线)等检验了模型的准确性。
In the work of safety evaluation at intersections and signal scheme design, the driver’s behavior characteristics during the yellow light must be considered. Therefore, it is necessary to construct a reasonable driver behavior model. Aiming at the driver behavior model at the signalized intersection during the yellow light period, the author used the video to collect the driver’s behavior data during the yellow light period. After data preprocessing, taking into account the vehicle position and the vehicle speed when the yellow light turns on, The regression model constructed the driver behavior model, and used the receiver operating characteristic curve (ROC curve) to test the accuracy of the model.