The invention discloses a driver high-speed driving distraction recognition modeling method based on a GM-HMM, and the method comprises the following steps: testing and collecting data: carrying out adriver-in-loop simulation driving test based on a simulation driver, and recording a video, wherein the test road condition is a high-speed road condition, and the data collected in the test comprises the rotating speed of a steering wheel, a yaw angle and a longitudinal acceleration; randomly interfering a driver in the test process; processing the test data: according to the test video, performing marking, standard normalization, standard deviation calculation, slicing, data division and other steps on the test data to obtain a distraction state training database, a distraction state test database, a non-distraction state training database and a non-distraction state test database; training a distraction state recognition model and a non-distraction state recognition model based on theGM-HMM; testing the model. A driver high-speed driving distraction state recognition model is established by simulating driving test acquisition data, and the method has the advantages of accurate recognition and low cost.
本发明公开了基于GM‑HMM的驾驶员高速驾驶分心识别建模方法,包括以下步骤:试验并采集数据:进行基于模拟驾驶器的驾驶员在环模拟驾驶试验并录像,实验路况为高速路况,试验中采集的数据包括方向盘转速、偏航角和纵向加速度;试验过程中随机对驾驶员进行干扰;处理试验数据:根据试验录像,对试验数据进行标记、标准正态化、计算标准差、切片、数据划分等步骤,得到分心状态训练数据库和分心状态测试数据库、非分心状态训练数据库和非分心状态测试数据库;训练基于GM‑HMM的分心状态识别模型和非分心状态识别模型;测试模型。通过模拟驾驶试验采集数据,建立驾驶员高速驾驶分心状态识别模型,具有识别准确,成本低廉的优点。
Driver high-speed driving distraction recognition modeling method based on GM-HMM
基于GM-HMM的驾驶员高速驾驶分心识别建模方法
2021-02-05
Patent
Electronic Resource
Chinese
Driver driving distraction behavior recognition method based on driving behavior data
European Patent Office | 2021
|Driver cognitive distraction recognition
British Library Conference Proceedings | 2022
|Driver cognitive distraction recognition
SPIE | 2022
|Driver Distraction Assessment Using Driver Modeling
IEEE | 2013
|