摘要
目前很多研究使用车辆轨迹数据来识别急减速驾驶行为,但目前使用的固定阈值方法无法对不同驾驶场景做出区分且缺乏建模分析。基于车辆跟驰模型,提出了一种包含多种驾驶场景的急减速驾驶行为判断方法,该方法考虑照明条件、天气、道路车速等参数,解决了现有方法中缺乏场景分类的问题。使用聚类算法区分历史数据中的急减速驾驶行为,提取实际阈值并与模型结果进行比较,对该方法的准确性进行验证。结果表明,与现有方法相比,所建立的模型对不同种类驾驶场景的适应性较好,识别准确率较高。由此证明利用该模型可以更好地实现基于轨迹数据的车辆急减速行为识别,从而为驾驶安全研究打下基础。
At present,many researches use vehicle trajectory data to identify rapid deceleration driving behaviors,but the existing fixed threshold method can not distinguish different driving scenes and lack of modeling analysis.Based on the car following model,a method to judging rapid deceleration driving behavior which include multiple driving scenes was proposed.Some parameters were considered in this method,such as lighting conditions,weather,road speed,and solves the problem of lacking scene classification.Clustering algorithm was used to distinguish the rapid deceleration driving behavior in the historical data,actual threshold was extracted and compared with the model results to verify the accuracy of the method.The results show that the model has good adaptability and high accuracy for different driving scenes.Compared with the existing method,it is proved that the method can better identify the rapid deceleration behavior,then it can offer a foundation for driving safety research.
作者
王伟
赵琦
王力
李子悦
WANG Wei;ZHAO Qi;WANG Li;LI Zi-yue(Beijing Key Lab of Urban Intelligent Traffic Control Technology, North China University of Technology, Beijing 100144, China;Beijing Zhijia Travel Technology Co., Ltd., Beijing 100044, China)
出处
《科学技术与工程》
北大核心
2022年第10期4215-4221,共7页
Science Technology and Engineering
基金
北京市长城学者培养计划(CIT&TCD20190304)
北京市自然科学基金青年项目(4194078)。
关键词
交通工程
急减速行为判定
多场景模型
车辆轨迹数据
聚类算法
traffic engineering
rapid deceleration behavior judgement
multi-scene model
vehicle trajectory data
clustering algorithm
