华东交通大学学报2025，Vol.42Issue(6)：91-100,10.
冰雪环境下基于CNN-BiGRU-MHA的汽车异常驾驶行为识别
Anomalous Driving Behavior Recognition of Vehicles Based on CNN-BiGRU-MHA in Ice and Snow Environments
摘要
Abstract
To enhance the monitoring and detection of abnormal driving behavior of vehicles in snow and ice con-ditions,this paper proposes a data-driven method for identifying abnormal driving behaviors by integrating multi-channel CNN-BiGRU with MHA.Abnormal driving data are obtained by LAIF model,combined with driving characteristics and data features under ice and snow environments,abnormal driving behavior indicators are con-structed to characterize 6 kinds of abnormal driving behavior,namely rapid acceleration,rapid deceleration,rapid turning,rapid lane change,serpentine driving and skidding,and the ADASYN is introduced.The model proposed in this paper is compared and analysed with other models.The CNN-BiGRU-MHA detection model has an overall accuracy of 96.34%,which is better than other detection models indicating that the model can effectively detect the abnormal driving behavior of cars in ice and snow environments,and provides a theoretical basis for early warning of abnormal driving behavior.关键词
智能交通/异常驾驶行为识别/多头注意力机制/多标签分类/冰雪环境Key words
intelligent transportation/abnormal driving behavior recognition/multi-head attention mechanism/multi-label classification/ice and snow environments分类
交通工程引用本文复制引用
裴玉龙,范怡辰..冰雪环境下基于CNN-BiGRU-MHA的汽车异常驾驶行为识别[J].华东交通大学学报,2025,42(6):91-100,10.基金项目
黑龙江省重点研发项目(JD22A014) （JD22A014）
