安徽工程大学学报2024，Vol.39Issue(5)：26-31,6.
基于YOLOv8的车辆驾驶员疲劳检测应用研究
Application of Vehicle Driver Fatigue Detection Based on YOLOv8
摘要
Abstract
Fatigue driving is the main cause of traffic accidents.Due to the complexity and real-time requirements of fatigue driving detection scenarios,a vehicle driver fatigue detection and warning design method based on YOLOv8 is proposed.The YOLOv8 algorithm is improved in attention mechanism,data augmentation,lightweight network,etc.to improve the recognition accuracy and detection rate of vehicle driver fatigue detection.Mean while,key facial points are extracted to calculate the eye aspect ratio(EAR),and a fatigue evaluation classification model is established to achieve comprehensive judgment and warning of fatigue driving.A vehicle driver fatigue detection experimental platform is built to verify it.The results show that this approach can accurately obtain fatigue detection results,with an accuracy rate of 94％.关键词
YOLOv8/疲劳检测/注意力机制/眼睛纵横比Key words
YOLOv8/fatigue testing/attention mechanism/eye aspect ratio分类
信息技术与安全科学引用本文复制引用
王睿..基于YOLOv8的车辆驾驶员疲劳检测应用研究[J].安徽工程大学学报,2024,39(5):26-31,6.基金项目
安徽省高校优秀人才支持计划重点项目(gxyqZD2020056) （gxyqZD2020056）
安徽省高校自然科学重点项目(2022AH052741) （2022AH052741）
安徽商贸职业技术学院技术技能创新服务平台项目(2022ZDG01) （2022ZDG01）
安徽商贸职业技术学院"双高计划"项目(2020sgxm05-4) （2020sgxm05-4）
