基于Dlib的疲劳驾驶远程监测系统设计  

Design of a Fatigue Driving Remote Monitoring System Based on Dlib

作　　者：于星橦 YU Xingtong(School of Computer Science and Engineering,Northeastern University,Liaoning 110169,China)

机构地区：[1]东北大学计算机科学与工程学院,辽宁110169

出　　处：《集成电路应用》2024年第2期412-415,共4页Application of IC

摘　　要：阐述设计疲劳驾驶远程监测系统,利用Dlib人脸检测模型,通过计算EAR与MAR参数值来判断驾驶员是否闭眼或打哈欠,并通过HPE算法判断驾驶员头部姿态。若发现疲劳驾驶,系统会进行警告提示,并通过云端发送到监测平台进行人为干预,实现“双重保险”。经实验测试,此系统可以准确判定货车驾驶员的疲劳状态,降低事故风险。This paper describes the design of a remote monitoring system for fatigue driving,using the Dlib face detection model to determine whether the driver is closing their eyes or yawning by calculating the EAR and MAR parameter values,and using the HPE algorithm to determine the driver's head posture.If fatigue driving is detected,the system will issue a warning prompt and send it to the monitoring platform through the cloud for human intervention,achieving"dual insurance".Through experimental testing,this system can accurately determine the fatigue status of truck drivers and reduce the risk of accidents.

关 键 词：智能控制技术 Dlib EAR MAR HPE 疲劳驾驶 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]