基于计算机视觉的疲劳驾驶检测方法  

Fatigue driving detection method based on computer Vision

作　　者：严晓波 张艳莎 潘凤 蔡姗 王杰 Yan Xiaobo;Zhang Yansha;Pan Feng;Cai Shan;Wang Jie(College of Data Science and Information Engineering,Guizhou Minzu University,Guiyang 550025;Key Laboratory of Pattern Recognition and Intelligent System of Guizhou Province,Guiyang 550025)

机构地区：[1]贵州民族大学数据科学与信息工程学院,贵阳550025 [2]贵州省模式识别与智能系统重点实验室,贵阳550025

出　　处：《现代计算机》2023年第4期38-42,共5页Modern Computer

基　　金：贵州省高等学校教学内容和课程体系改革项目(2020053);贵州省普通高等学校青年科技人才成长项目(黔较合KY字〔2022〕177号)。

摘　　要：提出利用识别眼睛睁闭频率和持续时间的方法来检测疲劳驾驶。采用LifaceDetect检测人脸68个特征点,从特征点中定位眼睛的图像位置,通过SVM对提取出的人眼图像特征进行眼睛睁闭状态判断,再根据PERCLOSE准则判断驾驶员的疲劳状态。实验证明,该方法能实时检测出驾驶员眼睛的睁闭状态,且准确率较高,能有效判别出驾驶员的疲劳状态。It is proposed to detect fatigue driving by using a method to identify the frequency and duration of eye opening.LifaceDetect is used to detect 68 feature points of the human face,locate the image position of the eye from the feature points,judge the closed state of the extracted human eye image features through SVM,and then judge the fatigue state of the driver according to the PERCLOSE criterion.Experimental results show that this method can detect the open state of the driver’s eyes in real time,and the accuracy rate is high,which can effectively determine the fatigue state of the driver.

关 键 词：疲劳驾驶检测 LifaceDetect SVM 眼睛状态识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] U463.6[自动化与计算机技术—计算机科学与技术] U492.8[机械工程—车辆工程]