基于驾驶员面部特征的疲劳检测系统研究  

Research on Fatigue Detection System based on Driver Facial Features

作　　者：刘馨雨 李庭燎 Liu Xinyu;Li Tingliao

机构地区：[1]南京审计大学统计与数据科学学院,江苏省南京市210000 [2]南京审计大学商学院,江苏省南京市210000

出　　处：《时代汽车》2023年第10期195-198,共4页Auto Time

基　　金：2021年江苏省大学生实践创新训练项目“大学生创新创业训练计划项目进度及经费预算表”(2021AX08006C)。

摘　　要：疲劳驾驶在我国的交通事故引发率居高不下,如何对驾驶员进行科学有效的疲劳驾驶检测并及时预警已经成为了当下热议的话题。为减少疲劳驾驶造成的交通安全风险,本文对基于驾驶员面部特征的检测方法进行了研究,通过对疲劳特征参数的提取克服了单一参数疲劳驾驶判断方法导致的判定精准度低等缺陷,且计算需求小,普适性能强。The incidence of traffic accidents caused by fatigue driving in China remains high,and how to detect and warn drivers scientifically and effectively fatigue driving and timely warning has become a hot topic.In order to reduce the traffic safety risks caused by fatigue driving,this paper studies the detection method based on the driver's facial features,and overcomes the shortcomings of low judgment accuracy caused by the single-parameter fatigue driving judgment method by extracting fatigue feature parameters,and the calculation requirements are small and the universal performance is strong.

关 键 词：疲劳驾驶 检测 PERCLOS 人眼定位 

分 类 号：U49[交通运输工程—交通运输规划与管理]