基于眼部特征的驾驶员疲劳检测方法研究  

Research on Fatigue Detection Method of Drivers Based on Eye Feature

作　　者：涂超 赵波[1] TU Chao;ZHAO Bo(Shanghai University of Engineering and Technology,Shanghai 201600)

机构地区：[1]上海工程技术大学,上海201600

出　　处：《计算机与数字工程》2021年第11期2200-2203,2236,共5页Computer & Digital Engineering

摘　　要：随着汽车保有量的持续增加,随之而来的交通事故也持续增长,大部分的交通事故是由疲劳驾驶引起的。因此研究出一种能够有效检测驾驶员疲劳的方法具有重要意义。论文主要研究了基于级联的Adaboost驾驶员面部检测算法,在检测到人脸的基础上运用SDM算法进行人脸特征点定位,然后根据PERCLOS原理来判断驾驶员是否疲劳,实验表明该方法能够准确地检测驾驶员的疲劳状态。With the continuous increase of the car ownership,the traffic accidents have continued to increase,and most of the traffic accidents are caused by the fatigue driving.Therefore,it is of great significance to study the method to effectively detect the driver's fatigue.In this paper,the Adaboost driver face detection algorithm based on cascade is studied.On the basis of face detec⁃tion,SDM algorithm is used to locate the face feature points,and then according to the PERCLOS principle to judge whether the driver is tired or not.The experimental results show that this method can accurately detect the driver's fatigue state.

关 键 词：疲劳检测 面部检测 SDM算法 PERCLOS原理 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]