Open AccessReal-Time Detection of Fatigue Driving Based on Face Recognition
Author(s) -
Xingxing Li,
Jun Luo,
Chao Duan,
Zhi Yan,
Panpan Yin
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1802/2/022044
Subject(s) - closing (real estate) , computer vision , artificial intelligence , face (sociological concept) , face detection , computer science , facial recognition system , feature (linguistics) , position (finance) , field (mathematics) , feature extraction , mathematics , social science , linguistics , philosophy , finance , sociology , political science , pure mathematics , law , economics
At present, fatigue driving is the third most dangerous factor affecting traffic accidents. Therefore, how to accurately and quickly identify the driver’s fatigue state is a common concern in the world. With the rapid development of machine vision and its application in the field of detection, a new solution to the problem of fatigue driving detection is proposed. Based on this, this paper proposes a fatigue driving detection technology based on face recognition. By means of computer image processing technology, the fatigue state of drivers is detected. The specific contents are as follows: based on dlib face recognition 68 feature points detection, the index of left and right eyes and mouth face marks are obtained respectively. The video stream is processed by OpenCV to detect the position information of human eyes and mouth. The eye opening or closing degree and mouth opening or closing degree are calculated to judge the blink frequency and yawn frequency, so as to determine whether the driver is tired.