Open AccessReal-Time Driver Awareness Detection System
Author(s) -
Ameen Mohammed,
Emad A. Mohammed,
Ashty M. Aaref
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/745/1/012053
Subject(s) - computer science , python (programming language) , artificial intelligence , robustness (evolution) , computer vision , face detection , edge detection , idle , landmark , feature extraction , face (sociological concept) , image processing , facial recognition system , image (mathematics) , social science , biochemistry , chemistry , sociology , gene , operating system
Nowadays, drowsiness is the major reason for many road accidents. Due to this fact, different attempts have been made to successfully detect fatigue. In this paper, a computer vision method has been presented to determine the presence of fatigue in a driver’s face. A way for fatigue recognition through the exploitation of facial features has been proposed. A landmark algorithm has been used to finds the marks of the eye edge and then calculate Eye Aspect Ratio (EAR), which is the main threshold parameter to judge whether the driver is sleeping or not. A new approach has been proposed to calculate EAR, which gives more accurate results than the common method. The results illustrate that the proposed method gives maximum detection fluctuation of (0.18), while the common method gives (0.33) detection fluctuation, the proposed system gives robustness against noise, so it can detect face and gives a decision for driver awareness with a noise level of (130) dB. An OpenCV library for image processing and Dlib library for feature extraction with the python IDLE has been utilized.