Open AccessDriver Drowsiness Detection Based on Face Feature and Perclos
Author(s) -
Sarath Gopi,
E. Punarselvam,
K Dhivya,
Malathi Kanagasabai,
N. Sandhanaselvi
Publication year - 2021
Publication title -
international journal of scientific research in science and technology
Language(s) - English
Resource type - Journals
eISSN - 2395-602X
pISSN - 2395-6011
DOI - 10.32628/ijsrst218319
Subject(s) - distraction , computer vision , artificial intelligence , face (sociological concept) , feature (linguistics) , computer science , frame (networking) , face detection , feature extraction , facial recognition system , telecommunications , psychology , social science , linguistics , philosophy , neuroscience , sociology
Driving vehicles are complex and require undivided attention to prevent road accidents. Fatigue and distraction are a major risk factor that causes traffic accidents, severe injuries, and a high risk of death. Some progress has been made for driver drowsiness detection using a contact-based method that utilizes vehicle parts (such as steering angle and pressure on the pedal) and physiological signals (electrocardiogram and electromyogram). However, a contactless system is more potential for real-world conditions. In this study, we propose a computer vision-based method to detect driver's drowsiness from a video taken by a camera. The method attempts to recognize the face and then detecting the eye in every frame. From the detected eye, iris regions for left and right eyes are used to calculate the PERCLOS measure (the percentage of total time that eye is closed). The proposed method was evaluated based on public YawDD video dataset. The results found that PERCLOS value when the driver is alert is lower than when the driver is drowsy.