Driver fatigue has been an important factor for large number of vehicle accidents. Drowsy-driving crashes are estimated to result in roughly 800 deaths and 50,000 injuries each year, according to the National Highway Traffic Safety Administration. In the field of accident prevention systems, developing solutions to detect or prevent drowsiness is a serious challenge. Because in case of drowsiness, there is a need to develop methods to counter its effects, presented on the road. The driver's eyes will be monitored in real time to see if they are open or closed. It is thought that indicators of driver weariness can be recognised by monitoring the eyes in order to avoid an automobile accident. Images of a face, as well as observation of eye movements and eyelid patterns, are part of a fatigue detection sequence. The landmarks of frontal driver facial in a frame are obtained after the position of the eyes is determined using the Dlib toolkit. A new parameter, termed Eyes Aspect Ratio, is included to measure the tiredness of the driver in the current frame based on the eyes, landmarks. The study's findings can be used to improve smart transportation systems, ensure driver safety, and eliminate drowsy driving-related losses.
Real-Time Driver Drowsiness Detection Using Dlib And openCV
2022-12-16
1009041 byte
Conference paper
Electronic Resource
English
A Real-Time Driver Drowsiness Detection Using OpenCV, DLib
Springer Verlag | 2022
|Driver Drowsiness Detection Using Open CV and DLIB
IEEE | 2023
|Driver Drowsiness Detection System with OpenCV & Keras
IEEE | 2021
|Driver Drowsiness Detection System with OpenCV and Keras
IEEE | 2024
|Drowsiness Detection System Using OpenCV
IEEE | 2025
|