One of the major contributors to traffic accidents is drowsy driving. Globally, there are more people dying and sustaining deadly injuries each year. Road accidents can be avoided if the motorist's drowsiness is detected. In this research, a machine learning method for drowsiness detection is described. The areas of the driver's eyes are located using face detection, and these regions serve as templates for eye tracking in following frames. Finally, drowsiness detection is performed on the tracked eye pictures to produce alarm warnings. This method's three stages are detection of Face, detection of Eyes, and detection of Drowsiness. The driver's face is recognized using image processing, which then captures the image of the driver's eyes to check for signs of fatigue. The LSTM-KNN face detection method uses image frames that have been collected as input before producing the recognized face. The eye state is determined via EAR (Eye Aspect Ratio). Based on several test footage, the system employs frames for both face and eye tracking, with an average accuracy rate for eye localization and tracking of 81.5%. As a result, the suggested method for real-time driver drowsiness monitoring is a practical and affordable strategy.
Driver Drowsiness Monitoring and Detection using Machine Learning
2023-01-05
4209977 byte
Conference paper
Electronic Resource
English
Driver Drowsiness Detection Using Machine Learning
IEEE | 2023
|Snooze Breaker: Driver Drowsiness Detection Using Machine Learning
Springer Verlag | 2021
|Driver Drowsiness Detection Using Deep Learning
IEEE | 2023
|Driver Drowsiness Detection Using Deep Learning
IEEE | 2023
|Driver Drowsiness Detection using Deep Learning
IEEE | 2022
|