Paper Contents
Abstract
Drowsiness, especially during tasks like driving, presents a critical safety concern. To tackle this issue, we propose an innovative real-time drowsiness detection system leveraging Eye Aspect Ratio (EAR) analysis. By harnessing advanced computer vision techniques and precise facial landmark detection algorithms, our system continuously tracks and monitors the movements of the driver's eyes. Through meticulous calculation of the EAR, which signifies the ratio of distances between specific eye landmarks, our system discerns subtle changes indicative of drowsiness, such as eyelid drooping and reduced blink frequency. Upon reaching a predefined EAR threshold, the drowsiness detection mechanism promptly triggers, alerting the individual in real-time to take necessary corrective actions. Seamlessly integrated within a Flask-based web application, complemented with SocketIO integration for efficient communication, our system facilitates the processing of live video streams from a camera, ensuring robust performance across various environments. Rigorous testing and validation have demonstrated the system's remarkable reliability and accuracy in detecting drowsiness, offering a proactive solution to mitigate the inherent risks associated with driver fatigue. By significantly enhancing safety in critical settings, our system stands as a vital tool in the ongoing effort to prevent accidents caused by drowsy driving.
Copyright
Copyright © 2024 Vemula Bhavani devi. This is an open access article distributed under the Creative Commons Attribution License.
