Driver Drowsiness Detection System Based on Eye State Analysis

Abstract

Abstract: The Driver Drowsiness Detection System, utilizing eye state analysis, introduces an innovative approach with OpenCV for real-time monitoring of eye movements. This combination enables precise eye tracking and analysis, essential for assessing driver alertness. Upon detecting drowsiness, the system employs a modified Convolutional Neural Network (CNN) architecture to evaluate its severity. This neural network processes extracted features from the driver's eyes, providing a nuanced assessment of drowsiness levels. By leveraging these technologies, the system enhances safety by promptly alerting drivers to their decreasing alertness levels, potentially mitigating drowsy driving-related accidents. The integration of shape prediction with OpenCV offers a robust foundation for accurate eye monitoring, while the modified CNN architecture ensures effective drowsiness assessment. This research contributes to advancing intelligent driver assistance systems, underscoring the significance of integrating stateof-the-art technologies to address critical road safety concerns.