Drowsiness Detection System for Vehicles Using Raspberry PI

Drowsy driving is a leading cause of road accidents worldwide, leading to severe consequences, including fatalities and property damage. This research introduces a real-time drowsiness detection system aimed at alerting drivers and reducing accident risks. The system leverages computer vision and machine learning algorithms to identify early indicators of drowsiness, such as eye closure, head movements, and facial expressions. A Convol utional Neural Network (CNN) is trained using a dataset containing images of drivers, achieving a 95% accuracy rate in drowsiness detection. To enhance driver awareness, the system is equipped with real-time alerts, including visual, auditory, and vibrational warnings when drowsiness is detected. Extensive testing on driver datasets demonstrates the system's effectiveness in recognizing drowsiness and minimizing accident risks. This study highlights the potential of machine learning and computer vision in real-time drowsiness monitoring, contributing to improved road safety.