Description of Invention
The real-time driver drowsiness detection system aims to improve road safety by using computer vision and machine learning. It operates with a standard webcam to monitor the driver’s facial features and identify signs of drowsiness, like prolonged eye closure and yawning. The system integrates face detection with the Haar Cascade classifier, facial landmark detection using Dlib, and metrics such as the Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR) to spot drowsiness. Additionally, it uses head pose estimation through OpenCV’s SolvePnP method to enhance accuracy. When drowsiness is detected, the system issues an auditory alert and notifies emergency contacts via a custom Telegram bot. It also logs detection events for performance evaluation. This approach combines traditional computer vision with modern machine learning to provide a practical solution for reducing drowsiness-related accidents.