Driver Drowsiness Detection

Designed and developed a hardware-based driver drowsiness detection system using ESP32-CAM and computer vision techniques. Implemented facial landmark detection using OpenCV and dlib to monitor eye closure and calculate the Eye Aspect Ratio (EAR) to detect signs of drowsiness in real time. Integrated Arduino Uno with an LCD, LEDs, and a buzzer to provide immediate visual and audible alerts. Developed a Flask-based web dashboard to display the camera stream and driver status, with additional Telegram notifications for drowsiness alerts. The project aims to improve road safety through an affordable, real-time driver monitoring solution.