Driver Drowsiness Alert with RPi

Abstract

Driver drowsiness is a major cause of road accidents, especially on long journeys or during nighttime driving. This project presents a Raspberry Pi-based real-time driver drowsiness detection system that uses computer vision and facial landmarks to detect signs of fatigue. The system leverages a PiCamera to capture the driver’s facial image, from which it computes the Eye Aspect Ratio (EAR) using dlib’s facial landmark detector. When the EAR falls below a predefined threshold for a consecutive number of frames, it indicates eye closure due to drowsiness. In response, an auditory alert is triggered using a buzzer connected to the Raspberry Pi’s GPIO pins to wake the driver. This cost-effective, non-intrusive solution enhances road safety by providing early warnings of driver fatigue.