Real-Time Monitoring of Driver Drowsiness and Distraction Detection

Driver fatigue and distraction are major contributors to road accidents worldwide. This project presents a real-time driver monitoring system that employs computer vision and machine learning techniques to detect drowsiness and inattentiveness. The system uses facial landmark detection to monitor eye closure and facial orientation, leveraging the Dlib library for accurate face and landmark identification. Video is captured from the default camera, and the Eye Aspect Ratio (EAR) is calculated to determine eye status.When the EAR falls below a threshold for a sustained duration, an audio alert is triggered,signaling potential fatigue. The system also detects prolonged absence of the driver’s face,indicating distraction, and issues an alert. Additionally, a Convolutional Neural Network (CNN) is implemented for gender classification, providing contextual information about the driver. This intelligent monitoring framework enables proactive intervention, enhancing road
safety by alerting drivers before fatigue or distraction leads to accidents. The system’s modular architecture allows easy integration into vehicles, providing scalable and
real-time detection to improve driver safety.