In recent years, the importance of ensuring road safety has intensified, prompting the development of advanced driver monitoring systems. This paper presents a real-time bus driver monitoring system utilizing a Raspberry Pi, OpenCV, a RaspiCam and machine learning techniques. The system aims to enhance passenger safety by detecting driver fatigue and distraction, which are major contributors to road accidents. The proposed solution leverages the Raspberry Pi's processing capabilities and the RaspiCam's imaging features to continuously capture and analyze the driver's facial expressions and eye movements. OpenCV's robust image processing algorithms are employed to identify signs of drowsiness and inattentiveness. The innovative aspects of the proposed solution include the use of Eye Aspect Ratio (EAR) for drowsiness detection and Mouth Aspect Ratio (MAR) for detecting yawning. Both the EAR and MAR are calculated through real-time facial landmark analysis. The system issues alerts when unsafe driving behavior is detected, thereby allowing for timely intervention. The proposed monitoring system is cost-effective and scalable. It offers a promising approach to improving public transportation safety by mitigating the risks associated with driver fatigue and distraction. Experimental results showed an accuracy of 92% for fatigue detection and 88% for distraction detection. This demonstrates the system's effectiveness in real-time detection and its potential for deployment in commercial bus fleets.
Real-Time Bus Driver Monitoring System Using Machine Learning
2024-11-16
709898 byte
Conference paper
Electronic Resource
English
Real-Time Driver Drowsiness Detection System Using Machine Learning
Springer Verlag | 2023
|Real-Time Detection System of Driver Distraction Using Machine Learning
Online Contents | 2013
|