VigilEye: Machine learning-powered driver fatigue recognition for safer roads

Abstract

In an era where autonomous vehicles are on the horizon, the importance of human vigilance during driving cannot be understated. One of the paramount challenges road safety advocates face is driver fatigue, a silent culprit behind many tragic accidents. Our project seeks to address this issue by merging facial feature recognition with cutting-edge machine learning techniques, harnessing tools such as OpenCV and Dlib. This approach is centred around 68 precise facial feature detectors, adept at capturing specific markers like the status of a driver's eyes. Once data is acquired, our algorithms scrutinize it for fatigue indicators. Offering both cost and user benefits, our non-intrusive system swiftly alerts drivers, through auditory or tactile means, upon detecting drowsiness. Our system achieved a remarkable 94 % efficiency in timely and accurate fatigue detection through exhaustive testing across varied scenarios, underscoring its potential to revolutionize road safety.

Keywords

• Driver fatigue
• Machine learning (ML) algorithms
• Facial Extraction
• KNN