AN INTELLIGENT DRIVER DROWSINESS DETECTION SYSTEM USING VISION TRANSFORMERS

Abstract

Recent advances in co m p uter vi si on and deep learning have significantly enhanced intelligent transportation systems and advanced driver assistance systems (ADAS). Nevertheless, driver drowsiness remains a major contributor to road traffic accidents, accounting for a considerable number of fatalities and economic losses worldwide. Early and reliable detection of dr iver f atigue is ther ef or e essential for improving road safety. However, existing visionbased drowsiness detection m e t h o d s o f t e n e n c o u n t e r limitations in terms of real-time performance, computational efficiency, and robustness under varying illumination conditions, facial appearances, occlusions, a n d h e a d p o s e v a r ia t i on s. To address these challenges, this presents a vision-based intelligent driver drowsiness detection f r a m e w o r k t h a t p e r f o r m s c o n t i n u o u s , non -i n t r u s i v e m o n i t o r i n g o f t h e d r i v e r 's alertness. A standard RGB camera is employed to capture real-time facial video, while Haar Cascade classifiers are utilized for efficient face and eye localization. The d e t e c t e d e y e r e g i o n s a r e preprocessed and provided as input to a custom-designed Convolutional Neural Network (CNN) trained to classify eye s t a t e s a s o p e n o r c l o s e d .