ENHACNING ROAD SAFETY WITH YOLO: REAL-TIME DROWSINESS IDENTIFICATION IN DRIVERS

Abstract

Drowsiness-related accidents have been on the rise in recent years, posing significant risks to road safety and other critical domains. In this research, we propose a novel approach to address this issue by combining drowsiness detection and awake identification using the state-of-the-art You Only Look Once (YOLO) object detection algorithm. The primary objective of this study is to develop a robust and efficient computer vision system capable of accurately detecting drowsiness and identifying awake states in real-time. Through an extensive literature review, we explore the existing methods and technologies in drowsiness detection and awake identification. The YOLO algorithm is chosen due to its remarkable performance in object detection tasks, and we modify it to suit the specific requirements of drowsiness analysis. Our proposed system leverages facial cues, eye tracking, and head position to effectively distinguish between drowsy and awake states. Furthermore, we discuss the additional features and data incorporated into the system to improve the accuracy of wakefulness state classification. Our experimental results demonstrate the effectiveness of the proposed approach. The system achieves impressive performance metrics, surpassing existing methods in drowsiness detection and awake identification tasks The findings underline the importance of leveraging computer vision techniques to enhance safety in critical domains and pave the way for future advancements in this field.

Keywords:-drowsiness ,awake , yolo , ai , labelling .