YOLOv8 in Focus: A Review of its Application in Driver Monitoring Systems

Sameer Awasthi; Abhishek Verma; Ritesh Kr. Singh; Vidhik .

doi:10.37591/joedt.v14i3.7843

Abstract

This research presents a novel Driver Monitoring System (DMS) that utilises Convolutional Neural Networks (CNNs) to achieve remarkable results. Specifically, the YOLOv8 (You Only Look Once version 8) detection technique is used. The main goal is to increase road safety by using cutting-edge computer vision techniques to analyse driver behaviour in real-time. The YOLOv8 detection method, a cutting-edge CNN model renowned for its precision and effectiveness in object recognition, is the basis of the DMS. It focuses on using YOLOv8 to do tasks like gaze tracking, gesture detection, and facial recognition, making it possible to seamlessly monitor and interpret a range of driver behaviours. With the use of YOLOv8, the DMS can recognise and monitor important cues including gestures, eye movements, and facial expressions to evaluate the level of driver attention, weariness, and potential distractions. By doing a thorough analysis and assessing the YOLOv8-based DMS's efficacy in various driving situations. The system's capacity to reliably identify and mitigate safety concerns related to driver inattention impairment is exhibited through case studies and performance indicators. Furthermore, it discusses the ethical and regulatory ramifications of integrating the YOLOv8 detection algorithm into the DMS. Recommendations for industry standards compliance and privacy protection are addressed, with a focus on the proper application of this technology in the automobile sector. Overall, by demonstrating the effectiveness of the YOLOv8 detection algorithm in real-time behaviour analysis, this study advances driver monitoring systems. By utilising state-of-the-art CNN technology, the insights offered in this article open the door to safer and more intelligent modes of transportation.

Abstract

Keywords