Drowsiness Detection Using Deep Learning Approaches

Date
2022
Research Supervisor
Editor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
The driver’s drowsiness influences the majority of accidents. Designing realistic and easy-to deploy real-world solutions is critical to identifying the onset of drowsiness. This research looks at early drowsiness detection, providing early warnings and giving individuals plenty of time to respond. According to a new study, drowsy driving, or driving when too exhausted to drive a car safely, is significantly more common than ever. According to a recent study, even small changes in an individual’s state can be detected through their facial activities, especially if they are asleep or experiencing drowsiness during driving. Our current work explores the identification of early drowsiness indicators, where existing systems often rely on inaccurate techniques to detect these signs. Researchers believe that drowsy drivers cause one out of every ten crashes. The problem of sleepy drivers has received relatively little attention in recent years, as safety measures have focused on reducing distracted driving. One factor could be that it's difficult to estimate how many accidents are caused by drivers who have slept off or closed their eyes while driving. Here in this paper, we will show our work to detect drowsy drivers and alert them, accordingly.
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University
Printed Thesis
DOI
ISSN
ISBN