Author: Yoonchul Nam
Nam, Yoonchul, 2022 Drowsy driver detection and warning system on Raspberry Pi, Flinders University, College of Science and Engineering
Terms of Use: This electronic version is (or will be) made publicly available by Flinders University in accordance with its open access policy for student theses. Copyright in this thesis remains with the author. You may use this material for uses permitted under the Copyright Act 1968. If you are the owner of any included third party copyright material and/or you believe that any material has been made available without permission of the copyright owner please contact copyright@flinders.edu.au with the details.
Fatigue is a loss of alertness that reduces human performance and may or may not end up in sleep or micro-sleeps. It is one of the leading factors contributing to road crashes and has several problematic effects on driving performance. In order to reduce accidents caused by drowsy driving, various algorithms have been developed to detect driver's eye movements and sound alarms, and the information of the practical equipment and its experimental data in this study is offered to the drivers who want to apply this technique to their cars. In this study, camera performance is a large part of the work, and the author used two different types of cameras (general webcam and night vision camera) to check the accuracy of facial feature recognition, which can be identified whose face is in the image. He also studied factors that can affect facial recognition, such as the amount of light and the angle of the camera, to find out which environment shows the highest accuracy. There was a limit to the hardware such as low frames per second (fps) because it had to consider a reasonable price.
Keywords: Drowsiness Detection, Eye Blink Detection, Eye Aspect Ratio, Raspberry Pi, Night Vision Camera
Subject: Engineering thesis
Thesis type: Masters
Completed: 2022
School: College of Science and Engineering
Supervisor: Dr. Sherry Randhawa