Tools
Tools
Bandele, Olaomopo Oluwanifemi (2022) Real-time drowsiness detection using computer vision and deep learning techniques. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (5MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
The number of accidents caused by drowsy driving has been worrying, thus this research concentrated on developing a system that can reliably recognize a driver’s face and classify it as alert (open eyes) or drowsy (closed eyes). Convolutional neural network (CNN) and support vector machine (SVM) algorithms were trained on images of open and closed eyes of both sexes (male and female) and eye structures, as well as image of drivers wearing glasses so as to address limitations previous researchers had encountered. Pre-processing was performed to ensure that the many angles at which the drivers’ eyes could be positioned could be used to train the models. The SVM had an accuracy of 92% when tested on new images, whereas the CNN had an accuracy of 50%. For real-time testing, the trained CNN model was combined with open cv and a face recognition library, and detection was performed via a webcam.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Agarwal, Bharat UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TL Motor vehicles. Aeronautics. Astronautics Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 17 May 2023 10:28 |
| Last Modified: | 17 May 2023 10:28 |
| URI: | https://norma.ncirl.ie/id/eprint/6567 |
Actions (login required)
 |
View Item |