1. A novel approach for driver drowsiness detection using deep learning.
- Author
-
Kavitha, M. N., Saranya, S. S., Adithyan, K. Dhanush, Soundharapandi, R., and Vignesh, A. S.
- Subjects
DEEP learning ,DROWSINESS ,ARTIFICIAL neural networks ,ALGORITHMS ,TRAFFIC accidents ,MOUTH - Abstract
If the driver does not have proper rest, he/she tends to fall asleep causing an accident. The main objective of the project is to design a system that can detect the driver drowsiness and alert them to reduce road accidents. The system takes the input images through a camera which focus on the driver. Initially the face is detected using Naive Bayes Region of Interest (NB_ROI) algorithm, and then the eye and mouth regions are separated. In this paper, a single layer Artificial Neural Network is used along with the auto encoder module of the Deep Learning Toolbox to categorize them to one of the classes as 'drowsy' or 'alert' based on the eye closure detection. The proposed method offers better accuracy in driver drowsiness detection. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF