Raspberry Pi Based Driver Drowsiness Detection System Using Convolutional Neural Network (CNN)
Authors:
- 12 May 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 30-34
Abstract
This paper presents the implementation of a drowsiness driving detection system using Raspberry Pi. Drowsy driving can be defined as a behavioral decline in driving skills. In this work, the Convolutional Neural Network (CNN) has been used to classify drowsiness symptoms such as blinking and yawning. A total of 1310 images were used to train the CNN architecture. A 4 -layer convolution filter has been added as a layer in this CNN architecture. Adam optimization algorithm was then used to train the CNN. A real time study on the effectiveness of this prototype was conducted on 10 individuals. This proposed system successfully demonstrates a classification accuracy rate between 80% and 98%. Other factors that can affect the rate of classification accuracy, such as camera distance from the driver and lighting factors, are also studied in this paper.Keywords
This publication has 12 references indexed in Scilit:
- Review Paper on Yawning Detection Prediction System for Driver Drowsiness2021
- Real-Time Smart Drivers Drowsiness Detection Using DNN2021
- A Real-time Driving Drowsiness Detection Algorithm With Individual Differences ConsiderationIEEE Access, 2019
- Face Detection Based on Viola-Jones Algorithm Applying Composite Features2019
- A Smartphone-Based Drowsiness Detection and Warning System for Automotive DriversIEEE Transactions on Intelligent Transportation Systems, 2018
- An improved fatigue detection system based on behavioral characteristics of driver2017
- Real-Time Driver Drowsiness Detection for Embedded System Using Model Compression of Deep Neural Networks2017
- EEG-Based Real-Time Drowsiness Detection Using Hilbert-Huang Transform2015
- Eye tracking based driver fatigue monitoring and warning system2011
- The Monitoring Method of Driver's Fatigue Based on Neural Network2007