State-of-the-Art Analysis of Modern Drowsiness Detection Algorithms Based on Computer Vision
Authors:
- Fudail HasanFHFudail Hasan
- Alexey KashevnikAKAlexey Kashevnik
- 12 May 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 141-149
Abstract
The paper presents a state-of-the-art analysis of modern drowsiness detection algorithms based on computer vision technologies as well as considers the problem of yawning detection for the vehicle driver. Based on the analysis of the literature we classify drowsiness detection techniques into three groups: the driving pattern of the vehicle; psychophysiological characteristics of drivers; and computer vision techniques for driver monitoring. The computer vision methods look most promising since they are non-intrusive for the driver. The importance of the driver drowsiness monitoring system rises from the number of drowsiness-related accidents. Yawning is an important identifier of drowsiness, even though it is not the most reliable drowsiness indicator. Some of the methods that are based on computer vision are presented and discussed in the paper. We developed and evaluated a yawning detection model. We analyzed available datasets for yawning detection and conclude that the existing datasets have to be enhanced by pictures taken in real driving conditions. We propose yawning detection dataset-preparation as well as detection model development and evaluation.Keywords
Funding Information
- Russian Foundation for Basic Research (19-29-06099)
- ITMO University
This publication has 31 references indexed in Scilit:
- An Accurate ECG-Based Transportation Safety Drowsiness Detection SchemeIEEE Transactions on Industrial Informatics, 2016
- The ULg multimodality drowsiness database (called DROZY) and examples of use2016
- EOG-based drowsiness detection using convolutional neural networks2014
- Detecting driver drowsiness using feature-level fusion and user-specific classificationExpert Systems with Applications, 2014
- Hybrid method based on topography for robust detection of iris center and eye cornersACM Transactions on Multimedia Computing, Communications, and Applications, 2013
- EEG-based drowsiness detection for safe driving using chaotic features and statistical testsJournal of Medical Signals & Sensors, 2011
- Rapid object detection using a boosted cascade of simple features2005
- Real-Time Nonintrusive Monitoring and Prediction of Driver FatigueIEEE Transactions on Vehicular Technology, 2004
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004
- Method of detecting drowsiness level by utilizing blinking durationJSAE Review, 1996