State-of-the-Art Analysis of Modern Drowsiness Detection Algorithms Based on Computer Vision
The paper presented a state-of-the-art analysis of modern drowsiness detection algorithms based on computer vision technologies as well as consider the problem of yawning detection for the vehicle driver. Based on the literature analysis we classify drowsiness detection techniques into three groups:...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
FRUCT
2021-05-01
|
Series: | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
Subjects: | |
Online Access: | https://www.fruct.org/publications/fruct29/files/Has.pdf |
Summary: | The paper presented a state-of-the-art analysis of modern drowsiness detection algorithms based on computer vision technologies as well as consider the problem of yawning detection for the vehicle driver. Based on the literature analysis 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. So, the computer vision methods look most promising since they are non-intrusive for the driver. The importance of the driver drowsiness monitoring system is due to the number of drowsiness-related accidents. Yawning is an important identifier of drowsiness, even 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. |
---|---|
ISSN: | 2305-7254 2343-0737 |