Detection and Analysis of Driver Drowsiness
Driver drowsiness is one of the major causes of road accidents. An estimated number of 1.2 million crashes, 8,000 lost lives, 500,000 injuries annually relates to drowsy-driving. From the information provided by a number of statistical reports, it can be proven that a large number of fatalities is c...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2019
|
| Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85063518320&doi=10.1109%2fICEEST.2018.8643326&partnerID=40&md5=f7ff02e573eefe623826a1fb212168c4 http://eprints.utp.edu.my/23555/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Driver drowsiness is one of the major causes of road accidents. An estimated number of 1.2 million crashes, 8,000 lost lives, 500,000 injuries annually relates to drowsy-driving. From the information provided by a number of statistical reports, it can be proven that a large number of fatalities is caused by driver drowsiness. In earlier researches, to estimate the level of drowsiness, the measures to be focused on are single measures either vehicle-based, physiological measure, behavioural measure or subjective measure. This paper analyses two single measures which includes physiological and behavioural measures such as EEG signals and video sequences together. Features extracted from EEG signals are the Delta, Theta and Alpha frequency bands which includes Delta power (P-(δ-Abs)), Theta power (P-(θ-Abs)) and Alpha power (P-(α-Abs)). Features extracted from the video sequences are eyes state specifically the eye closure. With the obtained features extracted, the significant features are combined with the physiological measure chosen to be measured to be the Theta band since it has previously been related to the drowsy state for numerous researches. The behavioural measure chosen are the eye states which are the eye closures. The results obtained through this research for the single physiological measure has an accuracy of 91 for all frequency bands. The behavioural measure obtained shows the eye opening and closing of the eyes. After fusing both the measures, one subject shows the most accurate detection of drowsiness. Three subjects give a contradictory result in detecting drowsiness. Overall, this study shows that EEG frequency band powers and eye closure can be used to infer drowsiness. Thus the study shows a promising prospect of detecting drowsiness and alerting the driver with an alarm. © 2018 IEEE. |
|---|