Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 6, Issue 3, 2022

Fatigue driving and distraction detection system based on machine vision

Download as PDF

DOI: 10.23977/acss.2022.060303 | Downloads: 39 | Views: 906

Author(s)

Hongzhao Chen 1, Ziyi Luo 1, Yuxuan Feng 1, Xiaoyang Wang 1, Chunyou Lin 1

Affiliation(s)

1 Dongguan University of Technology, Dongguan 523000, Guangdong Province, China

Corresponding Author

Chunyou Lin

ABSTRACT

The development of automobiles has brought great convenience to people's travel. However, the rapid increase in the number of vehicles leads to the increase of traffic accidents. Fatigue and distracted driving has become the important factor causing traffic accidents, and the detection of fatigue driving technology has gradually attracted the attention of researchers. In order to cope with different road conditions and complex in-vehicle environments, methods based on multi sensor have become the mainstream for application to driving detection, however, different driving habits and environments may lead to false information. In this paper, we propose an integrated-information method based on machine vision and deep learning, the Dlib library with 68 features is used to map the face, PERCLOS method is used to calculate the EAR (eye aspect ratio) and MAR (mouth aspect ratio) to evaluate the fatigue level of the face, also, we turn the key points of the 2D face into the 3D face model, and calculate the Euler angle of the head position in real time. A Yolov5 target-detected algorithm is used to identify and warn distracted behaviors such as smoking, drinking, and using mobile phones. The training accuracy reaches 90.23%, and the total detection frame rate is 4.78 frames per second. In our system, a UI is designed based on Wxpython, and thresholds such as eyes-closed and mouth-closed behaviors could be set in real time through a human-computer interface, the mode of monitoring behavior could be switched and the abnormal driving data will be recorded at the same time. The detection system designed in this paper is mainly divided into three parts: facial feature detection, head position prediction, distracted behaviors detection which realizes the evaluation and warning of the driver's fatigue driving and distracted state.

KEYWORDS

Fatigue driving, deep learning, face detection, target detection

CITE THIS PAPER

Hongzhao Chen, Ziyi Luo, Yuxuan Feng, Xiaoyang Wang, Chunyou Lin, Fatigue driving and distraction detection system based on machine vision. Advances in Computer, Signals and Systems (2022) Vol. 6: 19-25. DOI: http://dx.doi.org/10.23977/acss.2022.060303.

REFERENCES

[1] Li Duhou, Liu Qun, Yuan Wei et al.Relationship between fatigue driving and traffic accidents [J]. Journal of Transportation Engineering, 2010 (4): 104109.
[2] Shuang Shuang Lv. Review of patented techniques of fatigue driving based on image analysis [J]. China Science and Technology Information 2018 (17): 17-19.
[3] Lizhen Xu. Research on fatigue driving detection technology [J]. The Internet of Things Tech, 2017, 7(04):95-96+98. DOI:10.16667/j.issn.2095-1302.2017.04.031.
[4] Fu R, Wang H, Zhao W. Dynamic driver fatigue detection using hidden Markov model in real driving condition[J]. Expert Systems with Applications, 2016, 63: 397-411.
[5] Sangeetha M, Kalpanadevi S. Driver Fatigue Management System using Embedded ECG Sensor[J]. International Journal for Scientific Research & Development, 2015(4): 1220-1224.
[6] Jian W, Bing L. Design and Simulated Implementation of MATLAB-Based Warning System for Fatigue Driving Driver[C]// Ninth International Conference on Hybrid Intelligent Systems. IEEE, 2009:467-470.
[7] X.-Y. Gao, Y.-F. Zhang, W.-L. Zheng, et al., Neural Engineering (NER), 2015 7th International IEEE/EMBS Conference on (IEEE, 2015), 767–770 (2015) 
[8] LEE K, HYUN S A E, OAH S. Detecting driver fatigue by steering wheel grip force[J]. International Journal of Contents, 2016, 12(1): 44-48.
[9] T Soukupova´, Ech J C. Real-Time Eye Blink Detection using Facial Landmarks. 2016.
[10] M. Mao, L. Du, Vehicular Electronics and Safety, 2007. ICVES. IEEE International Conference on (IEEE, 2007), 1–4 (2007).

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 15977
Visits: 270910

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.