Sleep Technology for Driving Safety

Sei-Wang Chen, Kuo Peng Yao, Hui Wen Lin

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

In this chapter, a vision system for monitoring driver vigilance is presented. The level of vigilance is determined by integrating a number of facial parametric values including: percentage of eye closure over time, average eye closure duration, eye blinking frequency, average degree of gaze, average duration of mouth openness and head nodding frequency. Initially, facial features including the eyes, mouth and head are first located in the input video sequence. They are then tracked over subsequent images. Facial parameters are estimated during facial feature tracking. A number of video sequences having drivers of both sex and of different ages under various illuminations and road conditions are employed to test the performance of the proposed system. Finally, we suggest future work on how to extend the system in terms of both efficiency and effectiveness.

Original languageEnglish
Title of host publicationIntelligent Systems, Control and Automation
Subtitle of host publicationScience and Engineering
PublisherSpringer Netherlands
Pages219-243
Number of pages25
DOIs
Publication statusPublished - 2012 Jan 1

Publication series

NameIntelligent Systems, Control and Automation: Science and Engineering
Volume64
ISSN (Print)2213-8986
ISSN (Electronic)2213-8994

Fingerprint

Sleep
Driver
Closure
Lighting
Safety
Feature Tracking
Monitoring
Time-average
Vision System
Percentage
Illumination

Keywords

  • Driver vigilance monitoring system
  • Facial feature detection and tracking
  • Facial parameter estimation
  • Fuzzy reasoning
  • Vision system

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Mechanical Engineering
  • Computer Science Applications
  • Control and Optimization

Cite this

Chen, S-W., Yao, K. P., & Lin, H. W. (2012). Sleep Technology for Driving Safety. In Intelligent Systems, Control and Automation: Science and Engineering (pp. 219-243). (Intelligent Systems, Control and Automation: Science and Engineering; Vol. 64). Springer Netherlands. https://doi.org/10.1007/978-94-007-5470-6_12

Sleep Technology for Driving Safety. / Chen, Sei-Wang; Yao, Kuo Peng; Lin, Hui Wen.

Intelligent Systems, Control and Automation: Science and Engineering. Springer Netherlands, 2012. p. 219-243 (Intelligent Systems, Control and Automation: Science and Engineering; Vol. 64).

Research output: Chapter in Book/Report/Conference proceedingChapter

Chen, S-W, Yao, KP & Lin, HW 2012, Sleep Technology for Driving Safety. in Intelligent Systems, Control and Automation: Science and Engineering. Intelligent Systems, Control and Automation: Science and Engineering, vol. 64, Springer Netherlands, pp. 219-243. https://doi.org/10.1007/978-94-007-5470-6_12
Chen S-W, Yao KP, Lin HW. Sleep Technology for Driving Safety. In Intelligent Systems, Control and Automation: Science and Engineering. Springer Netherlands. 2012. p. 219-243. (Intelligent Systems, Control and Automation: Science and Engineering). https://doi.org/10.1007/978-94-007-5470-6_12
Chen, Sei-Wang ; Yao, Kuo Peng ; Lin, Hui Wen. / Sleep Technology for Driving Safety. Intelligent Systems, Control and Automation: Science and Engineering. Springer Netherlands, 2012. pp. 219-243 (Intelligent Systems, Control and Automation: Science and Engineering).
@inbook{644e9f03313b4584b879cb1c3798072c,
title = "Sleep Technology for Driving Safety",
abstract = "In this chapter, a vision system for monitoring driver vigilance is presented. The level of vigilance is determined by integrating a number of facial parametric values including: percentage of eye closure over time, average eye closure duration, eye blinking frequency, average degree of gaze, average duration of mouth openness and head nodding frequency. Initially, facial features including the eyes, mouth and head are first located in the input video sequence. They are then tracked over subsequent images. Facial parameters are estimated during facial feature tracking. A number of video sequences having drivers of both sex and of different ages under various illuminations and road conditions are employed to test the performance of the proposed system. Finally, we suggest future work on how to extend the system in terms of both efficiency and effectiveness.",
keywords = "Driver vigilance monitoring system, Facial feature detection and tracking, Facial parameter estimation, Fuzzy reasoning, Vision system",
author = "Sei-Wang Chen and Yao, {Kuo Peng} and Lin, {Hui Wen}",
year = "2012",
month = "1",
day = "1",
doi = "10.1007/978-94-007-5470-6_12",
language = "English",
series = "Intelligent Systems, Control and Automation: Science and Engineering",
publisher = "Springer Netherlands",
pages = "219--243",
booktitle = "Intelligent Systems, Control and Automation",
address = "Netherlands",

}

TY - CHAP

T1 - Sleep Technology for Driving Safety

AU - Chen, Sei-Wang

AU - Yao, Kuo Peng

AU - Lin, Hui Wen

PY - 2012/1/1

Y1 - 2012/1/1

N2 - In this chapter, a vision system for monitoring driver vigilance is presented. The level of vigilance is determined by integrating a number of facial parametric values including: percentage of eye closure over time, average eye closure duration, eye blinking frequency, average degree of gaze, average duration of mouth openness and head nodding frequency. Initially, facial features including the eyes, mouth and head are first located in the input video sequence. They are then tracked over subsequent images. Facial parameters are estimated during facial feature tracking. A number of video sequences having drivers of both sex and of different ages under various illuminations and road conditions are employed to test the performance of the proposed system. Finally, we suggest future work on how to extend the system in terms of both efficiency and effectiveness.

AB - In this chapter, a vision system for monitoring driver vigilance is presented. The level of vigilance is determined by integrating a number of facial parametric values including: percentage of eye closure over time, average eye closure duration, eye blinking frequency, average degree of gaze, average duration of mouth openness and head nodding frequency. Initially, facial features including the eyes, mouth and head are first located in the input video sequence. They are then tracked over subsequent images. Facial parameters are estimated during facial feature tracking. A number of video sequences having drivers of both sex and of different ages under various illuminations and road conditions are employed to test the performance of the proposed system. Finally, we suggest future work on how to extend the system in terms of both efficiency and effectiveness.

KW - Driver vigilance monitoring system

KW - Facial feature detection and tracking

KW - Facial parameter estimation

KW - Fuzzy reasoning

KW - Vision system

UR - http://www.scopus.com/inward/record.url?scp=85042944632&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042944632&partnerID=8YFLogxK

U2 - 10.1007/978-94-007-5470-6_12

DO - 10.1007/978-94-007-5470-6_12

M3 - Chapter

T3 - Intelligent Systems, Control and Automation: Science and Engineering

SP - 219

EP - 243

BT - Intelligent Systems, Control and Automation

PB - Springer Netherlands

ER -