中国邮电高校学报(英文) ›› 2016, Vol. 23 ›› Issue (4): 91-100.doi: 10.1016/S1005-8885(16)60050-X

• Others • 上一篇    

Fatigue driving detection based on Haar feature and extreme learning machine

常征,王宇,班晓娟   

  1. 北京科技大学
  • 收稿日期:2015-11-25 修回日期:2016-04-28 出版日期:2016-08-30 发布日期:2016-08-30
  • 通讯作者: 班晓娟 E-mail:banxj@ustb.edu.cn
  • 基金资助:
    中国国家自然科学基金;中国国家自然科学基金;中央高校基本科研业务费专项资金;教育部新世纪人才计划;中国国家博士后科研基金

Fatigue driving detection based on Haar feature and extreme learning machine

Zheng CHANG1,Yu WANG2,   

  • Received:2015-11-25 Revised:2016-04-28 Online:2016-08-30 Published:2016-08-30
  • Supported by:
    ;Fundamental Research Funds for the Central Universities;New century personnel plan for the Ministry of Education;China Post-doctoral Science Foundation

摘要: As the significant branch of intelligent vehicle networking technology, the intelligent fatigue driving detection technology has been introduced into the paper in order to recognize the fatigue state of the vehicle driver and avoid the traffic accident. The disadvantages of the traditional fatigue driving detection method have been pointed out when we study on the traditional eye tracking technology and traditional artificial neural networks. On the basis of the image topological analysis technology, Haar like features and extreme learning machine algorithm, a new detection method of the intelligent fatigue driving has been proposed in the paper. Besides, the detailed algorithm and realization scheme of the intelligent fatigue driving detection have been put forward as well. Finally, by comparing the results of the simulation experiments, the new method has been verified to have a better robustness, efficiency and accuracy in monitoring and tracking the drivers’ fatigue driving by using the human eye tracking technology.

关键词: Haar feature, extreme learning machine, fatigue driving detection

Abstract: As the significant branch of intelligent vehicle networking technology, the intelligent fatigue driving detection technology has been introduced into the paper in order to recognize the fatigue state of the vehicle driver and avoid the traffic accident. The disadvantages of the traditional fatigue driving detection method have been pointed out when we study on the traditional eye tracking technology and traditional artificial neural networks. On the basis of the image topological analysis technology, Haar like features and extreme learning machine algorithm, a new detection method of the intelligent fatigue driving has been proposed in the paper. Besides, the detailed algorithm and realization scheme of the intelligent fatigue driving detection have been put forward as well. Finally, by comparing the results of the simulation experiments, the new method has been verified to have a better robustness, efficiency and accuracy in monitoring and tracking the drivers’ fatigue driving by using the human eye tracking technology.

Key words: Haar feature, extreme learning machine, fatigue driving detection