Fatigue driving detection based on Haar feature and extreme learning machine

doi:10.1016/S1005-8885(16)60050-X

中国邮电高校学报(英文版) ›› 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

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/Abstract

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

Zheng CHANG Xiaojuan Ban Yu WANG. Fatigue driving detection based on Haar feature and extreme learning machine[J]. JOURNAL OF CHINA UNIVERSITIES OF POSTS AND TELECOM, 2016, 23(4): 91-100.

参考文献

1. Lu K. A study on OpenCV-based algorithms for face detection and tracking. Master Thesis. Shanghai, China: East China University of Science and Technology, 2015 (in Chinese) 2. Yang W L, Zheng J Y, Zhan C, et al. Pupil localization algorithm based on Kinect sensor. Transducer and Microsystem Technologies, 2015, 34(2): 125?128 (in Chinese) 3. Zhu Z Z, Wang W, Duan X D, et al. Real-time detection of facial eye status based on Kinect sensor. Journal of Dalian Nationalities University, 2015, 17(1): 81?84 (in Chinese) 4. Viola P, Jones M J. Robust real-time object detection. CRL 2001/01. Cambridge, MA, USA: Cambridge Research Laboratory, 2001: 25p 5. Dai B, Wu X F, Wang B. A visual saliency model based on Haar like featuress and structural complexity. Journal of Fudan University (Natural Science), 2014, 53(5): 651?658 (in Chinese) 6. Gao Y. Human movement detection based on Haar features. Master Thesis. Changchun, China: Jilin University, 2013 (in Chinese) 7. Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: a new learning scheme of feedforward neural networks. Proceedings of the 2004 IEEE International Joint Conference on Neural Networks (IJCNN’04): Vol 2, Jul 25?29, 2004, Budapest, Hungary. Piscataway, NJ, USA: IEEE, 2004: 985?990 8. Lienhart R, Maydt J. An extended set of Haar-like feature for rapid object detection. Proceedings of the 2002 International Conference on Image Processing (ICIP’02): Vol 1, Sept 10?13, 2002, Vancouver, Canada. Piscataway, NJ, USA: IEEE, 2002: 900?903 9. Lienhart R，Kuranov A，Pisarevsky V. Empirical analysis of detection cascades of boosted classifiers for rapid object detection. Pattern Recognition: Proceedings of the 25th DAGM Symposium. Sept 10?12, 2003, Magdeburg, Germany. LNCS 2781. Berlin, Germany: Springer, 2003: 297?304 10. Huang G F, Cheng X P, Ren F. An automatic recognition approach of human gestures. Journal of Southwest China Normal University, 2010, 35(4): 136?140 (in Chinese) 11. Guo K, Ishwar P, Konrad J. Action recognition using sparse representation of covariance manifold of optical flow. Proceedings of the 7th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS’10), Aug 29-Sept 1, 2010, Boston, MA, USA. Piscataway, NJ, USA: IEEE, 2010: 188?195 12. Gu Y, Liu J F, Chen Y Q, et al. Constraint online sequential extreme learning machine for lifelong indoor localization system. Proceedings of the 2014 International Joint Conference on Neural Networks (IJCNN’14), Jul 6-11, 2014, Beijing, China. Piscataway, NJ, USA: IEEE, 2014: 732?738 13. Chang Z, Ban X J, Shen Q, et al. Research on three-dimensional motion history image model and extreme learning machine for human body movement trajectory recognition. Mathematical Problems in Engineering, 2015: ID 528190/ 1?15 14. Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications. Neurocomputing, 2006, 70(1/2/3): 489?501 15. Chang Z, Ban X J, Liu X. Recognition of human head movement trajectory based on the three-dimensional somatosensory technology. Knowledge Engineering and Management: Proceedings of the 7th International Conference on Intelligent Systems and Knowledge Engineering (ISK’12), Dec 15?17, 2012, Beijing, China. Advances in Intelligent Systems and Computing 214. Berlin, Germany: Springer, 2014: 611?622

Fatigue driving detection based on Haar feature and extreme learning machine

Fatigue driving detection based on Haar feature and extreme learning machine

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价