疲劳驾驶检测中基于稀疏表示的眼睛状态识别研究

doi:10.7517/j.issn.1674-0475.2016.01.095

影像科学与光化学 ›› 2016, Vol. 34 ›› Issue (1): 95-101.DOI: 10.7517/j.issn.1674-0475.2016.01.095

疲劳驾驶检测中基于稀疏表示的眼睛状态识别研究

王冬梅, 冯偲, 王海鹏, 于微波

长春工业大学电气与电子工程学院, 吉林长春 130012

收稿日期:2015-10-08 修回日期:2015-11-23 出版日期:2016-01-15 发布日期:2016-01-15
通讯作者: 王冬梅
基金资助:
吉林省科技发展计划项目(20120434)资助

Eye State in Drive Fatigue Detection Based on Sparse Representation

WANG Dongmei, FENG Cai, WANG Haipeng, YU Weibo

Institute of Electrical and Electronic Engineering, Changchun University of Technology, Changchun 130012, Jilin, P. R. China

Received:2015-10-08 Revised:2015-11-23 Online:2016-01-15 Published:2016-01-15

摘要/Abstract

摘要：

为了解决传统接触式疲劳驾驶检测方法影响驾驶、检测算法识别率较低等问题,本文提出一种基于稀疏表示的眼睛状态识别的方法。利用K-SVD(K均值奇异值分解)方法对输入的训练集构造过完备冗余字典,利用正交匹配追踪法对测试的图像进行稀疏表示,然后根据重构图像和测试图像之间的误差,确定测试图像所属的类别,判断出测试图像的状态。实验中将K-SVD和OMP(正交匹配追踪)方法与其它字典学习和稀疏表示方法进行对比,结果表明,利用K-SVD字典学习算法结合OMP算法获得了较好的识别效果。

关键词: 疲劳驾驶, 人眼状态, 稀疏表示, K-SVD, OMP

Abstract:

In this paper, we proposed an eyes state in driver fatigue recognition algorithm based on sparse representation in order to solve the problems that in traditional contact detection, just like affect driver, low recognition rate, etc. First,construct a complete redundant dictionary to training set using K-SVD method and sparse representation the test images employing orthogonal matching pursuit method. Then determine the error between the test images and the reconstructed images. At last,determine the type of test images and judge the state of test images. And contrast the K-SVD to the other dictionary learning methods and sparse representation methods, the experimental results showedthat the K-SVD algorithm combined with OMP obtained better recognition effect.

Key words: driver fatigue, eye state, sparse representation, K-SVD, OMP

王冬梅, 冯偲, 王海鹏, 于微波. 疲劳驾驶检测中基于稀疏表示的眼睛状态识别研究[J]. 影像科学与光化学, 2016, 34(1): 95-101.

WANG Dongmei, FENG Cai, WANG Haipeng, YU Weibo. Eye State in Drive Fatigue Detection Based on Sparse Representation[J]. Imaging Science and Photochemistry, 2016, 34(1): 95-101.

参考文献

[1] Wierwille W W, Ellsworth L A, Wreggit S S, Fairbanks R J, Kirn C L. Research on vehicle-based driver status/performance monitoring; development, validation, and refinement of algorithms for detection of driver drowsiness. Final report[R]. U.S. Department of Transportation.1994.
[2] 高晓晶. 司机疲劳状况监控系统的研究与实现[D]. 电子科技大学, 2009. Gao X J.Research and implementation of driver fatigue monitoring system[D]. University of Electronic Science and Technology, 2009.
[3] Thorne D R, Johnson D E, Redmond D P, Sing H C, Belenky G, Shapiro J M. The Walter Reed palm-held psychomotor vigilance test[J]. Behavior Research Methods, 2005,37(1): 111-118.
[4] 陈信.鉴定疲劳的方法研究[J].航天医学工程研究所论文汇编,1978,1(1):1-10. Chen X. Method for identification of fatigue[J]. Compilation of Papers, Space Medical Engineering Institute,1978,1(1):1-10.
[5] 阎淑芳,呼庆媛,贾正锐.机动车驾驶员操作技能分析[J].人类工效学, 1997,3(2): 60-61. Yan S F, Hu Q Y, Jia Z R. Analysis of motor vehicle driver's operation skill[J]. Chinese Journal of Ergonomics, 1997,3(2): 60-61.
[6] 李立凌.基于人眼定位技术的疲劳驾驶检测方法[D].电子科技大学, 2012. Li L L.Fatigue driving detection method based on the human eye positioning technology[D]. University of Electronic Science and Technology, 2012.
[7] Li Q, Song K. The realization and software design of fatigue driving early warning device[J]. Journal of Liaoning University: Natural Science Edition, 2004,30(4): 367-369.
[8] 杨彬,黄耀志.基于PERCLOS的汽车司机疲劳监控方法的研究[J].微计算机信息, 2005,21(08): 119-121. Yang B, Huang Y Z. Research on fatigue monitoring method of automobile driver based on PERCLOS[J]. Micro Computer Information, 2005,21(08): 119-121.
[9] 王磊,周乐囡,姬红兵.一种面向信号分类的匹配追踪新方法[J].电子与信息学报, 2014,36(6): 1299-1306. Wang L, Zhou L N, Ji H B. A new method of matching pursuit based on signal classification[J]. Journal of Electronic and Information, 2014,36(6): 1299-1306.
[10] 马小薇.基于压缩感知的OMP图像重构算法改进[J].电子科技, 2015,4: 014. Ma X W. Improvement of OMP image reconstruction algorithm based on compressed sensing[J]. Electronic Science and Technology, 2015,4: 014.
[11] Haupt J, Nowak R. Signal reconstruction from noisy random projections[J]. Information Theory, IEEE Transactions on, 2006,52(9): 4036-4048.
[12] Huang J, Huang X, Metaxas D. Learning with dynamic group sparsity[C]. Computer Vision, 2009 IEEE 12th International Conference on. IEEE, 2009: 64-71.
[13] Mairal J, Bach F, Ponce J, Sapiro G. Online dictionary learning for sparse coding[C]. Proceedings of the 26th Annual International Conference on Machine Learning. ACM, 2009: 689-696.
[14] 郎利影,王勇,李思骞.基于压缩感知OMP改进算法的图像重构[J].电视技术, 2015,39(6): 8-12. Lang L Y, Wang Y, Li S Q. Image reconstruction based on compressed sensing OMP algorithm[J]. TV Technology, 2015,39(6): 8-12.
[15] 练秋生,石保顺,陈书贞.字典学习模型,算法及其应用研究进展[J].自动化学报, 2015,41(2): 240-260. Lian Q S, Shi B S, Chen S Z. Research progress of dictionary learning model, algorithm and its application[J]. Automation Journal, 2015,41(2): 240-260.
[16] 王小娜.基于字典学习的图像稀疏表示及其在压缩感知中的应用[D].燕山大学, 2013. Wang X N .Image sparse representation based on dictionary learning and its application in compressed sensing[D].Yanshan University, 2013.
[17] 赵广銮.稀疏表示在图像识别中的应用[D].北京邮电大学, 2013. Zhao G L. Application of sparse representation in image recognition[D]. Beijing University of Posts and Telecommunications. 2013.
[18] 孙锐,王晶晶.一种基于核K-SVD和稀疏表示的车辆识别方法[J].模式识别与人工智能, 2014, 5: 007. Sun R,Wang J J. A vehicle identification method based on kernel K-SVD and sparse representation[J]. Pattern Recognition and Artificial Intelligence, 2014, 5: 007.

疲劳驾驶检测中基于稀疏表示的眼睛状态识别研究

Eye State in Drive Fatigue Detection Based on Sparse Representation

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	TONG Zhenhe(TUNG Chenho), WU Lizhu. Y-TYPE ZEOLITES AS MICRO-REACTORS FOR PHOTOCHEMICAL PREPARATION OF LARGE-RING COMPOUNDS[J]. 影像科学与光化学, 1996, 14(1): 4-9.
[2]	TONG ZHEN-HE, WU LI-ZHU. CATION-ENHANCED INTRAMOLECULAR PHOTODIMERI-ZATION AND EXCIMER FORMATION OF POLYE-THERS BEARING NAPHTHALE CHROMOPHORES[J]. 影像科学与光化学, 1994, 12(4): 318-321.