基于流形保持投影的驾驶疲劳识别

张伟; 夏利民; 罗大庸

基于流形保持投影的驾驶疲劳识别

中南大学信息科学与工程学院,湖南,长沙,410075

基金项目: 国家自然科学基金资助项目（50808025）；国家博士点基金资助项目（20090162110057）；湖南省教育厅重点项目（08a003）

详细信息

作者简介:
张伟（1972- ），男，博士生，讲师．研究领域为交通信息与控制．
夏利民（1963- ），男，博士，教授，博士生导师．研究领域为模式识别与图像处理．
罗大庸（1944- ），男，教授，博士生导师．研究领域为控制理论．

中图分类号: TP391.41
计量
- 文章访问数: 1977
- HTML全文浏览量: 0
- PDF下载量: 246
出版历程
- 收稿日期: 2009-12-13
- 修回日期: 2010-05-16
- 发布日期: 2011-02-19

Driver Fatigue Recognition Based on Manifold Preserving Projections

College of Information Science and Engineering, Central South University, Changsha 410075, China

摘要

摘要: 提出了一种基于流形保持投影的驾驶疲劳识别方法．利用光流技术计算人脸皮层的运动速度，并以此作为疲劳特征；为了有效地进行疲劳特征提取（即特征降维），在保局投影的基础上，将数据的非近邻信息引入目标函数中，提出了流形保持投影方法，有效地保持了疲劳数据的局部流形结构和全局流形结构，同时利用格拉姆—施密特正交化过程解决了保局投影非正交问题．实验结果表明该方法具有很好的识别效果．
- 疲劳识别 /
- 光流 /
- 保局投影 /
- 流形保持投影
Abstract: A new method for driver fatigue recognition based on manifold preserving projections(MPP) is presented. Facial velocity information,which is determined using optical flow techniques,is used to characterize fatigue.The manifold preserving projections are proposed to extract the effective fatigue feature(viz.dimensionality reduction).The method incorporates the non-locality information of data into the objective function of locality preserving projection(LPP),which preserve the local and global structure of the data manifold,and Gram-Schmidt orthogonalization is used to solve non-orthogonal problem of LPP.The experiments show that the proposed method attains a satisfactory recognition effect.
- fatigue recognition /
- optical flow /
- locality preserving projections /
- manifold preserving projections

HTML全文

参考文献(11)

[1]	Yang G,Lin Y,Bhattacharya P.A driver fatigue recognition model using fusion of multiple features[C]//IEEE International Conference on Systems,Man and Cybernetics:vol.2.Piscat-away,NJ,USA:IEEE,2005:1777-1784
[2]	Eriksson M,Papanikotopoulos N P.Eye-tracking for detection of driver fatigue[C]//IEEE Conference on Intelligent Transportation System.Piscataway,NJ,USA:IEEE,1997:314-319
[3]	王荣本,郭克友,储江伟.一种基于Gabor小波的驾驶员眼部状态识别方法的研究[J].中国图象图形学报,2003,8(9):1043-1047.Wang R B,Guo K Y,Chu J W.Study on method of recognizing driver's eye state base on Gabor wavelet in driver behavior surveillance[J].Journal of Image and Graphics,2003,8(9):1043-1047
[4]	Ji Q,Yang X J.Real-time eye,gaze,and face pose tracking for monitoring driver vigilance[J].Real-Time Imaging,2002,8(5):357-377
[5]	李志春.驾驶员疲劳状态识别检测技术研究与工程实现[D].镇江:江苏大学,2009.Li Z C.Research on driver's fatigue status detection technology and realization in engineering[D].Zhenjiang:Jiangsu University,2009
[6]	李衡峰.基于综合集成的驾驶疲劳识别[D].长沙:中南大学,2005.Li H F.Driver's fatigue recognition basde on metasynthesis[D].Changsha:Central South University,2005
[7]	Yin B C,Fan X,Sun Y F.Multiscale dynamic features based driver fatigue detection[J].International Journal of Pattern Recognition and Artificial Intelligence,2009,23(3):3575-3589
[8]	Anderson K,McOwan P W.A real-time automated system for the recognition of human facial expressions[J].IEEE Transactions on Systems,Man,and Cybernetics-Part B:Cybernetics,2006,36(1):96-105
[9]	Horn B K P,Schunck B G.Determining optical flow[J].Artificial Intelligence,1981,17(1/2/3):185-204
[10]	He X F,Niyogi P.Locality preserving projections[C]//Annual Conference on Neural Information Processing Systems:vol.16.Cambridge,MA,USA:MIT Press,2003:153-160
[11]	夏利民,张良春.基于自适应粒子滤波器的物体跟踪[J].中国图象图形学报,2009,14(1):112-117.Xia L M,Zhang L C.Object tracking based on adaptive particle filter[J].Journal of Image and Graphics,2009,14(1):112-117.

施引文献

资源附件(0)

计量

文章访问数: 1977
HTML全文浏览量: 0
PDF下载量: 246
被引次数: 0

基于流形保持投影的驾驶疲劳识别

计量

出版历程

Driver Fatigue Recognition Based on Manifold Preserving Projections

计量

出版历程

目录