期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2015
卷号：8
期号：10
页码：107-114
DOI：10.14257/ijsip.2015.8.10.12
出版社：SERSC
摘要：Driver fatigue detection based on one feature is usually inaccurate. To solve the problem, a method of driver fatigue detection based on multi-features is proposed. We have analyzed the relationship between driver facial features, driving routes and vehicle handing behavior. Data of three features are collected by driving simulator and divided into two levels of awake and fatigue based on driver subjective assessment. After being discretized and normalized, the partial data is as the input data of neural network. The neural network is trained by BP algorithm. Other data is as the test samples. Experimental results show that compared with one feature, the method has higher accuracy rate and lower false positive rate
