基于树莓派的眼部疲劳状态实时监测系统  

A Real-time Monitoring System for Eye Fatigue Based on Raspberry Pi

作　　者：林虹 吴良峰 LIN Hong;WU Liangfeng(Department of Information Engineering, Yango University,Fuzhou, Fujian 350015, China;Underlying Platform Center, Fuzhou Rockchips Electronics CO.Ltd., Fuzhou, Fujian 350003, China)

机构地区：[1]阳光学院信息工程学院,福建福州350015 [2]福州瑞芯微电子股份有限公司底层平台中心,福建福州350003

出　　处：《闽江学院学报》2019年第2期76-83,共8页Journal of Minjiang University

基　　金：福建省中青年教师教育科研项目(JA15628)

摘　　要：为了更加高效、便捷地获取驾驶员的精神状态,提出一种硬件结构简单、开发成本较低的疲劳状态实时监测系统。该系统采用树莓派开发板和Python语言进行实现,对OpenCV进行优化后,利用Dlib库的人脸68点标记模型完成脸部和眼部特征点定位,并利用EAR算法计算眼部特征状态对应的EAR参数,以此作为疲劳状态检测的依据。最后在机动车上配备系统进行实车模拟测试,实验结果表明,该系统检测准确率高并有很好的实时性。In order to get the driver’s mental state more efficiently and conveniently, a real-time monitoring system for fatigue state is presented, which has simple hardware structure and low development cost. The system is implemented with raspberry development board and Python language. After optimizing the OpenCV, the face and eye feature points are located using the 68 point mark model of the face of the Dlib library, and the EAR algorithm is used to calculate the EAR parameters corresponding to the eye feature state, which is used as the basis of the fatigue state detection. Finally, the vehicle is equipped with a system for real vehicle simulation test. The experimental results show that the system has high detection accuracy and good real-time performance.

关 键 词：疲劳检测 眼部纵横比 树莓派 OPENCV PYTHON 

分 类 号：U463.6[机械工程—车辆工程] TP391.41[交通运输工程—载运工具运用工程]