基于嵌入式平台人眼疲劳检测终端的设计与实现  

Design and implementation of human-eye fatigue detection terminal based on Android platform

作　　者：李春杰[1] 王春[1] 王全虎[1] 

机构地区：[1]中国科学技术大学软件学院,江苏苏州215123

出　　处：《现代电子技术》2016年第24期6-8,13,共4页Modern Electronics Technique

基　　金：苏州市应用基础研究项目(SYG201543);江苏省科技项目-基础研究计划(自然科学基金)(BK20141209)

摘　　要：设计并实现一套基于Android平台的人眼疲劳检测终端。从摄像头中获取驾驶员的脸部图像数据,快速识别并定位到人脸部。再进行人眼部的定位,利用最大类间法Otsu对人眼进行目标提取以及Robert Cross边缘检测获得人眼的轮廓,从而进行人眼状态分析;利用PERCLOS原理进行疲劳的状态判断,并且借助开源视觉库Android-Open CV提高了系统的开发效率。在室内环境的实验结果表明该终端的表现良好。A human-eye fatigue detection terminal based on Android platform was designed and implemented. It can acquire the driver＇s face image data from the camera, recognize and locate quickly the face, and then locate the eyes. The Otsu is used to extract the human-eye target and the Robert Cross edge detection is used to acquire the outline of the human-eye to ana- lyze the eye status. The PERCLOS principle is adopted to judge the fatigue status of human-eye. The development efficiency of the system is improved by means of the open-source vision library Android-OpenCV. The results of experiment in the indoor environment show that the terminal behaves well.

关 键 词：人眼疲劳检测 人眼状态分析 人脸定位 人眼轮廓获取 ANDROID 

分 类 号：TP316.81[自动化与计算机技术—计算机软件与理论] TP391[自动化与计算机技术—计算机科学与技术]