基于视频的人眼跟踪方法研究  

Study of the Eye-tracking Methods Based on Video

作　　者：刘纪红[1] 李中帆[1] 

机构地区：[1]东北大学信息科学与工程学院,沈阳110819

出　　处：《小型微型计算机系统》2012年第9期2087-2090,共4页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(60774097)资助

摘　　要：疲劳驾驶是交通事故发生的主要原因之一.在车载的驾驶员疲劳检测系统中,对于人眼的高效、实时、准确检测和跟踪是关键技术之一.本文研究基于视频信息的驾驶员人脸图像中眼睛的跟踪方法.采用Viola-Jones算法和AdaBoost算法设计了Haar级联人脸分类器,根据人脸的几何结构和眼睛的特性,通过两次定位的方法实现了对眼睛的定位和跟踪.实验表明,本文方法具有检测精度高、鲁棒性强的特点.Driver fatigue is one of the chief causes of traffic accident. Detecting and tracking driver＇s eyes effectively and exactly and in real-time is one of the key technologies in the system for detecting driver fatigue. This paper studies the eye-tracking methods in the images with the driver＇s face based on video. Firstly, a Haar cascade classifier for the face is designed by applying Viola-Jones arith- metic and AdaBoost arithmetic. Then the eye tracking is realized by two-step location methods. The experimental results shows that the methods presented in this paper are accurate and robust.

关 键 词：疲劳检测 人脸定位 分类器 人眼定位 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]