基于眼睛特征跟踪的眼睛状态跟踪  

Eye States Tracking Based on Tracking Eye Features

作　　者：曹倩霞[1] 罗大庸[2] 李顺[1] 

机构地区：[1]长沙理工大学交通运输学院,湖南长沙410076 [2]中南大学信息科学与工程学院,湖南长沙410075

出　　处：《计算机测量与控制》2007年第12期1794-1797,共4页Computer Measurement &Control

摘　　要：眼睛状态的跟踪具有广泛的应用,如在面部表情分析和驾驶疲劳报警系统的应用方面,此时需要跟踪的不仅仅是人眼的位置,而且还需要返回眼睛的状态,以及眼睛模型的参数。基于眼睛特征跟踪的眼睛状态跟踪方法是先检测出表征眼睛状态的眼睛特征,然后通过跟踪这些特征达到跟踪眼睛状态的目的。在实验平台是PII/500微机,256M内存,Windows2000操作系统中处理速度是接近每秒7帧。对214图像序列进行了实验测试,跟踪精度达到97.6%。There are many applications of the robust eye states tracking, such as facial expression analysis and driver awareness systems. In these researches, we need to do more than tracking the locations of the person＇ s eyes but obtain their detailed description. We need to recover the state of the eyes and the parameters of an eye model. , we develop a eye states tracking model based on tracking eye features by extracting eye features which characterizing the eye states firstly, then tracking these features to track the eye states. Processing speed on a Pentium PⅡ/500 PC is approximately 7 frames/second. In experimental tests on 214 image sequences from subject, accurate tracking results are obtained in 97. 6% of image sequences.

关 键 词：眼睛特征检测 眼睛特征跟踪 眼睛状态跟踪 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]