驾驶员眼部状态识别方法的研究  

Study on the Recognition of the Driver's Eye States

作　　者：郭克友[1] 储江伟[1] 王荣本[1] 

机构地区：[1]吉林大学交通学院,吉林长春130025

出　　处：《系统工程与电子技术》2003年第10期1186-1188,1228,共4页Systems Engineering and Electronics

基　　金：教育部科学技术研究重点项目资助课题 (0 0 0 3 7)

摘　　要：驾驶员在正常驾驶、瞌睡驾驶及疲劳驾驶 3种状态下的眼睛张开程度有一定的区别。根据这一特点 ,设计了一种 3层BP网络 ,利用图像预处理获取到的眼部区域特征值作为网络输入向量 ,输出对应 3种不同状态。实验结果表明 ,该网络可快速有效地识别出驾驶员眼部精神状态。Under the circumstances of the natural driving, drowsing driving and fatigued driving of a driver, the opening degrees of the eyes are different to some extent. Based on this characteristic, a three-layer artificial neural network is designed. The eigenvalues of the eye's area which are gained by image preprocessing are used as the inputs of the network, and the outputs of the network correspond to the three different conditions. Experiments have proved the validity of the network.

关 键 词：行为监控 眼睛状态识别 BP神经网络 图像处理 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]