一种快速驾驶员疲劳检测方法  

A fast method for driver fatigue detection

作　　者：蒋文博[1] 谢晓明[1] 

机构地区：[1]北京化工大学信息科学与技术学院,北京100029

出　　处：《电子设计工程》2015年第23期34-36,39,共4页Electronic Design Engineering

摘　　要：疲劳驾驶是道路交通事故发生的重要原因,对此提出基于Adaboost的快速疲劳检测方法。首先,通过Adaboost分类器对眼睛进行定位;然后通过局部模板搜索确定二值化阈值,实现眼球虹膜轮廓的分割,再使用快速Hough变换,通过三个边缘特征点及其中垂线交点确定轮廓圆心,重绘虹膜圆形轮廓,根据面积比实现判断。增加打哈欠的检测作为疲劳的判断标准,通过Adaboost算法训练分类器来判别打哈欠的状态。在实际测试中,有效降低了判别眼睛闭合时的计算复杂度,有较好的准确性,能够应用在实际驾驶的过程中。Fatigue driving is one of the most important reasons of road traffic accidents, to solve this problem, propose a fast fa- tigue detection method based on Adaboost algorithm. First, locate the eyes through Adaboost classifier;, then find binary thresh- old by local template searching and segment the iris counter;, last, use fast Hough transform, determine the center by 3 edge- feature points and their perpendicular bisector intersection, redraw the iris counter and make the judgment by area ratio. In- crease a way for detecting the yawning based on Adaboost. In the actual test,the method reduces the computational complexity of discriminating eye closure and proves strong and high accuracy, can be used in the actual driving.

关 键 词：疲劳驾驶 人眼检测 ADABOOST 分类器 打哈欠 

分 类 号：TN391.41[电子电信—物理电子学]