灰度视频序列中驾驶员疲劳实时检测方法  

Real-time driving fatigue detection in gray image sequence

作　　者：蒋建国[1] 刘扬[1] 詹曙[1] 李化雷[1] 

机构地区：[1]合肥工业大学计算机与信息学院

出　　处：《合肥工业大学学报（自然科学版）》2008年第9期1424-1427,1442,共5页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(60474035)

摘　　要：介绍了一种灰度视频序列中快速、有效的通过判断眼睛睁开程度来检测驾驶疲劳的方法,首先通过改进的Sobel算子在面部区域获得五官边缘的二值化图像,然后进行连通区域判断,并结合五官几何特征、区域生长及形态学算法精确定位眼睛位置,最后利用上下眼睑的相对距离来判断是否疲劳。实验结果表明;该算法对尺寸、旋转角度等有很好的适应性。This paper introduces a quick and effcient algorithm for driving fatigue detection in gray-level image sequence＇s by measuring the open degree of a driver＇s eyes. Firstly, the binary edge of facial features in the facial region is obtained by the improved Sobel operator. Secondly, an 8-connected component algorithm is used,and then the location of eyes is confirmed accurately by integrating facial features＇ geometrical characteristics, region growing and the morphology algorithm. Finally, the fatigue is judged by the distance change of the eyelid. Experimental results indicate that the algorithm is robust to the image with different size and rotation angle.

关 键 词：灰度视频序列 眼睛定位 几何特征 改进的Sobel算子 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]