发布时间:2015/1/22 10:16:12 作者:金嘉琦,陈健 【字体:
大 中 小】
金嘉琦,陈健
(沈阳工业大学 机械工程学院 车辆工程系,辽宁 沈阳 110870)
摘要:人脸检测是基于PERCLOS的疲劳驾驶检测中的一项关键技术。将CCD摄像头得到的驾驶员人脸图像映射到YCbCr颜色空间,创立一个基于肤色的二维高斯数学模型。用自适应阈值分割法对人脸图像进行二值化处理,然后将得到的二值化人脸图像进行形态学分析。最后通过面部特征对连通域进行分析和处理,实现人脸的检测并框定。
关键词:肤色;面部特征;YCbCr颜色空间;人脸检测
中图分类号:TJ765.4+1 文献标志码:A doi:10.3969/j.issn.1006-0316.2015.01.019
文章编号:1006-0316 (2015) 01-0074-03
Facial features detection and location of driver fatigue driving
JIN Jia-qi,CHEN Jian
( School of Mechanical Engineering, Shenyang University of Technology, Shenyang 110000, China )
Abstract:The face detection is the key technology in the field of detecting driving fatigue based on PERCLOS. The driver’s face images using CCD camera mapped into YCbCr color space and a 2-dimensional mathematical of Gause distribution was developed on the basis of human face complexion. The face image by likelihood figure adaptive threshold is carried out morphology operation to dispose. The facial regions is obtained by analyzing the connected component based on farcical fractures.
Key words:complexion;facial features;YCbCr chrominance space;face detection
———————————————
收稿日期:2014-09-03
作者简介:金嘉琦(1955-),辽宁沈阳人,博士,教授,主要研究方向为车辆工程;陈健(1990-),辽宁新民人,硕士,主要研究方向为车辆工程。