摘要
疲劳驾驶是导致车辆发生事故的一个主要因素。为了有效防止疲劳驾驶现象的发生,文章研究了一种采用图像识别对驾驶员疲劳状态检测判别的嵌入式监控终端设备。该设备以嵌入式芯片作为核心控制器,利用安装于驾驶台前上方的摄像头采集驾驶员的脸部图像,微处理器采用HOG-SVM算法识别脸部特征,采用灰度积分投影法来实现对图像中眼睛张开定位,使用PERCLOS算法判定人的驾驶状态并实现疲劳状态语音报警提示,同时把驾驶员状态发送到远程管理平台.
Fatigue driving is a major factor leading to vehicle accidents.In order to effectively prevent the occurrence of fatigue driving,the paper studies an embedded monitoring terminal device that uses image vision recognition to detect driver fatigue status.The design uses a single-chip microcomputer as the core controller,uses a camera installed in front of the driver to collect the driver's facial image,uses the HOG SVM algorithm to locate facial features,uses the PERCLOS algorithm to determine the driving state of the person and realizes the fatigue state voice alarm prompt,and at the same time,the device send the status of the driver to the remote management platform.
作者
胡冠山
HU Guanshan(Department of Information Technology,Shandong Jiaotong University,Jinan 250357,China)
出处
《传感器世界》
2021年第6期6-9,17,共5页
Sensor World
基金
山东省交通厅科技计划项目“基于云计算的城市交通瓶颈与区域路网协同控制研究”(No.2017B96)。
关键词
嵌入式
疲劳驾驶
图像识别
embedded system
fatigue driving
image vision
