首页 | 本学科首页   官方微博 | 高级检索  
     

基于多面部特征融合的驾驶员疲劳检测算法
引用本文:刘炜煌,钱锦浩,姚增伟,焦新涛,潘家辉.基于多面部特征融合的驾驶员疲劳检测算法[J].计算机系统应用,2018,27(10):177-182.
作者姓名:刘炜煌  钱锦浩  姚增伟  焦新涛  潘家辉
作者单位:华南师范大学 软件学院, 佛山 528225,华南师范大学 软件学院, 佛山 528225,华南师范大学 软件学院, 佛山 528225,华南师范大学 软件学院, 佛山 528225,华南师范大学 软件学院, 佛山 528225
基金项目:国家自然科学基金青年科学基金(61503143);广州市科技计划项目珠江科技新星科技创新人才专项(201710010038);广东省自然科学基金博士科研启动项目(2014A030310244)
摘    要:本文将卷积神经网络(Convolutional Neural Network,CNN)应用到视频理解中,提出一种基于多面部特征融合的驾驶员疲劳检测算法.本文使用多任务级联卷积网络(Multi-Task Cascaded Convolutional Networks,MTCNN)定位驾驶员的嘴部、左眼,使用CNN从驾驶员嘴部、左眼图像中提取静态特征,结合CNN从嘴部、左眼光流图中提取动态特征进行训练分类.实验结果表明,该算法比只使用静态图像进行驾驶员疲劳检测效果更好,准确率达到87.4%,而且可以很好地区别在静态图像中很相似的打哈欠和讲话动作.

关 键 词:疲劳检测  多任务级联卷积网络  光流  特征融合  计算机视觉
收稿时间:2018/2/6 0:00:00
修稿时间:2018/2/28 0:00:00

Driver Fatigue Detection Algorithm Based on Multi-Facial Feature Fusion
LIU Wei-Huang,QIAN Jin-Hao,YAO Zeng-Wei,JIAO Xin-Tao and PAN Jia-Hui.Driver Fatigue Detection Algorithm Based on Multi-Facial Feature Fusion[J].Computer Systems& Applications,2018,27(10):177-182.
Authors:LIU Wei-Huang  QIAN Jin-Hao  YAO Zeng-Wei  JIAO Xin-Tao and PAN Jia-Hui
Affiliation:School of Software, South China Normal University, Foshan 528225, China,School of Software, South China Normal University, Foshan 528225, China,School of Software, South China Normal University, Foshan 528225, China,School of Software, South China Normal University, Foshan 528225, China and School of Software, South China Normal University, Foshan 528225, China
Abstract:In this study, Convolution Neural Network (CNN) is applied to video comprehension, and a driver fatigue detection algorithm based on multi-facial feature fusion is proposed. In the study, Multi-Task Cascaded Convolutional Neural Networks (MTCNN) is used to locate the driver''s mouth and left eye. CNN is used to extract the static features from the driver''s mouth and left-eye image, combined with the dynamic features that CNN extracted from the mouth and left eye optical flow to train for classification. The experimental results show that this algorithm with an accuracy rate of 87.4% is better than only use the static image for driver fatigue detection and it can well distinguish between yawning and speech actions that are similar in static images.
Keywords:fatigue detection  Multi-Task Cascaded Convolutional Networks (MTCNN)  optical flow  feature fusion  computer vision
点击此处可从《计算机系统应用》浏览原始摘要信息
点击此处可从《计算机系统应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号