摘要
哈欠检测可以用于对驾驶员的疲劳驾驶行为发出警告,从而减少交通事故的发生。提出了一种基于卷积神经网络的哈欠检测算法,可以把驾驶员的面部图片直接作为神经网络的输入,避免对面部图片进行复杂的显式特征提取。利用Softmax分类器对神经网络提取的特征进行分类,判断是否为打哈欠行为。该算法在YawDD数据集上取得了92.4%的哈欠检测准确率。与现有多个算法相比,所提算法具有检测准确率高、实现简单等优点。
Yawning detection can be used to warn drivers of fatigue driving behavior,thereby reducing traffic accidents.A yawning detection algorithm based on convolutional neural network was proposed.The driver's facial image can be directly used as input for neural network,so as to avoid the complex explicit feature extraction of the facial image.The Softmax classifier is used to classify the features extracted from the neural network to determine whether the behavior is yawning or not.This algorithm achieves 92.4% accuracy in the YawDD dataset.Compared with other existing algorithms,the proposed method has the advantages of high detection accuracy and simple implementation.
引文
[1]DWIVEDI K,BISWARANJAN K,SETHI A.Drowsy driver detection using representation learning[C]∥IEEE International Advance Computing Conference.IEEE,2014:995-999.
[2]ABTAHI S,SHIRMOHAMMADI S,HARIRI B,et al.A yawning measurement method using embedded smart cameras[C]∥Instrumentation and Measurement Technology Conference.IEEE,2013:1605-1608.
[3]GALLUP A C,ELDAKAR O T.The thermoregulatory theory of yawning:what we know from over 5years of research[J].Frontiers in Neuroscience,2013,6:188.
[4]OMIDYEGANEH M,SHIRMOHAMMADI S,ABTAHI S,et al.Yawning Detection Using Embedded Smart Cameras[J].IEEE Transactions on Instrumentation&Measurement,2016,65(3):1-13.
[5]谢国波,陈云华,张灵,等.基于嘴巴特征点曲线拟合的哈欠检测[J].计算机工程与科学,2014,36(4):731-736.
[6]ANITHA C,VENKATESHA M K,ADIGA B S.A Two Fold Expert System for Yawning Detection[J].Procedia Computer Science,2016,92:63-71.
[7]FAN X,YIN B C,SUN Y F.Yawning detection based on Gabor wavelets and LDA[J].Beijing Gongye Daxue Xuebao,2009,35(3):409-413,432.
[8]LI L,CHEN Y,LI Z.Yawning detection for monitoring driver fatigue based on two cameras[C]∥International IEEE Conference on Intelligent Transportation Systems.IEEE Xplore,2009:1-6.
[9]LU Y,WANG Z.Detecting Driver Yawning in Successive Images[C]∥International Conference on Bioinformatics and Biomedical Engineering.IEEE Xplore,2007:581-583.
[10]IBRAHIM M M,SORAGHAN J J,PETROPOULAKIS L,et al.Yawn analysis with mouth occlusion detection[J].Biomedical Signal Processing&Control,2015,18:360-369.
[11]王忠民,曹洪江,范琳.一种基于卷积神经网络深度学习的人体行为识别方法[J].计算机科学,2016,43(Z11):56-58.
[12]CUN Y L,BOSER B,DENKER J,et al.Handwritten digit recognition with a backpropogation network[J].World of Computer Science&Information Technology Journal,1990,2(2):396-404.
[13]ABTAHI S,OMIDYEGANEH M,SHIRMOHAMMADI S,et al.YawDD:A Yawning Detection DataSet[C]∥Proceedings of the 5th ACM Multimedia Systems Conference.New York:ACM Press,2014:24-28.
[14]曹莹,苗启广,刘家辰,等.AdaBoost算法研究进展与展望[J].自动化学报,2013,39(6):745-758.
[15]王平,全吉成,赵柏宇.基于双线性插值的图像缩放在GPU上的实现[J].微电子学与计算机,2016,33(11):129-132.
[16]刘春晓,朱臻阳,伍敏,等.基于主色检测与灰度传播的彩色图像灰度化方法[J].计算机辅助设计与图形学学报,2016,28(3):433-442.
[17]VOLOSHYN D.Application of deep learning and computer vision frameworks for solving video context prediction problem[C]∥Proceedings of the 10th International Conference of Programming.2016:164-169.
[18]ZHANG W,YI L M,WANG T,et al.Driver yawning detection based on deep convolutional neural learning and robust nose tracking[C]∥International Joint Conference on Neural Networks.IEEE,2015:1-8.