基于面部几何特征及手部运动特征的驾驶员疲劳检测
|
摘要
驾驶员疲劳驾驶是造成交通事故的主要原因之一,为解决该问题,提出一种新的基于机器视觉的驾驶员疲劳状态检测方法。根据驾驶员视频图像特点,采用基于肤色检测的Adaboost算法提取面部以及手部的感兴趣区域(Regionsofinterest,ROIs)。基于尺度不变特征变换(Scale invariant feature transform,SIFT)特征点匹配获取眼、嘴以及手部的SIFT特征点,据此得出面部以及手部特征参数。将Perclos、MClosed、Phdown以及SA 4个特征参数作为模型输入,疲劳度等级作为模型输出,建立三层BP神经网络模型,并应用贝叶斯正则化并结合动量梯度下降法较好地解决了传统BP人工神经网络训练高精度和预测低精度的过拟合现象。试验数据表明,该方法能够克服光照、背景、角度以及个体差异的影响,且疲劳检测的正确识别率达到99.64%。
Fatigue driving is one of the major causes of traffic accidents. In order to solve the problem, a new method based onmachine vision for driver fatigue detection is proposed. According to the characteristics of the driver's video image, the regions ofinterest(ROIs) of face and hand are extracted by the Adaboost algorithm based on skin color detection. Based on SIFT(scaleinvariant feature transform) feature points matching, the SIFT feature points of the eye, mouth and hand are extracted, and the facialand hand feature parameters are obtained. The 4 characteristic parameters of Perclos, MClosed, Phdown and SA are used as modelinputs, and the fatigue grade is used as model output. Three layer BP neural network model is established. The Bayesianregularization and the momentum gradient descent method are used to solve the overfitting phenomena of the traditional BP neuralnetwork training with high accuracy and low prediction accuracy. The experimental data show that the method can overcome theinfluence of illumination, background, angle and individual difference, and the correct recognition rate of fatigue detection is 99.64%.
Fatigue driving is one of the major causes of traffic accidents. In order to solve the problem, a new method based onmachine vision for driver fatigue detection is proposed. According to the characteristics of the driver's video image, the regions ofinterest(ROIs) of face and hand are extracted by the Adaboost algorithm based on skin color detection. Based on SIFT(scaleinvariant feature transform) feature points matching, the SIFT feature points of the eye, mouth and hand are extracted, and the facialand hand feature parameters are obtained. The 4 characteristic parameters of Perclos, MClosed, Phdown and SA are used as modelinputs, and the fatigue grade is used as model output. Three layer BP neural network model is established. The Bayesianregularization and the momentum gradient descent method are used to solve the overfitting phenomena of the traditional BP neuralnetwork training with high accuracy and low prediction accuracy. The experimental data show that the method can overcome theinfluence of illumination, background, angle and individual difference, and the correct recognition rate of fatigue detection is 99.64%.
引文
[1]WEI C S,WANG Y T,LIN C T,et al.Toward drowsiness detection using non-hair-bearing eeg-based braincomputer interfaces[J].IEEE Trans.Neural Syst.Rehabil Eng.,2018,26(2):400-406.
[2]KHUNPISUTH O,CHOTCHINASRI T,KOSCHAKOSAIV,et al.Driver drowsiness detection using eye-closeness detection[C]//International Conference on Signal-Image Technology&Internet-Based Systems.IEEE,November26-29,2017,Las Palmas de Gran Canaria,Spain,2017:661-668.
[3]KOH S,BO R C,LEE J I,et al.Driver drowsiness detection via PPG biosignals by using multimodal head support[C]//International Conference on Control,Decision and Information Technologies,April 10-13,2017,Thessaloniki,Greece,2017:0383-0388.
[4]LIN C T,CHEN Y C,WU R C,et al.Assessment of driver's driving performance and alertness using EEG-based fuzzy neural networks[C]//IEEE International Symposium on Circuits and Systems.IEEE,May 15-18,2005,Rio de Janeiro,Brazil,2005,1:152-155.
[5]HAYASHI K,ISHIHARA K,HASHIMOTO H,et al.Individualized drowsiness detection during driving by pulse wave analysis with neural network[J].Intelligent Transport Systems,2005.Proceedings.IEEE,2005:901-906.
[6]TAKEI Y,FURUKAWA Y.Estimate of driver’s fatigue through steering motion[C]//2005 IEEE International Conference on Systems,Man and Cybernetics,October6-9,2005,Bari,Italy,2005,2(10-12):1765-1770
[7]POMERLEAU D,JOCHEM T.Rapidly Adapting machine vision for automated vehicle steering[J].IEEEExpert,1996,11(2):19-27.
[8]WANG Rongben,LI Guo,TONG Bing liang,et al.Monitoring mouth movement for driver fatigue or distraction with one camera[C]//The International IEEEConference on Intelligent Transportation Systems,November 4-7,2004 Maui,Hawaii,USA,2004:314-319.
[9]PAUL V,MICHAEL J.Robust real-time face detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[10]GUO L,GE P S,ZHANG M H,et al.Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine[J].Expert Systems with Applications,2012,39(4):4274-4286.
[11]LOWE D G.Distinctive image features from scaleinvariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[12]LI B,YU S,LU Q.An improved K-nearest-neighbor algorithm for text categorization[J].Expert Systems with Applications An International Journal,2012,39(1):1503-1509.
[13]DINGES D F,GRACE R.PERCLOS:A valid psychophysiological measure of alertness as assessed by psychomotor vigilance,FHWAMCRT-99-010[R].Washington,DC,Federal.Highway Administration,1998.
[14]PETER G,KURT K,VERA K,et al.Circadian and wake-dependent modulation of fastest and slowest reaction times during the psychomot or vigilance lask[J].Physiology&Behavior,2004,80:695-701.
[15]NEYAMADPOUR A,TAIB S,ABDULLAH W A T W.Using artificial neural networks to invert 2D DCresistivity imaging data for high resistivity contrast regions:A MATLAB application[J].Computers&Geosciences,2009,35(11):2268-2274
[16]ORON-GILAD T,RONEN A.Road characteristics and driver fatigue:A simulator study[J].Traffic Injury Prevention,2007,8(3):281-289.
[2]KHUNPISUTH O,CHOTCHINASRI T,KOSCHAKOSAIV,et al.Driver drowsiness detection using eye-closeness detection[C]//International Conference on Signal-Image Technology&Internet-Based Systems.IEEE,November26-29,2017,Las Palmas de Gran Canaria,Spain,2017:661-668.
[3]KOH S,BO R C,LEE J I,et al.Driver drowsiness detection via PPG biosignals by using multimodal head support[C]//International Conference on Control,Decision and Information Technologies,April 10-13,2017,Thessaloniki,Greece,2017:0383-0388.
[4]LIN C T,CHEN Y C,WU R C,et al.Assessment of driver's driving performance and alertness using EEG-based fuzzy neural networks[C]//IEEE International Symposium on Circuits and Systems.IEEE,May 15-18,2005,Rio de Janeiro,Brazil,2005,1:152-155.
[5]HAYASHI K,ISHIHARA K,HASHIMOTO H,et al.Individualized drowsiness detection during driving by pulse wave analysis with neural network[J].Intelligent Transport Systems,2005.Proceedings.IEEE,2005:901-906.
[6]TAKEI Y,FURUKAWA Y.Estimate of driver’s fatigue through steering motion[C]//2005 IEEE International Conference on Systems,Man and Cybernetics,October6-9,2005,Bari,Italy,2005,2(10-12):1765-1770
[7]POMERLEAU D,JOCHEM T.Rapidly Adapting machine vision for automated vehicle steering[J].IEEEExpert,1996,11(2):19-27.
[8]WANG Rongben,LI Guo,TONG Bing liang,et al.Monitoring mouth movement for driver fatigue or distraction with one camera[C]//The International IEEEConference on Intelligent Transportation Systems,November 4-7,2004 Maui,Hawaii,USA,2004:314-319.
[9]PAUL V,MICHAEL J.Robust real-time face detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[10]GUO L,GE P S,ZHANG M H,et al.Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine[J].Expert Systems with Applications,2012,39(4):4274-4286.
[11]LOWE D G.Distinctive image features from scaleinvariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[12]LI B,YU S,LU Q.An improved K-nearest-neighbor algorithm for text categorization[J].Expert Systems with Applications An International Journal,2012,39(1):1503-1509.
[13]DINGES D F,GRACE R.PERCLOS:A valid psychophysiological measure of alertness as assessed by psychomotor vigilance,FHWAMCRT-99-010[R].Washington,DC,Federal.Highway Administration,1998.
[14]PETER G,KURT K,VERA K,et al.Circadian and wake-dependent modulation of fastest and slowest reaction times during the psychomot or vigilance lask[J].Physiology&Behavior,2004,80:695-701.
[15]NEYAMADPOUR A,TAIB S,ABDULLAH W A T W.Using artificial neural networks to invert 2D DCresistivity imaging data for high resistivity contrast regions:A MATLAB application[J].Computers&Geosciences,2009,35(11):2268-2274
[16]ORON-GILAD T,RONEN A.Road characteristics and driver fatigue:A simulator study[J].Traffic Injury Prevention,2007,8(3):281-289.