人脸识别在疲劳驾驶检测中的应用研究
|
摘要
论文将卷积神经网络应用于人脸识别,对瞳孔定位算法进行改进,有效地克服了原算法计算量大的问题.根据驾驶员眼睛在不同状态下宽高比例不同的特点,实现了一种简单可行的眼睛状态判断方法,并通过PERCLOS算法对驾驶员的疲劳状态进行判定.论文采用改进Hough变换方法定位驾驶员眼睛,准确率为92%,平均响应时间为29ms,驾驶员眼睛状态的判断准确率为83.9%.设计了一种基于人脸识别的疲劳驾驶检测原型系统,实现驾驶员脸部特征检测、眼睛定位、眼睛状态判断、疲劳判定等功能.实验结果表明,系统对疲劳状态的识别率为87.5%,疲劳判断的响应时间为17ms,有较好的实际应用价值.
In the present study, convolutional neural network is applied in face recognition and improving the pupil localization algorithm, which effectively overcomes the problem of large computational complexity of the original algorithm. It is realized according to the characteristics of the driver's eyes in different states.A simple and feasible eye state judgment method is used, and the driver's fatigue state is determined by the PERCLOS algorithm. The improved Hough transform method has a positioning accuracy and average time of92% and 29 ms for the driver's eyes, respectively, and the correct rate for the driver's eye state is 83.9%. A fatigue driving detection prototype system based on face recognition was designed to achieve the functions of driver facial feature detection, eye positioning, eye state judgment and fatigue judgment. The experimental results show that the recognition rate of fatigue is 87.5%, and the response time of fatigue judgment is 17 ms,which has good practical application value.
In the present study, convolutional neural network is applied in face recognition and improving the pupil localization algorithm, which effectively overcomes the problem of large computational complexity of the original algorithm. It is realized according to the characteristics of the driver's eyes in different states.A simple and feasible eye state judgment method is used, and the driver's fatigue state is determined by the PERCLOS algorithm. The improved Hough transform method has a positioning accuracy and average time of92% and 29 ms for the driver's eyes, respectively, and the correct rate for the driver's eye state is 83.9%. A fatigue driving detection prototype system based on face recognition was designed to achieve the functions of driver facial feature detection, eye positioning, eye state judgment and fatigue judgment. The experimental results show that the recognition rate of fatigue is 87.5%, and the response time of fatigue judgment is 17 ms,which has good practical application value.
引文
[1]Sun G,Jin Y,Li Z,et al.A vision-based head status judging algorithm for driving fatigue detection system[J]Advances in Transportation Studies,2015(37).
[2]Grace R,Byrne V E,Legrand J M.A machine vision based drowsy driver detection system for heavy vehicles[EB/OL].[2014-01-17].http://citeseerx.ist.psu.e-du/showciting?cid=4007209.
[3]耿新,周志华,陈世福.基于混合投影函数的眼睛定位[J].软件学报,2003,14(8):1394-1400.
[4]郑培,宋正河,周一鸣.基于PERCLOS的机动车驾驶员驾驶疲劳的识别算法[J].中国农业大学学报2002,7(2):104-109.
[5]葛如海,陈彦博,刘志强,等.基于计算机视觉的驾驶疲劳识别方法的研究[J].中国安全科学学报2006,16(9):134-138.
[6]石坚,吴远鹏,卓斌,马勇,许晓鸣.汽车驾驶员主动安全性因素的辨识与分析[J].上海交通大学学报,2000,(04):441-444.
[7]王荣本,郭克友,储江伟.一种基于Gabor小波的驾驶员眼部状态识别方法的研究[J].中国图像图形学报,2003,8(9):1043-1047.
[8]The Database of Face,AT&T Laboratories Cambridge Available:http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html.
[9]Lai X U,De-Long Z.Technology of human eyes detection[J].Computer Systems&Applications,2010,6:056.
[10]夏阿南.基于人眼动态特性的驾驶疲劳检测方法研究[D].大连海事大学,2014.
[11]常胜江,孟春宁,韩建民,等.人眼检测技术研究进展[J].数据采集与处理,2015,30(6):1131-1146.
[12]Liao Q,Hong J,Jiang M.A comparison of edge detection algorithm using for driver fatigue detection system[C]//The,International Conference on Industrial Mechatronics and Automation.2010:80-83.
[13]Tenorio E Z,Thomaz C E.Análise Multilinear Discriminante de FormasFrontais de Imagens 2D de Face[C]//Proceedings of the X SimposioBrasileiro de AutomacaoInteligente SBAI.2011:266-271.
[14]王小鹏,闫国梁,闫文秀.基于最大熵分割和肤色模型的人眼定位[J].计算机工程,2010,36(14):161-165.
[15]WANG W,CHANG F.A precise eye localization method based on region projection[J].Journal of Optoelectronics&Laser,2011,22(4):618-622.
[16]李绍文,王江波.驾驶员疲劳检测系统的研究[J]计算机工程与应用,2013,49(15):253-258.
[17]张旭东,严宏斌,张忠伟,等.一种考虑驾驶员姿态及光照因素的疲劳驾驶稳健检测算法[J].电子技术(上海),2014(12):26-30.
[18]郭永彩,李文涛,高潮.基于PERCLOS的驾驶员疲劳检测算法[J].计算机系统应用,2009,18(8):54-57.
[2]Grace R,Byrne V E,Legrand J M.A machine vision based drowsy driver detection system for heavy vehicles[EB/OL].[2014-01-17].http://citeseerx.ist.psu.e-du/showciting?cid=4007209.
[3]耿新,周志华,陈世福.基于混合投影函数的眼睛定位[J].软件学报,2003,14(8):1394-1400.
[4]郑培,宋正河,周一鸣.基于PERCLOS的机动车驾驶员驾驶疲劳的识别算法[J].中国农业大学学报2002,7(2):104-109.
[5]葛如海,陈彦博,刘志强,等.基于计算机视觉的驾驶疲劳识别方法的研究[J].中国安全科学学报2006,16(9):134-138.
[6]石坚,吴远鹏,卓斌,马勇,许晓鸣.汽车驾驶员主动安全性因素的辨识与分析[J].上海交通大学学报,2000,(04):441-444.
[7]王荣本,郭克友,储江伟.一种基于Gabor小波的驾驶员眼部状态识别方法的研究[J].中国图像图形学报,2003,8(9):1043-1047.
[8]The Database of Face,AT&T Laboratories Cambridge Available:http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html.
[9]Lai X U,De-Long Z.Technology of human eyes detection[J].Computer Systems&Applications,2010,6:056.
[10]夏阿南.基于人眼动态特性的驾驶疲劳检测方法研究[D].大连海事大学,2014.
[11]常胜江,孟春宁,韩建民,等.人眼检测技术研究进展[J].数据采集与处理,2015,30(6):1131-1146.
[12]Liao Q,Hong J,Jiang M.A comparison of edge detection algorithm using for driver fatigue detection system[C]//The,International Conference on Industrial Mechatronics and Automation.2010:80-83.
[13]Tenorio E Z,Thomaz C E.Análise Multilinear Discriminante de FormasFrontais de Imagens 2D de Face[C]//Proceedings of the X SimposioBrasileiro de AutomacaoInteligente SBAI.2011:266-271.
[14]王小鹏,闫国梁,闫文秀.基于最大熵分割和肤色模型的人眼定位[J].计算机工程,2010,36(14):161-165.
[15]WANG W,CHANG F.A precise eye localization method based on region projection[J].Journal of Optoelectronics&Laser,2011,22(4):618-622.
[16]李绍文,王江波.驾驶员疲劳检测系统的研究[J]计算机工程与应用,2013,49(15):253-258.
[17]张旭东,严宏斌,张忠伟,等.一种考虑驾驶员姿态及光照因素的疲劳驾驶稳健检测算法[J].电子技术(上海),2014(12):26-30.
[18]郭永彩,李文涛,高潮.基于PERCLOS的驾驶员疲劳检测算法[J].计算机系统应用,2009,18(8):54-57.