汽车安全驾驶中的人眼视线估计
|
摘要
汽车驾驶安全性的提高，有赖于汽车被动安全和主动安全技术的研究。作为主动安全技术的组成部分，对驾驶员驾车状态的监控是必不可少的。本文的研究内容是使用普通的摄像头实时地进行人眼视线方向估计和驾驶员困倦状态检测，用以判断驾驶员是否处于安全驾驶状态。
首先，本文对人眼模型进行了讨论，在传统纺锤形眼睛模型的基础上，忽略下眼睑，只保留上眼睑、虹膜和内外角点。
然后，本文研究了眼睛各个特征的检测方法，包括眼睛窗口定位，角点检测，虹膜检测以及眼睑检测，并且采用一种简单的视线定位方法定位视线方向。本文将虹膜用圆来拟合，将上眼睑视为一段圆弧，研究并采用亚像素边缘检测方法检测亚像素级的虹膜边缘和基于梯度朝向和梯度方向信息的Hough变换的方法检测虹膜和眼睑。实验表明，本文采用的方法在低分辨率图像条件下具有更高的估计精度和实时性。
最后，本文将所提出的人眼视线方向估计算法应用于实时视线方向监控系统。这个系统能够实时地对驾驶员视线方向和困倦状态进行监控。从系统运行的效果看，在实验室环境中，本系统的运行效率是很高的。
The enhancement of automobile driving security depends on the research of automobile passive security and the initiative security technology. As one of initiative security technologies, it is essential to monitor the condition of the driver. In this thesis, we focus on how to estimate the gaze of human eye and detect whether the driver is sleepy in real-time with a common camera, so that we can determine whether the driver is at unsafe driving condition.
First of all, we discuss the eye model. Based on the traditional spindly eye model, we ignore the down-eyelid, only retain upper-eyelid, iris and eye corners.
Then, we research methods of eye features detection, including eye window positioning, eye corners detection, iris detection and eye-lid detection. And we adopt a simple method to estimate gaze. We fit the iris to a circle and regard the upper-eyelid as a section of circular arc. Then we use the method of sub-pixel detection to detect sub-pixel edge and the method of Hough transform based on gradient orientation and gradient direction to detect circle. The experiment indicates that these methods have the higher estimating precision and more timeliness under the low resolution image condition.
Finally, we apply the gaze estimation algorithm this paper proposed in a real-time gaze safety examination system. This system can carry on the monitoring of the gaze direction and the sleepy condition real-time. From the running effect of this system, the efficiency of this system is very high in the laboratory environment.
首先，本文对人眼模型进行了讨论，在传统纺锤形眼睛模型的基础上，忽略下眼睑，只保留上眼睑、虹膜和内外角点。
然后，本文研究了眼睛各个特征的检测方法，包括眼睛窗口定位，角点检测，虹膜检测以及眼睑检测，并且采用一种简单的视线定位方法定位视线方向。本文将虹膜用圆来拟合，将上眼睑视为一段圆弧，研究并采用亚像素边缘检测方法检测亚像素级的虹膜边缘和基于梯度朝向和梯度方向信息的Hough变换的方法检测虹膜和眼睑。实验表明，本文采用的方法在低分辨率图像条件下具有更高的估计精度和实时性。
最后，本文将所提出的人眼视线方向估计算法应用于实时视线方向监控系统。这个系统能够实时地对驾驶员视线方向和困倦状态进行监控。从系统运行的效果看，在实验室环境中，本系统的运行效率是很高的。
The enhancement of automobile driving security depends on the research of automobile passive security and the initiative security technology. As one of initiative security technologies, it is essential to monitor the condition of the driver. In this thesis, we focus on how to estimate the gaze of human eye and detect whether the driver is sleepy in real-time with a common camera, so that we can determine whether the driver is at unsafe driving condition.
First of all, we discuss the eye model. Based on the traditional spindly eye model, we ignore the down-eyelid, only retain upper-eyelid, iris and eye corners.
Then, we research methods of eye features detection, including eye window positioning, eye corners detection, iris detection and eye-lid detection. And we adopt a simple method to estimate gaze. We fit the iris to a circle and regard the upper-eyelid as a section of circular arc. Then we use the method of sub-pixel detection to detect sub-pixel edge and the method of Hough transform based on gradient orientation and gradient direction to detect circle. The experiment indicates that these methods have the higher estimating precision and more timeliness under the low resolution image condition.
Finally, we apply the gaze estimation algorithm this paper proposed in a real-time gaze safety examination system. This system can carry on the monitoring of the gaze direction and the sleepy condition real-time. From the running effect of this system, the efficiency of this system is very high in the laboratory environment.
引文
1．陆化普，李瑞敏，朱茵．智能交通系统概论．第一版．北京：中国铁道出版社．2004．
2．Milan Sonka，Vaclav Hlavac，Roger Boyle等．图像处理、分析与机器视觉．第二版．北京：人民邮电出版社．2003．
3．孙荣恒．应用数理统计．第二版．北京：科学出版社．2003．
4. Yoshio Matsumotoy, Alexander Zelinsky. An Algorithm for Real-time Stereo Vision Implementation of Head Pose and Gaze Direction Measurement. Proceedings of Fourth International Conference on Automatic Face and Gesture Recognition, 2000: pp. 499-504.
5. Kin-Man Lam and Yan-Lin Li. An Efficient Approach for Facial Feature Detection. Proceedings oflCSP 98: pp. 1100-1103.
6. Yong Ma, Xiaoqing Ding, Zhenger Wang, Ning Wang. Robust Precise Eye Location Under Probabilistic Framework. Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004.
7．宋加涛，刘济林，池哲儒，王蔚．人脸正面图像中眼睛的精确定位．计算机辅助设计与图形学学报．2005，17(3)：pp．540-545．
8. Luis Jordao, Matteo Perrone and Joao Paulo Costeira. Active Face and Feature Tracking. Proc. of IEEE Conference on Computer Vision and Pattern Recognition, 1999.
9. Jie Zhu and Jie Yang. Subpixel Eye Gaze Tracking. Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition 2002
10. Shinjiro Kawato and Jun Ohya. Real-time Detection of Nodding and Head-shaking by Directly Detecting and Tracking the "Between-Eyes". Automatic Face and Gesture Recognition, 2000. Proceedings. Fourth IEEE International Conference, 2000: pp. 40-45.
11. Shinjiro Kawato and Jun Ohya. Two-step Approach for Real-time Eye Tracking with a New Filtering Technique Systems Man and Cybernetics. IEEE International Conference, 2000, 12(8): pp. 1366-1371.
12．苗守杰，刘希顺，刘安芝．一种快速精确的虹膜定位方法．微计算机信息．2005，21(11)．
13．王成儒，胡正平，练秋生．一种虹膜定位算法．计算机辅助设计与图形学学报．2002，14(10)：pp．950-952．
14．柴秀娟，山世光，高文．陈熙霖．基于样例学习的面部特征自动标定算法．软件学报．2005，16(5)：pp．718-726．
15. Zhiwei Zhu and Qiang Ji. Real Time 3D Face Pose Tracking From an Uncalibrated Camera. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 2004.
16. Raffaella Lanzarotti, N. Alberto Borghese and Paola Campadelli. Robust identification and matching of fiducial points for the reconstruction of 3D human faces from raw video sequences. Proceedings of the First International Symposium on 3D Data Processing Visualization and Transmission 2002.
17．林维训，潘纲，吴朝晖，潘云鹤．脸部特征定位方法综述．中国图象图形学报．2003，8(8)：pp．849-859．
18. Kanade T. Picture processing by computer complex and recognition of human faces [Ph. D. Thesis]. Kyoto: Kyoto University, 1973.
19. Brunelli R, Poggio T. Face recognition: Features versus templates. IEEE Transactions on Pattem Analysis and Machine Intelligence. 1993, 15(10): pp. 1042～1052.
20. Feng GC, Yuen PC. Variance projection function and its application to eye detection for human face recognition. Pattern Recognition Letters. 1998, 19(9): pp. 899～906.
21. Feng GC, Yuen PC. Multi cues eye detection on gray intensity image. Pattern Recognition. 2001, 34(5): pp. 1033～1046.
22．耿新，周志华，陈世福．基于混合投影函数的眼睛定位．软件学报．2003，14(8)：pp．1394～1400．
23. Rein-Lien Hsu. Face Detection in Color Images. IEEE Transaction on Pattern Analysis and Machine Intelligence. 2002, 24(5): pp. 696-706.
24. C. Tony Huang and O. Robert Mitchell. A Euclidean Distance Transform Using Grayscale Morphology Decomposition. Pattern Analysis and Machine Intelligence, IEEE Transactions on Volume 16, 1994.
25. Paul T. Jackway. Gradient Watersheds in Morphological Scale-Space. IEEE Transactions on Image Processing. 1996, 5 (6): pp. 913-921.
26. Paul T. Jackway, Moharned Deriche. Scale-Space Properties of the Multiscale Morphological Dilation-Erosion. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1996, 18(1): pp. 38-51.
27．陈白帆，蔡自兴．基于尺度空间理论的Harris角点检测．中南大学学报(自然科学版)．2005，36(5)：pp．751-754．
28. L. Kitchen and A. Rosenfeld. Gray level Comer detection. Pattern Recognition Letters. 1982: pp. 95-102.
29. K. Brunnstrom, T. Lindeberg, and J. O. Eklundh. Active detection and classification of Junctions. Proc. 2nd European Conf. Computer Vision LNCS 588. St. Margherita. Italy. 1992: pp. 701-709.
30. R. Haralick. Corner detection in color images by multiscalecombination of end-stopped cortical cells. Proc. IEEE Conf. Computer Vision and pattern Recognition.
31. W. Fosterner. A feature based correspondence algorithm for image matching. Intl. Arch. Photogramn. Remote Sensing 26, 1986: pp. 150-166.
32. Jian-Gang Wang, Eric Sung and Ronda Venkateswarlu. Eye Gaze Estimation from a Single Image of One Eye. Proceedings of the Ninth IEEE International Conference on Computer Vision. 2003
33. Andrew Fitzgibbon, Maurizio Pilu and Robert B. Fisher. Direct Least Square Fitting of Ellipses. IEEE Transaction on Pattern Analysis and Machine Intelligence. 1999, 21(5): pp. 253-257
34．王亮，胡卫明。谭铁牛．人运动的视觉分析综述。计算机学报．2002，25(3)．
35. J. F. Canny. A Computational approach to edge detection.IEEE Transactions on Pattern Analysis and Machine Itelligence. 1986: pp. 679-698
36．明英，蒋晶瑶，边馥苓．低分辨率目标的检测与实现．计算机工程．2005，31(1)：pp．179-180．
37．刘力双，张铫，卢慧卿，赵琳．图像的快速亚像素边缘检测方法．光电子·激光．2005，16(8)：pp．993-996．
38．刘卫光，崔江涛，周利华．插值和相位相关的图像亚像素配准方法．计算机辅助设计与图形学学报．2005，17(6)：pp．1273-1277．
39．陈艳琴，罗大庸．基于Kalman滤波和Mean Shift算法的人眼实时跟踪．模式识别与人工智能．2004，17(2)：pp．173-177．
2．Milan Sonka，Vaclav Hlavac，Roger Boyle等．图像处理、分析与机器视觉．第二版．北京：人民邮电出版社．2003．
3．孙荣恒．应用数理统计．第二版．北京：科学出版社．2003．
4. Yoshio Matsumotoy, Alexander Zelinsky. An Algorithm for Real-time Stereo Vision Implementation of Head Pose and Gaze Direction Measurement. Proceedings of Fourth International Conference on Automatic Face and Gesture Recognition, 2000: pp. 499-504.
5. Kin-Man Lam and Yan-Lin Li. An Efficient Approach for Facial Feature Detection. Proceedings oflCSP 98: pp. 1100-1103.
6. Yong Ma, Xiaoqing Ding, Zhenger Wang, Ning Wang. Robust Precise Eye Location Under Probabilistic Framework. Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004.
7．宋加涛，刘济林，池哲儒，王蔚．人脸正面图像中眼睛的精确定位．计算机辅助设计与图形学学报．2005，17(3)：pp．540-545．
8. Luis Jordao, Matteo Perrone and Joao Paulo Costeira. Active Face and Feature Tracking. Proc. of IEEE Conference on Computer Vision and Pattern Recognition, 1999.
9. Jie Zhu and Jie Yang. Subpixel Eye Gaze Tracking. Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition 2002
10. Shinjiro Kawato and Jun Ohya. Real-time Detection of Nodding and Head-shaking by Directly Detecting and Tracking the "Between-Eyes". Automatic Face and Gesture Recognition, 2000. Proceedings. Fourth IEEE International Conference, 2000: pp. 40-45.
11. Shinjiro Kawato and Jun Ohya. Two-step Approach for Real-time Eye Tracking with a New Filtering Technique Systems Man and Cybernetics. IEEE International Conference, 2000, 12(8): pp. 1366-1371.
12．苗守杰，刘希顺，刘安芝．一种快速精确的虹膜定位方法．微计算机信息．2005，21(11)．
13．王成儒，胡正平，练秋生．一种虹膜定位算法．计算机辅助设计与图形学学报．2002，14(10)：pp．950-952．
14．柴秀娟，山世光，高文．陈熙霖．基于样例学习的面部特征自动标定算法．软件学报．2005，16(5)：pp．718-726．
15. Zhiwei Zhu and Qiang Ji. Real Time 3D Face Pose Tracking From an Uncalibrated Camera. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 2004.
16. Raffaella Lanzarotti, N. Alberto Borghese and Paola Campadelli. Robust identification and matching of fiducial points for the reconstruction of 3D human faces from raw video sequences. Proceedings of the First International Symposium on 3D Data Processing Visualization and Transmission 2002.
17．林维训，潘纲，吴朝晖，潘云鹤．脸部特征定位方法综述．中国图象图形学报．2003，8(8)：pp．849-859．
18. Kanade T. Picture processing by computer complex and recognition of human faces [Ph. D. Thesis]. Kyoto: Kyoto University, 1973.
19. Brunelli R, Poggio T. Face recognition: Features versus templates. IEEE Transactions on Pattem Analysis and Machine Intelligence. 1993, 15(10): pp. 1042～1052.
20. Feng GC, Yuen PC. Variance projection function and its application to eye detection for human face recognition. Pattern Recognition Letters. 1998, 19(9): pp. 899～906.
21. Feng GC, Yuen PC. Multi cues eye detection on gray intensity image. Pattern Recognition. 2001, 34(5): pp. 1033～1046.
22．耿新，周志华，陈世福．基于混合投影函数的眼睛定位．软件学报．2003，14(8)：pp．1394～1400．
23. Rein-Lien Hsu. Face Detection in Color Images. IEEE Transaction on Pattern Analysis and Machine Intelligence. 2002, 24(5): pp. 696-706.
24. C. Tony Huang and O. Robert Mitchell. A Euclidean Distance Transform Using Grayscale Morphology Decomposition. Pattern Analysis and Machine Intelligence, IEEE Transactions on Volume 16, 1994.
25. Paul T. Jackway. Gradient Watersheds in Morphological Scale-Space. IEEE Transactions on Image Processing. 1996, 5 (6): pp. 913-921.
26. Paul T. Jackway, Moharned Deriche. Scale-Space Properties of the Multiscale Morphological Dilation-Erosion. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1996, 18(1): pp. 38-51.
27．陈白帆，蔡自兴．基于尺度空间理论的Harris角点检测．中南大学学报(自然科学版)．2005，36(5)：pp．751-754．
28. L. Kitchen and A. Rosenfeld. Gray level Comer detection. Pattern Recognition Letters. 1982: pp. 95-102.
29. K. Brunnstrom, T. Lindeberg, and J. O. Eklundh. Active detection and classification of Junctions. Proc. 2nd European Conf. Computer Vision LNCS 588. St. Margherita. Italy. 1992: pp. 701-709.
30. R. Haralick. Corner detection in color images by multiscalecombination of end-stopped cortical cells. Proc. IEEE Conf. Computer Vision and pattern Recognition.
31. W. Fosterner. A feature based correspondence algorithm for image matching. Intl. Arch. Photogramn. Remote Sensing 26, 1986: pp. 150-166.
32. Jian-Gang Wang, Eric Sung and Ronda Venkateswarlu. Eye Gaze Estimation from a Single Image of One Eye. Proceedings of the Ninth IEEE International Conference on Computer Vision. 2003
33. Andrew Fitzgibbon, Maurizio Pilu and Robert B. Fisher. Direct Least Square Fitting of Ellipses. IEEE Transaction on Pattern Analysis and Machine Intelligence. 1999, 21(5): pp. 253-257
34．王亮，胡卫明。谭铁牛．人运动的视觉分析综述。计算机学报．2002，25(3)．
35. J. F. Canny. A Computational approach to edge detection.IEEE Transactions on Pattern Analysis and Machine Itelligence. 1986: pp. 679-698
36．明英，蒋晶瑶，边馥苓．低分辨率目标的检测与实现．计算机工程．2005，31(1)：pp．179-180．
37．刘力双，张铫，卢慧卿，赵琳．图像的快速亚像素边缘检测方法．光电子·激光．2005，16(8)：pp．993-996．
38．刘卫光，崔江涛，周利华．插值和相位相关的图像亚像素配准方法．计算机辅助设计与图形学学报．2005，17(6)：pp．1273-1277．
39．陈艳琴，罗大庸．基于Kalman滤波和Mean Shift算法的人眼实时跟踪．模式识别与人工智能．2004，17(2)：pp．173-177．