基于人工神经网络动态标定算法的低成本视线追踪系统
|
摘要
针对视线追踪系统成本高、标定算法复杂的问题,研究了一种低成本视线追踪系统.系统采用低成本网络摄像头,采集到的图像首先采用Haar-like特征与肤色结合算法来进行人脸检测,并利用主动表现模型算法和光流法定位并跟踪人脸特征点;然后利用梯度向量法进行瞳孔中心检测;为了提高系统精度和鲁棒性,提出了一种人工神经网络的动态标定算法.实验表明,视线追踪系统不仅具有很好的鲁棒性,而且具有较高的精度,在头部静止的情况下平均误差为1.34°,在头部运动的情况下平均误差为3.26°.
In order to reduce the cost of eye-gaze tracking system and simplify the complexity of the calibration algorithm,a low-cost eye-gaze tracking system was developed.The Haar-like feature and skin color combination algorithm were used to detect the human face.The active appearance model(AAM)algorithm and the optical flow method were used to locate and track the face feature points.And the pupil center was detected by the gradient vector method.An artificial neural network dynamic calibration algorithm was proposed to improve the tracking accuracy and robustness.Experiments show that the eye-gaze tracking system not only has better robustness,but also has higher precision.The average error of the system is 1.34°at head rest,and 3.26°at head movement.
In order to reduce the cost of eye-gaze tracking system and simplify the complexity of the calibration algorithm,a low-cost eye-gaze tracking system was developed.The Haar-like feature and skin color combination algorithm were used to detect the human face.The active appearance model(AAM)algorithm and the optical flow method were used to locate and track the face feature points.And the pupil center was detected by the gradient vector method.An artificial neural network dynamic calibration algorithm was proposed to improve the tracking accuracy and robustness.Experiments show that the eye-gaze tracking system not only has better robustness,but also has higher precision.The average error of the system is 1.34°at head rest,and 3.26°at head movement.
引文
[1]Ohno T,Mukawa N.A free-head,simple calibration,gaze tracking system that enables gaze-based interaction[C]∥Proceedings of the 2004Symposium on Eye Tracking Research&Applications.[S.l.]:ACM,2004:115-122.
[2]Sigut J,Sidha S A.Iris center corneal reflection method for gaze tracking using visible light[J].IEEE Transactions on Biomedical Engineering,2011,58(2):411-419.
[3]Zhu Z,Ji Q.Novel eye gaze tracking techniques under natural head movement[J].IEEE Transactions on Biomedical Engineering,2007,54(12):2246-2260.
[4]Sigut J,Sidha S A.Iris center corneal reflection method for gaze tracking using visible light[J].IEEE Transactions on Biomedical Engineering,2011,58(2):411-419.
[5]Wojciechowski A,Fornalczyk K.Single web camera robust interactive eye-gaze tracking method[J].Bulletin of the Polish Academy of Sciences Technical Sciences,2015,63(4):879-886.
[6]Valenti R,Sebe N,Gevers T.Combining head pose and eye location information for gaze estimation[J].IEEE Transactions on Image Processing,2012,21(2):802-815.
[7]Williams O,Blake A,Cipolla R.Sparse and semi-supervised visual mapping with the S^3GP[C]∥Proceedings of Computer Vision and Pattern Recognition,2006IEEE Computer Society Conference on.[S.l.]:IEEE,2006:230-237.
[8]Lu F,Sugano Y,Okabe T,et al.Adaptive linear regression for appearance-based gaze estimation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(10):2033-2046.
[9]Cuong N H,Hoang H T.Eye-gaze detection with a single webcam based on geometry features extraction[C]∥Proceedings of Control Automation Robotics&Vision(ICARCV),2010 11th International Conference on.[S.l.]:IEEE,2010:2507-2512.
[10]Cootes T F,Edwards G J,Taylor C J.Active appearance models[C]∥Proceedings of European Conference on Computer Vision.Berlin Heidelberg:Springer,1998:484-498.
[11]Yamazoe H,Utsumi A,Yonezawa T,et al.Remote gaze estimation with a single camera based on facialfeature tracking without special calibration actions[C]∥Proceedings of the 2008Symposium on Eye Tracking Research&Applications.[S.l.]:ACM,2008:245-250.
[12]Baluja S,Pomerleau D.Non-intrusive gaze tracking using artificial neural networks[M].Pittsburgh,USA:Carnegie Mellon University,1994.
[2]Sigut J,Sidha S A.Iris center corneal reflection method for gaze tracking using visible light[J].IEEE Transactions on Biomedical Engineering,2011,58(2):411-419.
[3]Zhu Z,Ji Q.Novel eye gaze tracking techniques under natural head movement[J].IEEE Transactions on Biomedical Engineering,2007,54(12):2246-2260.
[4]Sigut J,Sidha S A.Iris center corneal reflection method for gaze tracking using visible light[J].IEEE Transactions on Biomedical Engineering,2011,58(2):411-419.
[5]Wojciechowski A,Fornalczyk K.Single web camera robust interactive eye-gaze tracking method[J].Bulletin of the Polish Academy of Sciences Technical Sciences,2015,63(4):879-886.
[6]Valenti R,Sebe N,Gevers T.Combining head pose and eye location information for gaze estimation[J].IEEE Transactions on Image Processing,2012,21(2):802-815.
[7]Williams O,Blake A,Cipolla R.Sparse and semi-supervised visual mapping with the S^3GP[C]∥Proceedings of Computer Vision and Pattern Recognition,2006IEEE Computer Society Conference on.[S.l.]:IEEE,2006:230-237.
[8]Lu F,Sugano Y,Okabe T,et al.Adaptive linear regression for appearance-based gaze estimation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(10):2033-2046.
[9]Cuong N H,Hoang H T.Eye-gaze detection with a single webcam based on geometry features extraction[C]∥Proceedings of Control Automation Robotics&Vision(ICARCV),2010 11th International Conference on.[S.l.]:IEEE,2010:2507-2512.
[10]Cootes T F,Edwards G J,Taylor C J.Active appearance models[C]∥Proceedings of European Conference on Computer Vision.Berlin Heidelberg:Springer,1998:484-498.
[11]Yamazoe H,Utsumi A,Yonezawa T,et al.Remote gaze estimation with a single camera based on facialfeature tracking without special calibration actions[C]∥Proceedings of the 2008Symposium on Eye Tracking Research&Applications.[S.l.]:ACM,2008:245-250.
[12]Baluja S,Pomerleau D.Non-intrusive gaze tracking using artificial neural networks[M].Pittsburgh,USA:Carnegie Mellon University,1994.