Eye Tracking and ROI Detection within a Computer Screen Using a Monocular Camera

  • Guangmin Sun Faculty of Information Technology, Beijing University of Technology, 100 Pingleyuan, Beijing 100124, China
  • Junjie Zhang Faculty of Information Technology, Beijing University of Technology, 100 Pingleyuan, Beijing 100124, China
  • Kun Zheng Faculty of Information Technology, Beijing University of Technology, 100 Pingleyuan, Beijing 100124, China
  • Xiaohui Fu Faculty of Information Technology, Beijing University of Technology, 100 Pingleyuan, Beijing 100124, China
Keywords: iris detection, gaze tracking, monocular camera, ROI detection

Abstract

The region of interest will change according to the task, even in the same situation. In the study, a method for region of interest detection within a computer screen using a monocular camera is proposed. In contrast to gaze tracking techniques that require particular devices (e.g., an eye tracker and RGB-D device) meanwhile complex calibration, a cheap and more convenient monocular camera is used in this study to solves the eye gaze tracking problem. Firstly, Human face is detected in a real-time video sequence using HoG features. Then, the landmarks around the eyes, which reflect the gaze position, are extracted. Next, the iris centers are detected in the eye region. In order to reduce the gaze error caused by head movement, a three-dimensional head model is proposed to estimate head pose. Finally, the eye region is tracked by calculating the eye vectors and head movement. Experiments were performed to evaluate the face detection, landmarks, iris detection, eye movement estimation, and head pose estimation on databases such as the Hong Kong, BioID, and Boston University head pose databases. Besides, experiments for gaze tracking were performed for a real-time video sequence. Deviation is calculated using Euclidean distance between the real and estimated points. The results show that the method achieves an average error of 1.85∘ with head fixed and 3.58∘ with head movement in the range of −45∘ and 45∘. The requirement is detecting the user’s attention in the screen area. Our method can reach the same level to the other methods, even though the accuracy is not state-of-the-art. Meanwhile, as we all know not only a specific point is concerned but also a region area according to the characteristics of human eye imaging, thus the proposed method can meet the requirements of demand.

Downloads

Download data is not yet available.

Author Biographies

Guangmin Sun, Faculty of Information Technology, Beijing University of Technology, 100 Pingleyuan, Beijing 100124, China

Guangmin Sun was born in Shanxi, China, in 1960. He received the B.Sc. degree in electronic engineering from Beijing Institute of Technology, Beijing, China, in 1982, the M.Sc. degree in communication and information systems from Nanjing University of Science and Technology, Nanjing, China, in 1991, and the Ph.D. degree in communication and information systems from Xidian University, Xi’an, China, in 1997. He is currently a Professor with the Beijing University of Technology. His current research interests include neural networks and applications, image processing, and pattern recognition.

Junjie Zhang, Faculty of Information Technology, Beijing University of Technology, 100 Pingleyuan, Beijing 100124, China

Junjie Zhang was born in Beijing, China, in 1993. He received his B.Sc degree in 2015 from Beijing University of Technology, Beijing, China. He combined master and doctor degree. He is currently pursuing his Ph.D. degree in Beijing University of Technology, China.

Kun Zheng, Faculty of Information Technology, Beijing University of Technology, 100 Pingleyuan, Beijing 100124, China

Kun Zheng was born in Hebei, China, in 1977. He received the B.Sc. degree in electronic engineering from Hebei University, Hebei, China, in 2001, M.Sc. degree in Software Engineering from Beijing University of Technology, Beijing, China, in 2006, and Ph.D. degree in Electronic Engineering from Beijing University of Technology in 2018. He is currently an associate professor with Beijing University of Technology. His current research interests include neural networks and applications, image processing, and intelligent education.

Xiaohui Fu, Faculty of Information Technology, Beijing University of Technology, 100 Pingleyuan, Beijing 100124, China

Xiaohui Fu was born in Hubei, China, in 1994. She received her B.Sc degree in 2016 from Wuhan University of Technology, Wuhan, China, and M.Sc. degree in 2019 from Beijing University of Technology, Beijing,China.

References

B.Li, H.Fu, D.Wen, et al. ‘Etracker: A Mobile Gaze-Tracking System with Near-Eye Display Based on a Combined Gaze-Tracking Algorithm’. Sensors (Basel), 18(5) pp. 1626-1644,2018.

W.Zhang,‘Eye gaze estimation from the elliptical features ofoneiris’. Optical Engineer-ing, 50(4),pp. 047003,2011.

R.Valenti, N.Sebe, T.Gevers. ‘Combining Head Pose and Eye Location Information for Gaze Estimation’. IEEE Transactions on Image Processing, 21(2), pp. 802-815, 2012.

A.Kasinski, A. Schmidt. ‘The architecture and performance of the face and eyes detec-tion system based on the Haar cascade classifiers’. Pattern Analysis & Applica-tions, 13(2), pp. 197-211, 2010.

Y. M.Cheung, Q.Peng,‘Eye Gaze Tracking With a Web Camera in a Desktop Envi-ronment’. IEEE Transactions on Human-Machine Systems, 45(4), pp. 419-430, 2015.

Y.Sun,L.Yin,‘Facial Expression Recognition Based on 3D Dynamic Range Model Se-quences’. 10(10), pp. 58-71, 2008.

D. Li, W. Pedrycz, ‘A central profile-based 3d face pose estimation’, Pattern Recogni-tion, 47(2), pp. 525-534, 2014.

S.Kong, R.Oyini Mbouna. ‘Head Pose Estimation from a 2-D Face Image using 3-D Face Morphing with Depth Parameters’. IEEE Transactions on Image Processing, 24(6), pp. 1-1, 2015.

T.Ojala, M.Pietikainen, T. Maenpaa,‘Multiresolution gray-scale and rotation invariant texture classification with local binary pattern’, IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7), pp. 971-987, 2002.

P.Viola, M.Jones,‘Robust Real-time Face Detection’. International Journal of Com-puter Vision, 57(2), pp. 137-154, 2004.

B. C.Ko, Son, Jung Eun, Nam, Jae-Yeal. ‘View-invariant, partially occluded human detection in still images using part bases and random forest’. Optical Engineering, 54(5), pp. 053113, 2015.

K.Qian, X.Chen, B.Sun,‘Compressive tracking based on locality sensitive histograms’. Pattern Recognition, 72(12), pp. 517-531, 2017.

C.Sagonas, E.Antonakos, G.Tzimiropoulos, et al. ‘300 Faces In-The-Wild Challenge: database and results’. Image & Vision Computing, 47(2), pp. 3-18, 2016.

L.Chen, H.Man, A. V. Nefian,‘Face recognition based on multi-class mapping of Fisher scores’. Pattern Recognition, 38(6), pp. 799-811, 2005.

O.Richard Duda. ‘Use of the Hough transformation to detect lines and curves in pic-tures’. 15(1), pp. 11-15, 1972.

Eye and gaze tracking for interactive graphic display. Machine Vision and Applica-tions, 15(3), pp.139-148, 2004.

C. W.Cho, W. L.Ji, K. Y.Shin, et al. ‘Gaze detection by wearable eye-tracking and NIR LED-based head-tracking device based on SVR’. ETRI Journal, 34(4) , pp. 542-552, 2012.

C. H.Morimoto, M. R. M.Mimica,‘Eye gaze tracking techniques for interactive appli-cations’. Computer Vision & Image Understanding, 98(1), pp. 4-24, 2015.

G Fanelli, M. Dantone, et al. ‘Random Forests for Real Time 3D Face Analysis’. In-ternational Journal of Computer Vision,101(3), pp. 437-458, 2013.

G Fanelli, M. Dantone. ‘Random Forests for Real Time 3D Face Analysis’. Interna-tional Journal of Computer Vision, 101(3), pp. 437-458, 2013.

L.Tamara Berg, C. Alexander Berg, ‘Jaety Edwards, David A. Forsyth’. Who’s in the Picture. Neural Information Processing Systems(NIPS), 2004.

L.L.Yu, X.M.Xia, K.J.Zhou, et al. ‘Affine invariant fusion feature extraction based on geometry descriptor and BIT for object recognition’. IET Image Processing, 13(1), pp. 57-72, 2018.

K. C.Lee, J.Ho, D. J.Kriegman,‘Acquiring linear subspaces for face recognition under variable lighting’. IEEE Trans Pattern Anal Mach Intell, 27(5), pp. 684-698, 2005.

L.Chen, H.Man, A. V. Nefian,‘Face recognition based on multi-class mapping of Fisher scores’. Pattern Recognition, 38(6), pp. 799-811, 2005.

J.Wu, Z.H.Zhou,‘Efficient face candidates selector for face detection’. Pattern Recog-nition, 36(5), pp. 1175-1186, 2003.

G.Fanelli,‘Real Time dead Pose Estimation from Consumer Depth Cameras’, Interna-tional Conference on Pattern Recognition. Springer-Verlag, 6835(1), pp. 101-110, 2011.

N.Gourier, D.Hall, J. L.Crowley,‘Estimating Face orientation from Robust Detection of Salient Facial Structures’. Fg Net Workshop on Visual Observation of Deictic Gestures, 2004.

N.Salehi, M.Keyvanara, A.Monadjemi. ‘Robust Real-Time Gradient-based Eye De-tection and Tracking Using Transform Domain and PSO-Based Feature Selec-tion’. Elcvia Electronic Letters on Computer Vision & Image Analysis, 16(1), pp. 15-32, 2015.

J. Zhu, J. Yang, Subpixel eye gaze tracking, Proc. 5th IEEE Int. Conf. Autom. Face Gesture Recog., pp.124-129, 2002.

D. Torricelli, S. Conforto, M. Schmid, T. DAlessio, ‘A neural-based remote eye gaze tracker under natural head motion’, Comput. Methods Programs Biomed., 92(1) , pp. 66-7, 2008.

Y. Sugano, Y. Matsushita, Y. Sato, H. Koike, ‘An incremental learning method for unconstrained gaze estimation’, Proc. Comput. Vis., 5304(1), pp. 656-667, 2008.

F. Lu, T. Okabe, Y. Sugano, Y. Sato, ‘Learning gaze biases with head motion for head pose-free gaze estimation’, Image Vis. Comput., 32(3), pp. 169-179, 2014.

F. Lu, Y. Sugano, T. Okabe, Y. Sato, ‘Adaptive linear regression for appearance-based gaze estimation’, IEEE Trans. Pattern Anal. Mach. Intell., 36(10), pp. 2033-2046, 2014.

Y. M.Cheung, Q.Peng. ‘Eye Gaze Tracking With a Web Camera in a Desktop Envi-ronment’. IEEE Transactions on Human-Machine Systems, 45(4), pp. 419-430, 2015.

R.Valenti, N.Sebe, T.Gevers. ‘Combining Head Pose and Eye Location Information for Gaze Estimation’. IEEE Transactions on Image Processing, 21(2), pp. 802-815, 2011.

Published
2020-12-24
Section
Advanced Practice in Web Engineering