High speed gaze tracking with visible light

Some gaze tracking systems have been proposed in the field, but very few of them can be directly applied in normal lighting environments. Many image imperfection issues are difficult to be dealt with so that a typical system is usually equipped with a strong infrared ray (IR) illuminant. The user experience is not so good even if the IR illuminant is invisible. In this paper, we present a high speed (240 frames/s) gaze tracking system operating in a normal office lighting condition. A set of image processing algorithms to deal with the issues of poor image contrast and high random noise have been presented. The experimental result shows that the system can achieve the accuracy of 1° and 1.7° for the horizontal and vertical coordinates of the detected iris center, respectively.

[1]  K. Preston White,et al.  Spatially dynamic calibration of an eye-tracking system , 1993, IEEE Trans. Syst. Man Cybern..

[2]  David Beymer,et al.  Eye gaze tracking using an active stereo head , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[3]  King Ngi Ngan,et al.  Face segmentation using skin-color map in videophone applications , 1999, IEEE Trans. Circuits Syst. Video Technol..

[4]  Jose Sigut,et al.  Iris Center Corneal Reflection Method for Gaze Tracking Using Visible Light , 2011, IEEE Transactions on Biomedical Engineering.

[5]  L. Trefethen,et al.  Numerical linear algebra , 1997 .

[6]  Ioannis Pitas,et al.  A novel method for automatic face segmentation, facial feature extraction and tracking , 1998, Signal Process. Image Commun..

[7]  A. Nait-Ali,et al.  An adaptive calibration of an infrared light device used for gaze tracking , 2002, IMTC/2002. Proceedings of the 19th IEEE Instrumentation and Measurement Technology Conference (IEEE Cat. No.00CH37276).

[8]  E. Reinhard Photographic Tone Reproduction for Digital Images , 2002 .

[9]  Abdesselam Bouzerdoum,et al.  Skin segmentation using color pixel classification: analysis and comparison , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  N. Ramanauskas,et al.  Calibration of Video-Oculographical Eye-Tracking System , 2006 .

[11]  Carlos Hitoshi Morimoto,et al.  Pupil detection and tracking using multiple light sources , 2000, Image Vis. Comput..

[12]  Narendra Ahuja,et al.  Appearance-based eye gaze estimation , 2002, Sixth IEEE Workshop on Applications of Computer Vision, 2002. (WACV 2002). Proceedings..

[13]  Peter D. Lawrence,et al.  Noncontact Binocular Eye-Gaze Tracking for Point-of-Gaze Estimation in Three Dimensions , 2009, IEEE Transactions on Biomedical Engineering.

[14]  Baozong Yuan,et al.  A novel approach for human face detection from color images under complex background , 2001, Pattern Recognit..

[15]  Peter D. Lawrence,et al.  Fixation Precision in High-Speed Noncontact Eye-Gaze Tracking , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[16]  Wen-Chung Kao,et al.  Real-time tone reproduction for video recording , 2012, 2012 IEEE 16th International Symposium on Consumer Electronics.

[17]  Erik Reinhard,et al.  Parameter Estimation for Photographic Tone Reproduction , 2002, J. Graphics, GPU, & Game Tools.

[18]  Zhiwei Zhu,et al.  Eye and gaze tracking for interactive graphic display , 2002, SMARTGRAPH '02.

[19]  Dongheng Li,et al.  Starburst: A hybrid algorithm for video-based eye tracking combining feature-based and model-based approaches , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.