Abstract
Aiming at the problem of poor robustness of gaze estimation in non-contact gaze tracking system, the gaze tracking system of single-camera multi-light source is improved. Based on the algorithm of cross-invariant gaze estimation, the traditional gaze-point calibration algorithm is improved. Based on the structure of the eyeball model, the influence of corneal curvature of the eyeball on the sight placement error is analyzed. For the error caused by the angle between the optic axis and the optical axis, an improved dynamic adaptive calibration algorithm is proposed, which divides the screen into 3 * 3 sub-regions. For each sub-region, a mapping parameter is calculated respectively to form a parameter matrix. The current parameter is an optimal parameter value dynamically obtained from the matrix in real time and the current region parameter is extracted to obtain the final eye-point placement. Experiments show that this method has significant effect on line of sight calibration.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Duchowski, T.: Eye Tracking Methodology: Theory and Practice. Springer, New York (2003)
Zhu, Z., Ji, Q.: Eye and Gaze tracking for interactive graphic display. Mach. Vis. Appl. 15(3), 139–148 (2004)
Schnieders, D., Fu, X., Wong, K.: Reconstruction of display and eyes from a single image. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR’10), pp. 1442–1449 (2010)
Zhang, C., Chi, J., Zhang, Z., Wang, Z.: The research on eye tracking for gaze tracking system. Acta Automatica Sinica 36(8), 1051–1061 (2010). (in Chinese)
Yoo, D., Kim, J., Lee, B., Chung, M.: Non-contact eye gaze tracking system by mapping of corneal reflections. In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition, Washington, D.C. IEEE Computer Society, pp. 94–99 (2002)
Yoo, D., Chung, M.: A novel nonintrusive eye Gaze estimation using cross-ratio under large head motion. Comput. Vis. Image Underst. (CVIU) 98(1), 25–51 (2005)
Han, K., Wang, X., Zhang, Z.L., Zhao, H.N.: A novel remote eye Gaze tracking approach with dynamic calibration. In: Proceedings of 15th IEEE International Workshop on Multimedia Signal Processing (MMSP2013), pp. 111–116 (2013)
Coutinho, F., Morimoto, C.: A depth compensation method for cross-ratio based Eye tracking. In: Proceedings of Symposium on Eye-Tracking Research and Applications (ETRA’10), pp. 137–140 (2010)
Han, K., Wang, X., Yu, C.L.: An efficient visual tracking method based on single CCD camera. In: Proceedings of 11th IEEE International Conference on Machine Learning and Cybernetics (ICMLC2012), pp. 1163–1168 (2012)
Zhang, Y., Meng, C.: Iris segmentation based on ellipse detection for Gaze tracking system. In: 2017 2nd International Conference on Materials Science, Machinery and Energy Engineering (MSMEE 2017)
One Irrillisecond face alignment with an ensemble of regression trees. KAZEMIV, SULLIVANJ. Computer Vision and Pattern Recognition (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhou, Y., Wang, C., Jia, H. (2019). Study on the Calibration Method of Gaze Point in Gaze Tracking. In: Hung, J., Yen, N., Hui, L. (eds) Frontier Computing. FC 2018. Lecture Notes in Electrical Engineering, vol 542. Springer, Singapore. https://doi.org/10.1007/978-981-13-3648-5_103
Download citation
DOI: https://doi.org/10.1007/978-981-13-3648-5_103
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-3647-8
Online ISBN: 978-981-13-3648-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)