基于角膜反射法的视线追踪系统的视线落点校正研究

doi:10.3969/j.issn.1000-1158.2022.03.06

摘要
图/表
参考文献(17)
相关文章 (15)

全文: PDF (2077 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要为了提高视线追踪系统的精度,将屏幕均分为6行8列共48个区域,在每个区域的中央设立校准点,测试者依次注视每个校准点,从而计算出48个校准点处的误差,将误差分解为X轴和Y轴两向误差,并把两向误差作为校正值分别进行曲面插值,从而获得整个屏幕内任意位置的X向和Y向校正值,使用校正值对视线落点的坐标进行校正。相对于目前较好的校正方法,采用该方法校正后X向误差降低了35.8%,Y向误差降低了53.3%;该视线落点校正方法的校正效果明显提升,可以有效地提高视线落点预测的精度。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	胡锴
	穆平安
	黄世龙

关键词 ：计量学, 视线追踪, 交比不变性, 瞳孔中心检测, 径向基插值

Abstract：In order to improve the accuracy of the system. The screen is divided into 6 rows and 8 columns, a total of 48 areas. Calibration points are set in the center of each area, and the tester looks at each calibration point in turn to calculate the 48 errors. The errors are decomposed into X-axis and Y-axis errors, and then the X-axis and Y-axis errors are used as calibration values and are interpolated to obtain the X-axis and Y-axis calibration values for any position within the entire screen. At last, X-axis and Y-axis calibration values are used to correct the X-axis and Y-axis coordinates of fixation point. Compared with the current better calibration method, the X-axis error is reduced by 35.8%, and the Y-axis error is reduced by 53.3%. The correction effect of this correction method is significantly improved, which can effectively improve the accuracy of eye tracking.

Key words： metrology eye tracking cross ratio invariance pupil center detection radial basis function

收稿日期: 2020-12-21 发布日期: 2022-03-23

PACS:

TB96

基金资助:2021年学位点引导布局与建设培训项目(XWDB2021105)

作者简介: 胡锴(1994-),江西上饶人,上海理工大学硕士研究生,主要研究方向为图像处理。Email：2971913255@qq.com

引用本文:

胡锴,穆平安,黄世龙. 基于角膜反射法的视线追踪系统的视线落点校正研究[J]. 计量学报, 2022, 43(3): 331-337.
HU Kai,MU Ping-an,HUANG Shi-long. Research on Correction of Fixation Point of Corneal-reflection-based Eye Tracking System. Acta Metrologica Sinica, 2022, 43(3): 331-337.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2022.03.06 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2022/V43/I3/331

［1］Laddi A, Prakash N R. Eye gaze tracking based directional control interface for interactive applications［J］. Multimedia Tools and Applications, 2019, 78(22): 31215-31230.
［2］Santis A D, Iacoviello D. Robust real time eye tracking for computer interface for disabled people［J］. Computer Methods and Programs in Biomedicine, 2009, 96(1): 1-11.
［3］Sunmyung P. A study on the characteristics of consumer visual-perceptional information acquisition in commercial facilities in regard to its construction of space from real-time eye gaze tracking［J］. Science of Emotion and Sensibility, 2018, 21(2): 3-14.
［4］Lee D, Yoon H, Hong H, et al. Fuzzy-system-based detection of pupil center and corneal specular reflection for a driver-gaze tracking system based on the symmetrical characteristics of face and facial feature points［J］. Symmetry, 2017, 9(11): 267-298.
［5］Xue N, Cai S W, Chen Y Y, et al. Gaze-tracking algorithm based on infrared gray image［J］. International Journal of Performability Engineering, 2019, 15(11): 2891-2898.
［6］Lu S F, Li R C, Jiao J N, et al. An eye gaze tracking method of virtual reality headset using a single camera and multi-light source［J］. Journal of Statistical Mechanics: Theory and Experiment, 2020, 1518(1): 12020-12029.
［7］Pamungkas D S, Erico A, Handri T. Controlling robot eyes using pupil detection［J］. Advanced Science Letters, 2018, 24(12): 9563-9566.
［8］Jang K S. Pupil detection using PCA and hough transform［J］. Journal of the Korea Society of Computer and Information, 2017, 22(2): 21-27.
［9］Martinikorena I, Cabeza R, Villanueva A, et al. Fast and robust ellipse detection algorithm for head-mounted eye tracking systems［J］. Journal of Computational and Theoretical Nanoscience, 2018,29(5): 845-860.
［10］梅向明,刘增贤,王汇淳,等. 高等几何［M］. 北京: 高等教育出版社,2008: 44-56.
［11］Yoshinobu E, Kiyotaka F. Head-free, remote eye-gaze detection system based on pupil-corneal reflection method with easy calibration using two stereo-calibrated video cameras［J］. IEEE Transactions on Biomedical Engineering, 2013, 60(10): 2952-60.
［12］张吉焱,刘文丽,高明亮,等. 人眼角膜参数计量校准与量值溯源方法研究［J］. 计量学报,2020, 41(11): 1339-1343.
Zhang J Y, Liu W L, Gao M L, et al. Calibration and Traceability Method for Human Cornea Parameters［J］. Acta Metrologica Sinica, 2020, 41(11): 1339-1343.
［13］Mestre C, Gautier J, Pujol J. Robust eye tracking based on multiple corneal reflections for clinical applications［J］. Journal of biomedical optics, 2018, 23(3):1-9.
［14］李抵非,陈赫,冯志刚,等. 一种双目立体视觉系统的校准方法［J］. 计量学报,2018, 39(4): 485-489.
Li D F, Chen H, Feng Z G, et al. A Calibration Method of Binocular Vision System［J］. Acta Metrologica Sinica, 2018, 39(4): 485-489.
［15］Coutinho F L, Morimoto C H. Improving head movement tolerance of cross-ratio based eye trackers［J］. International Journal of Computer Vision, 2013, 101(3): 459-481.
［16］兰善伟. 基于瞳孔角膜反射视线追踪技术的研究［D］. 哈尔滨: 哈尔滨工业大学, 2014: 31-33.
［17］Esmaeilbeigi M, Garmanjani G. Gaussian radial basis function interpolant for the different data sites and basis centers［J］. Calcolo, 2017, 54(1): 155-166.