DOI QR코드

DOI QR Code

Glint Reconstruction Algorithm Using Homography in Gaze Tracking System

시선 추적 시스템에서의 호모그래피를 이용한 글린트 복원 알고리즘

  • Ko, Eun-Ji (Division of Digital Media, Ewha Womans University) ;
  • Kim, Myoung-Jun (Division of Digital Media, Ewha Womans University)
  • Received : 2014.09.03
  • Accepted : 2014.10.06
  • Published : 2014.10.31

Abstract

Remote gaze tracking system calculates the gaze from captured images that reflect infra-red LEDs in cornea. Glint is the point that reflect infra-red LEDs to cornea. Recently, remote gaze tracking system uses a number of IR-LEDs to make the system less prone to head movement and eliminate calibration procedure. However, in some cases, some of glints are unable to spot. In this case, it is impossible to calculate gaze. This study examines patterns of glints that are difficult to detect in remote gaze tracking system. Afterward, we propose an algorithm to reconstruct positions of missing glints that are difficult to detect using other detected glints. Based on this algorithm, we increased the number of valid image frames in gaze tracking experiments, and reduce errors of gaze tracking results by correcting glint's distortion in the reconstruction phase.

간접 시선 추적 시스템은 적외선 조명을 각막에 반사시켜 그 모습을 카메라로 촬영하여 얻은 이미지에서 시선을 계산한다. 적외선 조명이 각막에 반사되어 이미지에 나타난 점을 글린트라고 한다. 최근 간접 추적 시스템은 머리의 움직임에 민감하지 않고 캘리브레이션 과정을 거치지 않도록 하기 위해 여러 개의 적외선 조명, 즉 여러개의 글린트를 사용하는 경우가 많다. 하지만 실험 도중 글린트의 일부가 보이지 않을 수 있는데, 이러한 경우 해당 프레임에서는 시선 계산을 할 수 없게 된다. 본 논문에서는 여러 개의 적외선 조명을 사용하는 시선 추적 시스템에서 여러 가지 이유로 유실되거나 인식이 어려운 글린트의 모습을 살펴본 후, 인식이 가능한 나머지 글린트 위치를 이용하여 이러한 글린트의 위치를 복원하는 알고리즘을 제안한다. 이 알고리즘을 통해 시선 추적 시 유효한 이미지 프레임의 개수를 증가 시키고, 복원 단계에서 글린트의 위치 변형 모델을 이용하여 글린트의 왜곡 또한 보정하여 시선 추적 결과의 오차도 줄일 수 있다.

Keywords

References

  1. J. Merchant, R. Morrissette and J. L. Porterfield , "Remote Measurement of Eye Direction Allowing Subject Motion Over One Cubic Foot of Space," Biomedical Engineering, IEEE Transactions on, vol. 21, no. 4, pp. 309-317, July. 1974
  2. K. P. White, T. E. Hutchinson, and J. M. Carley, "Spatially dynamic calibration of an eye-tracking system," Systems, Man and Cybernetics, IEEE Transactions on , vol. 23, no. 4, pp. 1162-1168, Jul/Aug. 1993 https://doi.org/10.1109/21.247897
  3. Y. Ebisawa, "Improved video-based eye-gaze detection method," Instrumentation and Measurement, IEEE Transactions on , vol. 47, no. 4, pp. 948-955, Aug. 1998 https://doi.org/10.1109/19.744648
  4. C. H. Morimoto and M. R. M. Mimica, "Eye gaze tracking techniques for interactive applications," Computer Vision and Image Understanding, vol. 98, no. 1, pp. 4-24, April. 2005. https://doi.org/10.1016/j.cviu.2004.07.010
  5. Z. Zhu and Q. Ji, "Eye gaze tracking under natural head movements," Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, vol. 1, pp. 918-923. June. 2005.
  6. L. Sesma-Sanchez, A. Villanueva and R. Cabeza, "Gaze Estimation Interpolation Methods Based on Binocular Data," Biomedical Engineering, IEEE Transactions on, vol. 59, no. 8, pp. 2235-2243, Aug. 2012. https://doi.org/10.1109/TBME.2012.2201716
  7. Y. Ebisawa and K. Fukumoto, "Head-Free, Remote Eye-Gaze Detection System Based on Pupil-Corneal Reflection Method With Easy Calibration Using Two Stereo-Calibrated Video Cameras," Biomedical Engineering, IEEE Transactions on , vol. 60, no. 10, pp. 2952-2960, Oct. 2013. https://doi.org/10.1109/TBME.2013.2266478
  8. D. H. Yoo, and M. J. Chung, "A novel non-intrusive eye gaze estimation using cross-ratio under large head motion," Computer Vision and Image Understanding, vol. 98, no. 1, pp. 25-51, April. 2005. https://doi.org/10.1016/j.cviu.2004.07.011
  9. K. Han, X. Wang, Z. Zhang and H. Zhao, "A novel remote eye gaze tracking approach with dynamic calibration," Multimedia Signal Processing (MMSP), 2013 IEEE 15th International Workshop on, pp. 111-116, 2013.
  10. F. L. Coutinho, and C. H. Morimoto. "Improving head movement tolerance of cross-ratio based eye trackers." International journal of computer vision, vol. 101, no. 3, pp. 459-481, 2013. https://doi.org/10.1007/s11263-012-0541-8
  11. Z. Zhang and Q. Cai, "Improving cross-ratio-based eye tracking techniques by leveraging the binocular fixation constraint," in Proceedings of the Symposium on Eye Tracking Research and Applications. ACM, 2014.
  12. D. W. Hansen, L. Roholm, and I. G. Ferreiros, "Robust glint detection through homography normalization," in Proceedings of the Symposium on Eye Tracking Research and Applications, pp. 91-94. ACM, 2014.
  13. E. J. Ko and M. J. Kim, "User-Calibration Free Gaze Tracking System Model," Journal of the Korea Institute of Information and Communication Engineering, vol. 18, no. 5, pp. 1096-1102, May. 2014. https://doi.org/10.6109/jkiice.2014.18.5.1096
  14. D. W. Hansen, and Q. Ji, "In the Eye of the Beholder: A Survey of Models for Eyes and Gaze," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 32, no. 3, pp. 478-500, March. 2010. https://doi.org/10.1109/TPAMI.2009.30
  15. E. D. Guestrin, and E. Eizenman, "General theory of remote gaze estimation using the pupil center and corneal reflections," Biomedical Engineering, IEEE Transactions on , vol. 53, no. 6, pp. 1124-1133, June. 2006 https://doi.org/10.1109/TBME.2005.863952
  16. C. A. Hennessey, and P. D. Lawrence, "Improving the Accuracy and Reliability of Remote System-Calibration-Free Eye-Gaze Tracking," Biomedical Engineering, IEEE Transactions on , vol. 56, no. 7, pp. 1891-1900, July. 2009. https://doi.org/10.1109/TBME.2009.2015955
  17. R. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision, 2th ed. New York, NY:Cambridge University Press, 2003.
  18. F. Devernay, (2007). C/C++ minpack. http://devernay.free.fr/hacks/cminpack/.