정보처리학회논문지B (The KIPS Transactions:PartB)

한국정보처리학회 (Korea Information Processing Society)
권호 표지
DOI QR코드

DOI QR Code

동공 움직임, 각막 반사광 및 Kalman Filter 기반 시선 추적에 관한 연구

A Study on Gaze Tracking Based on Pupil Movement, Corneal Specular Reflections and Kalman Filter

  • 발행 : 2009.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구에서는 모니터, 카메라 및 눈동자 좌표계간의 복잡한 3차원 관계를 고려하지 않고, 동공의 중심 위치와 모니터의 구석에 설치된 적외선 조명에 의한 네 개의 조명 반사광 사이의 관계를 사용하여 2차원적인 변환 방법으로 사용자의 시선 위치를 파악한다. 동공중심과 조명 반사광을 정확하게 추출하고, 이를 통해 계산된 시선 위치 계산의 정확도에 영향을 줄 수 있는 오차 요소들을 보정하는 것이 본 연구의 목적이다. 이를 위하여, 동공 중심을 통해 계산된 시선위치와 실제 시선 축이 이루는 카파에러를 초기 1회의 사용자 캘리브레이션을 통해 보정하였다. 또한, 칼만 필터를 기반으로 눈의 급격한 움직임 변화에도 각막 조명 반사광을 안정적으로 추적하여 시선 위치를 정확하게 추적한다. 실험 결과, 제안한 연구방법의 시선 위치 추출 오차는 눈의 급격한 움직임 변화에 상관없이 약 1.0$^\circ$ 를 나타냈다.

In this paper, we could simply compute the user's gaze position based on 2D relations between the pupil center and four corneal specular reflections formed by four IR-illuminators attached on each corner of a monitor, without considering the complex 3D relations among the camera, the monitor, and the pupil coordinates. Therefore, the objectives of our paper are to detect the pupil center and four corneal specular reflections exactly and to compensate for error factors which affect the gaze accuracy. In our method, we compensated for the kappa error between the calculated gaze position through the pupil center and actual gaze vector. We performed one time user calibration to compensate when the system started. Also, we robustly detected four corneal specular reflections that were important to calculate gaze position based on Kalman filter irrespective of the abrupt change of eye movement. Experimental results showed that the gaze detection error was about 1.0 degrees though there was the abrupt change of eye movement.

키워드

참고문헌

  1. M. Yamato, A. Monden, K. Matsumoto, K. Inoue and K. Torii, 'Quick Button Selection with Eye Gazing for General GUI Environments,' International Conference on Software: Theory and Practice. pp.712-719, 2000
  2. 이의철, 박강령, '눈동자 시선 추적에 의한 3차원 1인칭 슈팅게임', 한국정보처리학회 논문지, 제12-B권 제4호, pp.465-472, 2005 https://doi.org/10.3745/KIPSTB.2005.12B.4.465
  3. L. E. Sibert and R. J. K. Jacob, 'Evaluation of Eye Gaze Interaction,' Proc. of the CHI'00, pp.281-288, ACM in New York, 2000 https://doi.org/10.1145/332040.332445
  4. C. H. G. Wright, R. D. Ferguson, S. F. Barrett, H. G. Rylander III, and A. J. Welch, 'Hybrid Eye Tracking for Computer-aided Retinal Surgery,' ISA Biomedical Sciences Instrumentation, Vol.32, pp.225-245, 1996
  5. Richard S. E. Keefe, Larry J. siever, Richard C. Mohs, Ann E. Peterson, Theresa R. Mahon, R. Lindsey Bergman and Kenneth L. Davis, 'Eye Tracking, Schizophrenic Symptoms, and Schizotypal Personality Disorder,' European Archives of Psychiatry and Clinical Neuroscience, Vol.239, No.1, pp.39-42, 1989 https://doi.org/10.1007/BF01739742
  6. A. Azarbayejani, 'Visual Controlled Graphics,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.15, No.6, pp.602-605, 1993 https://doi.org/10.1109/34.216730
  7. T. D. Rikert and M. J. Jones, 'Gaze Estimation Using Morphable Models,' Proc of the 3rd International Conference on Face and Gesture Recognition, pp.436-441, Nara, Japan, 1998
  8. S. W. Shih et al., 'A Novel Approach to 3-D Gaze Tracking Using Stereo Cameras,' IEEE Trans. on SMC, Part B, pp.234-245, 2004
  9. D. H. Yoo and M. J. Chung, 'Non-Intrusive Eye Gaze Estimation without Knowledge of Eye Pose,' Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp.785-790, Seoul, Korea, May 17-19, 2004 https://doi.org/10.1109/AFGR.2004.1301630
  10. 고유진, 이의철, 박강령, '적외선 환경에서 얼굴 및 눈동자 움직임이 자유로운 시선 위치 추적에 대한 연구', 2006년 한국차세대 컴퓨팅학회 논문 발표회, 일산 KINTEX, 2006년
  11. R. N. Aslin and B. McMurray, 'Automated Corneal-Reflection Eye Tracking in Infancy: Methodological Developments and Applications to Cognition,' Lawrence Erlbaum Associates, Inc., Infancy, Vol.6, No.2, pp.155-163, 2004 https://doi.org/10.1207/s15327078in0602_1
  12. You Jin Ko, Eui Chul Lee, Kang Ryoung Park, 'A Study on Robust Eye Gaze Tracking System Allowing the Natural Facial Movements,' ACCV'07 Workshop on Multidimensional and Multi-view Image Processing, Tokyo, 2007
  13. Y. J. Ko, E. C. Lee and K. R. Park, 'A Robust Gaze Detection Method by Compensating for Facial Movements Based on Corneal specular reflections,' Pattern Recognition Letters, Vol.29, Issue10, pp.1474-1485, 15 July, 2008 https://doi.org/10.1016/j.patrec.2008.02.026
  14. http://www.logitech.com/index.cfm/webcam_communications/webcams/&cl=kr,ko (accessed on 2008. 12 .9)
  15. E. C. Lee, K. R. Park, J. Kim, 'Fake Iris Detection By Using the Purkinje Image,' Lecture Notes in Computer Science (ICB'06), Vol.3832, pp.397-403, Hong Kong, China, January 5-7, 2006 https://doi.org/10.1007/11608288_53
  16. F. A. Jenkins and H. E. White, 'Fundamentals of Optics Fourth edition,' McGraw-Hill, 1981
  17. J. Zhu and J. Yang, 'Subpixel Eye Gaze Tracking,' in Proc. Fifth IEEE International Conference on Automatic Face and Gesture Recognition, pp.124-129, Washington, D.C, 2002
  18. E. C. Lee and K. R. Park, 'A Study on Eye Gaze Estimation Method Based on Cornea Model of Human Eye,' Lecture Notes in Computer Science (MIRAGE 2007), pp.307-317, INRIA Rocquencourt, France, 2007 https://doi.org/10.1007/978-3-540-71457-6_28
  19. D. H. Cho, K. R. Park and D. W. Rhee, 'A Study on Robust Iris Detection for User Authentication in Mobile Phone,' 4th International Conference on Asian Language Processing and Information Technology (ALPIT 2005), pp.61-66, Bangkok, Thailand, 2005
  20. G. A. Baxes, 'Digital Image Processing-Principles and Application,' Wiley, 1994
  21. N. Otsu, 'A Threshold Selection Method from Gray-Level Histograms,' IEEE Trans. Systems, Man, and Cybernetics, Vol.SMC-9, No.1, pp.62-66, 1979 https://doi.org/10.1109/TSMC.1979.4310076
  22. P. Artal, A. Benito and J. Tabernero, 'The Human Eye is An Example of Robust Optical Design,' Journal of Vision, Vol.6, No.1, pp.1-7, 2006 https://doi.org/10.1167/6.1.1
  23. Zhiwei Zhu, Qiang Ji, and Kikuo Fujimura, 'Combining Kalman Filtering and Mean Shift for Real Time Eye Tracking Under Active IR Illumination,' Proceedings of the 16th International Conference on Pattern Recognition, Vol.4, p.40318, 2002
  24. 김수찬, 유재하, 김덕원, 'Kalman Filter를 이용한 비접촉식 응시점 추정 시스템에서의 빠른 머리 이동의 보정', 대한전자공학회 논문지, 제44권, 제10호, pp.35-41, 2007
  25. Hua Yang, Greg Welch, 'Model-Based 3D Object Tracking Using an Extended-Extended Kalman Filter and Graphics Rendered Measurements', CVIIE '05: Proceedings of the Computer Vision for Interactive and Intelligent Environment, pp.85-96, Washington, DC, USA, 2005 https://doi.org/10.1109/CVIIE.2005.14
  26. A. Gullstrand, 'Helmholz's physiological optics,' Optical Society of America, pp.350-358, 1924
  27. 이의철, 박강령, 'HMD (Head Mounted Display)에서 시선 추적을 통한 3차원 게임 조작 방법 연구', 대한전자공학회 논문지, 제45권 2호 sp편, pp.49-64, 2008
  28. http://www.polhemus.com/?page=Motion_Patriot (accessedon 2008. 12 .9)
  29. http://safari.oreilly.com/9780596516130/the_condensation_algorithm (accessed on 2008.12.9)
  30. Sukwon Choi, Daijin Kim, 'Robust Head Tracking Using 3D Ellipdoidal Head Model in Particle Filter Pattern Recognition,', Pattern Recognition, Vol.41, No.9, 2008, accepted for publication https://doi.org/10.1016/j.patcog.2008.02.002