Practical Gaze Detection by Auto Pan/Tilt Vision System

  • Kang Ryoung Park
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2869)


This paper presents a practical method for detecting the point in the monitor where a user gazes by moving his face and eyes. Previous gaze detection system uses a wide view camera, which can capture the whole face of user. In such case, the image resolution is so low that the fine movements of user’s eye cannot be exactly detected and the accurate eye gaze position cannot be located consequently. So, we implement the gaze detection system with a wide view camera and a narrow view camera. Because the narrow view camera captures the eye image with high magnification, the eye position easily escapes from the narrow view camera by user’s facial movements. For these reasons, we adopt the functionalities of auto focusing and auto panning/tilting into the narrow view camera and those are performed based on the information of the detected 3D facial feature positions by the wide view camera. As experimental results, our gaze detection system operates in real-time and the gaze detection accuracy between the computed positions and the real ones is about 3.57 cm of RMS error.


Gaze detection Wide View and Narrow View Camera 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Azarbayejani, A.: Visually Controlled Graphics. IEEE Trans. PAMI 15(6), 602–605 (1993)Google Scholar
  2. 2.
    Park, K.R., et al.: Gaze Point Detection by Computing the 3D Positions and 3D Motions of Face. IEICE Trans. Inf.&Syst. E.83-D(4), 884–894 (2000)Google Scholar
  3. 3.
    Park, K.R., et al.: Gaze Detection by Estimating the Depth and 3D Motions of Facial Features in Monocular Images. IEICE Trans. Fundamentals E.82-A(10), 2274–2284 (1999)Google Scholar
  4. 4.
    Ohmura, K., et al.: Pointing Operation Using Detection of Face Direction from a Single View. IEICE Trans. Inf. & Syst. J72-D-II(9), 1441–1447 (1989)Google Scholar
  5. 5.
    Ballard, P., et al.: Controlling a Computer via Facial Aspect. IEEE Trans. on SMC 25(4), 669–677 (1995)Google Scholar
  6. 6.
    Gee, A., et al.: Fast visual tracking by temporal consensus. Image and Vision Computing 14, 105–114 (1996)CrossRefGoogle Scholar
  7. 7.
    Heinzmann, J., et al.: 3D Facial Pose and Gaze Point Estimation using a Robust Real-Time Tracking Paradigm. In: Proceedings of ICAFGR, pp. 142–147 (1998)Google Scholar
  8. 8.
    Rikert, T., et al.: Gaze Estimation using Morphable Models. In: Proc. of ICAFGR, pp. 436–441 (1998)Google Scholar
  9. 9.
    Ali-A-L, A., et al.: Man-machine interface through eyeball direction of gaze. In: Proc. of the Southeastern Symposium on System Theory, pp. 478–482 (1997)Google Scholar
  10. 10.
    Tomono, A., et al.: Eye Tracking Method Using an Image Pickup Apparatus. European Patent Specification-94101635 (1994)Google Scholar
  11. 11.
    Seika-Tenkai-Tokushuu-Go. ATR Journal (1996) Google Scholar
  12. 12.
    Eyemark Recorder Model EMR-NC, NAC Image Technology Cooperation Google Scholar
  13. 13.
    Porrill, J., et al.: Robust and optimal use of information in stereo vision. Nature 397(6714), 63–66 (1999)CrossRefGoogle Scholar
  14. 14.
    Varchmin, A.C. et al.: Image based recognition of gaze direction using adaptive methods. Gesture and Sign Language in Human-Computer Interaction. In: Proc. Int. Gesture Workshop, Berlin, Germany, pp. 245–257 (1998) Google Scholar
  15. 15.
    Heinzmann, J., et al.: Robust real-time face tracking and gesture recognition. Proc. of the IJCAI 2, 1525–1530 (1997)Google Scholar
  16. 16.
    Matsumoto, Y., et al.: An algorithm for real-time stereo vision implementation of head pose and gaze direction measurement. In: Proc. the ICAFGR, pp. 499–504 (2000)Google Scholar
  17. 17.
    Newman, R., et al.: Real-time stereo tracking for head pose and gaze estimation. In: Proceedings the 4th ICAFGR, pp. 122–128 (2000)Google Scholar
  18. 18.
    Betke, M., et al.: Gaze detection via self-organizing gray-scale units. In: Proc. Int. Workshop on Recog., Analy., and Tracking of Faces and Gestures in Real-Time System, pp. 70–76 (1999)Google Scholar
  19. 19.
    Park, K.R., et al.: Intelligent Process Control via Gaze Detection Technology. EAAI 13(5), 577–587 (2000)Google Scholar
  20. 20.
    Broida, T., et al.: Recursive 3-D Motion Estimation from a Monocular Image Sequence. IEEE Trans. Aerospace and Electronic Systems 26(4), 639–656 (1990)CrossRefGoogle Scholar
  21. 21.
    Fukuhara, T., et al.: 3D-motion estimation of human head for model-based image coding. IEE Proc. 140(1), 26–35 (1993)Google Scholar
  22. 22.
    Park, K.R., et al.: Facial and Eye Gaze detection. In: Bülthoff, H.H., Lee, S.-W., Poggio, T.A., Wallraven, C. (eds.) BMCV 2002. LNCS, vol. 2525, pp. 368–376. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  23. 23.
    Daugman, J.G.: High confidence visual recognition of personals by a test of statistical independence. IEEE Trans. Pattern Anal. Machine Intell. 15(11), 1148–1160 (1993)CrossRefGoogle Scholar
  24. 24.

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Kang Ryoung Park
    • 1
  1. 1.Division of Media TechnologySangmyung UniversitySeoulRepublic of Korea

Personalised recommendations