Compensation Method of Natural Head Movement for Gaze Tracking System Using an Ultrasonic Sensor for Distance Measurement
Abstract
:1. Introduction
- -
- We perform mathematical analyses of the change of relative positions between the PC and corneal SR according to various head movements such as rotations and translations based on X-, Y-, and Z-axes. Based on these analyses, we find that only the head movement (causing the change of Z-distance between the camera and user’s eye) can affect the accuracy of gaze detection.
- -
- Based on this result, we measure the change of Z-distance of user’s eye using a small sized ultrasonic sensor. The ultrasonic sensor-based method does not require complicated camera calibration and it measures the Z-distance much faster than stereo cameras.
- -
- The accuracy of measured Z-distance by the ultrasonic sensor can be greatly enhanced by using the change of inter-distance of two eyes in the image, and the actual inter-distance in 3D space is measured by the ultrasonic sensor and the detected positions of two pupil centers in the image during the procedure of user calibration.
- -
- By using the additional information of the change of movement of both eyes in X-axis of the image, we can discriminate the head rotation from the head translation in the direction of Z-axis.
2. Proposed Method for Compensating User’s Head Movement
2.1. Gaze Tracking Algorithm
2.2. Analyses of the Change of Pupil-Corneal SR Vectors According to Head Movements
Head Movements | X Axis | Y Axis | Z Axis |
---|---|---|---|
Translation | T_X{+, –} | T_Y{+, –} | T_Z{+, –} |
Rotation | R_X{+, –} (Pitch) | R_Y{+, –} (Yaw) | R_Z{+, –} (Roll) |
X Axis | Y Axis | Z Axis | |
---|---|---|---|
Translation | No change | No change | Change (Equation (14)) |
Rotation | Change (Equation (18)) | Change (Equation (22)) | No change |
2.3. Compensating the Head Movement
3. Experimental Results
3.1. Comparisons of Gaze Tracking Errors without and with Our Compensation Methods
Kinds of Head Movement | Average Gaze Detection Error (STD) | |
---|---|---|
Without our Method | With our Method | |
No head movement | 0.58 (0.06) | |
R_X– | 2.32 (0.42) | 0.81 (0.17) |
R_X+ | 2.69 (0.35) | 0.70 (0.19) |
R_Y– | 0.71 (0.18) | 0.69 (0.13) |
R_Y+ | 0.70 (0.09) | 0.65 (0.11) |
R_Z– | 0.74 (0.16) | 0.71 (0.70) |
R_Z+ | 0.70 (0.14) | 0.69 (0.16) |
T_X– | 0.73 (0.12) | 0.67 (0.10) |
T_X+ | 0.71 (0.13) | 0.61 (0.10) |
T_Y– | 0.68 (0.13) | 0.65 (0.17) |
T_Y+ | 0.68 (0.20) | 0.63 (0.10) |
T_Z– | 8.43 (1.32) | 0.74 (0.17) |
T_Z+ | 3.82 (0.98) | 0.77 (0.12) |
Average | 1.81 (0.11) | 0.69 (0.06) |
Subjects | Average Gaze Detection Error | |
---|---|---|
Without our Method | With our Method | |
1 | 1.71 | 0.67 |
2 | 1.71 | 0.59 |
3 | 1.81 | 0.59 |
4 | 1.89 | 0.74 |
5 | 2.04 | 0.75 |
6 | 1.80 | 0.64 |
7 | 1.80 | 0.77 |
8 | 1.64 | 0.72 |
9 | 1.88 | 0.75 |
10 | 1.79 | 0.7 |
Average | 1.81 | 0.69 |
Kinds of Head Movement | Range |
---|---|
R_X+ | 25° |
R_X– | 25° |
R_Y+ | 25° |
R_Y– | 25° |
R_Z+ | 25° |
R_Z– | 25° |
T_X+ | 2.5 cm |
T_X– | 2.5 cm |
T_Y+ | 3 cm |
T_Y– | 3 cm |
T_Z+ | 10 cm |
T_Z– | 10 cm |
3.2. Comparisons of Gaze Tracking Errors with Our Method and Commercial System
Head Movement | Gaze Detection Error (STD) | |
---|---|---|
Our Method | Commercial System | |
R_X+ | 0.70 (0.19) | 1.61 (0.73) |
R_X– | 0.81 (0.17) | 1.36 (0.50) |
R_Y+ | 0.65 (0.11) | 1.69 (0.24) |
R_Y– | 0.69 (0.13) | 1.87 (0.65) |
R_Z+ | 0.69 (0.16) | 0.79 (0.14) |
R_Z– | 0.71 (0.15) | 0.69 (0.02) |
T_X+ | 0.61 (0.10) | 1.04 (0.64) |
T_X– | 0.67 (0.10) | 1.08 (0.25) |
T_Y+ | 0.63 (0.10) | 1.05 (0.26) |
T_Y– | 0.65 (0.17) | 0.70 (0.12) |
T_Z+ | 0.77 (0.12) | 1.42 (0.17) |
T_Z– | 0.74 (0.17) | 4.53 (0.43) |
Average | 0.69 (0.14) | 1.49 (0.35) |
Head Movement | Gaze Detection Error (STD) | |
---|---|---|
Our Method | Commercial System | |
R_X+ | 0.70 (0.19) | 0.59 (0.24) |
R_X– | 0.81 (0.17) | 0.99 (0.52) |
R_Y+ | 0.65 (0.11) | 0.69 (0.55) |
R_Y– | 0.69 (0.13) | 0.77 (0.37) |
R_Z+ | 0.69 (0.16) | 0.92 (0.50) |
R_Z– | 0.71 (0.15) | 0.92 (0.42) |
T_X+ | 0.61 (0.10) | 1.01 (0.35) |
T_X– | 0.67 (0.10) | 0.90 (0.14) |
T_Y+ | 0.63 (0.10) | 1.17 (0.53) |
T_Y– | 0.65 (0.17) | 0.67 (0.24) |
T_Z+ | 0.77 (0.12) | 0.77 (0.29) |
T_Z– | 0.74 (0.17) | 0.87 (0.23) |
Average | 0.69 (0.14) | 0.86 (0.37) |
4. Conclusions
Acknowledgments
Author Contributions
Conflicts of Interest
References
- Duchowski, A.T. A breadth-first survey of eye-tracking applications. Behav. Res. Methods Instrum. Comput. 2002, 34, 455–470. [Google Scholar] [CrossRef] [PubMed]
- Murphy-Chutorian, E.; Trivedi, M.M. Head pose estimation in computer vision: A survey. IEEE Trans. Pattern Anal. Mach. Intel. 2009, 31, 607–626. [Google Scholar] [CrossRef] [PubMed]
- Amarnag, S.; Kumaran, R.S.; Gowdy, J.N. Real time eye tracking for human computer interfaces. In Proceedings of IEEE 2003 International Conference on Multimedia and Expo 2003 (ICME’03), Baltimore, MD, USA, 6–9 July 2003; pp. 557–560.
- Jacob, R.J.K. Eye Movement-Based Human-Computer Interaction Techniques: Toward non-Command Interfaces. In Advances Human-Computer Interaction; Ablex Publishing Co: Norwood, NJ, USA, 1993; pp. 151–190. [Google Scholar]
- Sibert, L.E.; Jacob, R.J.K. Evaluation of eye gaze interaction. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Hague, The Netherlands, 1–6 April 2000; pp. 281–288.
- Ohno, T. Quick menu selection task with eye mark. Trans. Inf. Process. Soc. Jpn. 1999, 40, 602–612. [Google Scholar]
- Cho, C.W.; Lee, H.C.; Gwon, S.Y.; Lee, J.M.; Jung, D.; Park, K.R.; Kim, H.-C.; Cha, J. Binocular gaze detection method using a fuzzy algorithm based on quality measurements. Opt. Eng. 2014, 53, 053111-1–053111-22. [Google Scholar] [CrossRef]
- Morimoto, C.H.; Mimica, M.R.M. Eye gaze tracking techniques for interactive applications. Comput. Vis. Image Underst. 2005, 98, 4–24. [Google Scholar] [CrossRef]
- Heo, H.; Lee, J.M.; Jung, D.; Lee, J.W.; Park, K.R. Nonwearable gaze tracking system for controlling home appliance. Sci. World J. 2014, 2014, 1–20. [Google Scholar]
- Lee, H.C.; Lee, W.O.; Cho, C.W.; Gwon, S.Y.; Park, K.R.; Lee, H.; Cha, J. Remote gaze tracking system on a large display. Sensors 2013, 13, 13439–13463. [Google Scholar] [CrossRef] [PubMed]
- Bang, J.W.; Lee, E.C.; Park, K.R. New computer interface combining gaze tracking and brainwave measurements. IEEE Trans. Consum. Electron. 2011, 57, 1646–1651. [Google Scholar] [CrossRef]
- LC Technologies, Inc. Available online: http://www.eyegaze.com/ (accessed on 31 March 2015).
- SMI. Available online: http://www.smivision.com/ (accessed on 31 March 2015).
- TheEyeTribe. Available online: https://theeyetribe.com/ (accessed on 31 March 2015).
- Zhu, Z.; Ji, Q. Novel eye gaze tracking techniques under natural head movement. IEEE Trans. Biomed. Eng. 2007, 54, 2246–2260. [Google Scholar] [PubMed]
- Ohno, T.; Mukawa, N. A Free-Head, Simple Calibration, Gaze Tracking System That Enables Gaze-Based Interaction. In Proceedings of the Symposium on Eye Tracking Research & Applications, San Antonio, TX, USA, 22–24 March 2004; pp. 115–122.
- Talmi, K.; Liu, J. Eye and gaze tracking for visually controlled interactive stereoscopic displays. Sign. Process.-Image Commun. 1999, 14, 799–810. [Google Scholar] [CrossRef]
- Cho, D.-C.; Kim, W.-Y. Long-range gaze tracking system for large movements. IEEE Trans. Biomed. Eng. 2013, 60, 3432–3440. [Google Scholar] [CrossRef] [PubMed]
- Hennessey, C.; Noureddin, B.; Lawrence, P. A Single Camera Eye-Gaze Tracking System with Free Head Motion. In Proceedings of the Symposium on Eye Tracking Research & Applications, San Diego, CA, USA, 27–29 March 2006; pp. 87–94.
- Huang, Y.; Wang, Z.; Tu, X. A real-time compensation strategy for non-contact gaze tracking under natural head movement. Chin. J. Electron. 2010, 19, 446–450. [Google Scholar]
- Lee, J.M.; Lee, H.C.; Gwon, S.Y.; Jung, D.; Pan, W.; Cho, C.W.; Park, K.R.; Kim, H.-C.; Cha, J. A new gaze estimation method considering external light. Sensors 2015, 15, 5935–5981. [Google Scholar] [CrossRef] [PubMed]
- Lee, H.C.; Luong, D.T.; Cho, C.W.; Lee, E.C.; Park, K.R. Gaze tracking system at a distance for controlling IPTV. IEEE Trans. Consum. Electron. 2010, 56, 2577–2583. [Google Scholar] [CrossRef]
- Shih, S.-W.; Liu, J. A novel approach to 3-D gaze tracking using stereo cameras. IEEE Trans. Syst. Man Cybern. Part B-Cybern. 2004, 34, 234–245. [Google Scholar] [CrossRef]
- Gonzalez, R.C.; Woods, R.E. Digital Image Processing, 1st ed.; Addison-Wesley: Boston, MA, USA, 1992. [Google Scholar]
- Ding, L.; Goshtasby, A. On the canny edge detector. Pattern Recognit. 2001, 34, 721–725. [Google Scholar] [CrossRef]
- Kirkpatrick, D.G.; Seidel, R. The ultimate planar convex hull algorithm. SIAM J. Comput. 1986, 15, 287–299. [Google Scholar] [CrossRef]
- Richard, H.; Andrew, Z. Multiple View Geometry in Computer Vision; Cambridge University Press: Cambridge, UK, 2000. [Google Scholar]
- Helmholtz, H. Treatise on Physiological Optics; Dover Publications, Inc.: New York, NY, USA, 1924. [Google Scholar]
- SRF08 -I2C Range Finder. Available online: http://www.robot-electronics.co.uk/products/sensors/ultrasonics/srf08-i2c-range-finder.html (accessed on 31 March 2015).
- Webcam C600. Available online: https://support.logitech.com/en_us/product/5869 (accessed on 10 April 2015).
- Siwon Optical Technology Corp. Available online: http://www.siwon.co.kr (accessed on 11 January 2016).
- KODAK PROFESSIONAL High-Speed Infrared Film. Available online: http://www.kodak.com/global/en/ professional/support/techPubs/f13/f13.pdf (accessed on 10 April 2015).
- OpenCV. Available online: http://www.opencv.org (accessed on 10 April 2015).
- Student’s T-Test. Available online: http://en.wikipedia.org/wiki/Student’s_t-test (accessed on 10 April 2015).
- Cohen, J. A power primer. Psychol. Bull. 1992, 112, 155–159. [Google Scholar] [CrossRef] [PubMed]
- Tobii. Available online: http:// www.tobii.com/ (accessed on 28 December 2015).
- Ishima, D.; Ebisawa, Y. Eye Tracking Based on Ultrasonic Position Measurement in Head Free Video-based Eye-gaze Detection. In Proceedings of the IEEE EMBS Asian-Pacific Conference on Biomedical Engineering, Kyoto, Japan, 20–22 October 2003; pp. 258–259.
© 2016 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons by Attribution (CC-BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Jung, D.; Lee, J.M.; Gwon, S.Y.; Pan, W.; Lee, H.C.; Park, K.R.; Kim, H.-C. Compensation Method of Natural Head Movement for Gaze Tracking System Using an Ultrasonic Sensor for Distance Measurement. Sensors 2016, 16, 110. https://doi.org/10.3390/s16010110
Jung D, Lee JM, Gwon SY, Pan W, Lee HC, Park KR, Kim H-C. Compensation Method of Natural Head Movement for Gaze Tracking System Using an Ultrasonic Sensor for Distance Measurement. Sensors. 2016; 16(1):110. https://doi.org/10.3390/s16010110
Chicago/Turabian StyleJung, Dongwook, Jong Man Lee, Su Yeong Gwon, Weiyuan Pan, Hyeon Chang Lee, Kang Ryoung Park, and Hyun-Cheol Kim. 2016. "Compensation Method of Natural Head Movement for Gaze Tracking System Using an Ultrasonic Sensor for Distance Measurement" Sensors 16, no. 1: 110. https://doi.org/10.3390/s16010110
APA StyleJung, D., Lee, J. M., Gwon, S. Y., Pan, W., Lee, H. C., Park, K. R., & Kim, H.-C. (2016). Compensation Method of Natural Head Movement for Gaze Tracking System Using an Ultrasonic Sensor for Distance Measurement. Sensors, 16(1), 110. https://doi.org/10.3390/s16010110