這篇論文提出了針對行動手機的眼睛追蹤。此方法整合了眼睛偵測、角點偵測和等照圖中心偵測去改善眼睛追蹤的效果。在追蹤方面則使用光流法。基於光流法特性和眼睛偵測的方法，使整套系統更機械化。此外也利用手機上的方向感測裝置將追蹤結果加速並增加估測注視方向的精確度。在幾個正臉錄像實驗中，此方法展示了眼睛追蹤的準確度和估測注視方向的精確度。

In this thesis, we propose an eye tracking and gaze estimation system for mobile phone. We integrate an eye detector, cornereye center and iso-center to improve pupil detection. The optical flow information is used for eye tracking. We develop a robust eye tracking system that integrates eye detection and optical-flow based image tracking. In addition, we further incorporate the orientation sensor information from the mobile phone to improve the eye tracking for accurate gaze estimation. We demonstrate the accuracy of the proposed eye tracking and gaze estimation system through experiments on some public video sequences as well as videos acquired directly from mobile phone.

Abstract
Contents
List of Figures
List of Tables
Chapter 1. Introduction
1.1. Problem Description and Motivation
1.2. System Overview
1.3. Main Contribution
1.4. Thesis Outline
Chapter 2. Related Work
Chapter 3. Proposed Method
3.1. Eye detection in a single image
3.2. Eye tracking on video
3.3. Eye tracking refinement by orientation sensor
3.4. Eye gazing estimation with 3D display
Chapter 4. Parallelized System on Multi-core Embedded Platform
4.1. Performance on eye detection
4.2. Eye detection with orientation sensor
4.3. Gaze direction estimation
Chapter 5. Conclusion
Reference

[1] Xu, W. and Yang, M. H., "Object tracking via partial least squares analysis," IEEE Transactions on Image Processing, vol. 21, no. 10, 4454-4465 (2012).
[2] Robert, S. and Freund, E., "A decision-theoretic generalization of on-line learning and an application to boosting," Journal of Computer and System Sciences, vol 55, issue 1, 119-139 (1997).
[3] Agustin, J. S., Hansen, J. P., and Mateo, J., "Gaze beats mouse: hands-free selection by combining gaze and EMG," Conference on Human-computer Interaction (2008).
[4] Doshi, A. and Trivedi, M. M., "On the roles of eye gaze and head pose in predicting driver’s intent to change lanes," IEEE Transactions on Intelligent Transportation Systems, vol. 10, no. 3,453-462 (2009).
[5] Langton, S. R., Honeyman, H., and Tessler, E., "The influence of head contour and nose angle on the perception of eye-gaze direction," Perception and Psychophysics, vol. 66, no. 5, 752-771 (2004).
[6] Kim, H. J. and Kim, W. Y., "Eye detection in facial images using Zernike moments with SVM," Electronics and Telecommunications Research Institute Journal, vol.30, no.2, 335-337 (2008).
[7] D’Orazio, T., Leo, M., Cicirelli, G., and Distante, A., "An algorithm for real time eye detection in face images," International Conference on Pattern Recognition (2004).
[8] Kashani, M. A., Arani, M. M., and Ramezanpour, M. R., "Eye detection and tracking in image with complex background," International Conference on Electronics Computer Technology, vol 6, 57-61 (2011).
[9] Valenti, R. and Gevers, T., "Accurate eye center location and tracking using isophote curvature", IEEE Conference on Computer Vision and Pattern Recognition (2008).
[10] Ross, D. A., Lim, J., Lin, R. S., and Yang, M. H., "Incremental learning for robust visual tracking", International Journal of Computer Vision, vol 77, issue 1-3, 125-141 (2008).
[11] Lucas, B. D. and Kanade, T., "An iterative image registration technique with an application to stereo vision," Proceedings of Imaging Understanding Workshop, 121—130 (1981).
[12] Langton, S. R., Honeyman, H., and Tessler, E., "The influence of head contour and nose angle on the perception of eye-gaze direction," Perception and Psychophysics, vol. 66, no. 5,752–771 (2004).
[13] COGAIN, Communication by gaze interaction. Available: http://www.cogain.org
[14] Liu, X., Krahnstoever, N., Yu, T., and Tu, P., "What are customers looking at?," Advanced Video and Signal based Surveillance, 405–410 (2007).
[15] Robertson, N. and Reid, I., "Estimating gaze direction from low-resolution faces in video," European Conference on Computer Vision, 402–415 (2006).
[16] Hu, Y., Chen, L., Zhou, Y., and Zhang, H., "Estimating face pose by facial asymmetry and geometry," IEEE International Conference on Automatic Face and Gesture Recognition, 651–656 (2004).
[17] Ba, S. and Odobez, J., "From camera head pose to 3D global roomhead pose using multiple camera views," International Workshop Classification Events Activities Relationships (2007).
[18] Valenti, R., Sebe, N., and Gevers, T., "Combining Head Pose and Eye Location Information for Gaze Estimation," IEEE Transactions on Image Processing, vol 21, 802- 815 (2012).
[19] Huang, K. and Trivedi, M., "Robust real-time detection, tracking and pose estimation of faces in video streams, " International Conference on Pattern Recognition, 965–968 (2004).
[20] Miluzzo, E., Wang, T., Campbell, A. T., "EyePhone: activating mobile phones with your eyes," ACM SIGCOMM workshop on Networking, 15-20 (2010).
[21] Koenderink, J. and Doorn, A. J., "Surface shape and curvature scales," Image and Vision Computing, vol. 10, no. 8, 557–565 (1992).
[22] Dodgson, A., "Variation and extrema of human interpupillary distance," SPIE(2004).
[23] Wang, J. G., Sung, E., and Venkateswarlu, R., "Eye gaze estimation from a single image of one eye," IEEE International Conference on Computer Vision (2003).
[24] Rosten, E., Porter, R., and Drummond, T., "Faster and better: a machine learning approach to corner detection," IEEE Transactions Pattern Analysis and Machine Intelligence (2010).
[25] Valenti, R. and Gevers, T., "Robustifying eye center localization by head pose cues," IEEE Conference on Computer Vision and Pattern Recognition (2009).
[26] Bradski, G. R., "Computer vision face tracking for use in a perceptual user interface," Intel technology journal, 1-15 (1998).
[27] Scharstein, D. and Pal., C., "Learning conditional random fields for stereo," IEEE Conference on Computer Vision and Pattern Recognition (2007).
[28] Comaniciu, D., "Mean shift:a robust approach toward feature space analysis," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, 603-619 (2002).