結論與未來展望 - 適用於可見光環境之高速眼動儀系統設計

6. 1 結論

本文開發的可見光眼動儀能夠在不外加光源的情況下，透過影像處理技術達到 240 fps 的眼球追蹤，其平均誤差為 1.05^o，已經能夠媲美一般業餘研究的紅外光眼動儀所計算的準確度。雖然現有的眼動儀相關論文不下其數，[28][29]所提出的方法達到約 4^o的錯誤率，[27][30][31]所提出的方法達到約莫 1^o的錯誤率，[32]

提出的系統能夠在 IR 光源下，達到 407fps，但也使用相當長的 FIR 濾波器，以濾除因取樣率提升的雜訊干擾，[23]提出 3-D 眼球追蹤系統，並達到 0.5^o的錯誤率，其使用 200fps 的感測器，但將每秒取得的大量資料做平均，以 30fps 輸出，

表示其系統的靈敏度過高，易受到雜訊的影響，上述的成果都是以紅外線光源為主，直到 2011 年的期刊論文[18]，才提出可見光下的眼球追蹤系統，表 6-1 比較在 2007 年提出的一款紅外線眼動儀系統[14]，其系統架構與本文提出的較類似，

但使用紅外線光源，與 2011 年的期刊論文[18]，表 6-1 中可以發現紅外光眼動儀的穩定度較高，不同使用者在穩定度上的差異變化，在水平方向的變化為±0.19^o，垂直方向的變化為±0.22^o，而[18]與本文提出的系統在可見光環境下，於水平與垂直方向的穩定度變化分別為±0.37^o、±0.67^o 與±0.36^o、±0.72^o。比較後可以發現眼動儀系統在紅外光源下的穩定度較高，因為紅外光對環境光源的抵抗力非常高。

而本文提出的系統在垂直方向的錯誤率略高於[18]所提出的方法，最大的原因在於解析度的不同，[18]的影像解析度為 752×582，而本文的系統在 240fps 的取樣率下，影像的解析度為 432×320，而最後有用的影像大小約為 200×90，因此在垂直方向的錯誤率略高。

表 6-1 相關眼動儀系統比較

水平方向平均誤差垂直方向平均誤差

再者[18]的取樣率為 25fps，而本文提出的眼動儀系統，能夠在 240fps 的取樣率下，每張畫面都輸出座標點，達到平均水平方向 0.76^o與垂直方向 1.43^o的準確

2007 [14] 2011 [18] Proposed

Error (degree)

Horizontal

2007 [14] 2011 [18] Proposed

Error (degree)

Vertical

參考文獻

[1]. SMI (SensoMotoric Instruments). [Online] Available at:

http://www.smivision.com

[2]. Tobii. [Online] Availabe at: http://www.tobii.com

[3]. Eye Tracking. [Online] Available at http://en.wikipedia.org/wiki/Eye_tracking [4]. E. B. Huey, “Preliminary experiments in the physiology and psychology of

reading,” American Journal of Psychology, vol. 9, no. 4, pp. 575-586, Jul. 1897 [5]. R. Dodge and S. T. Cline, “The angle velocity of eye movements,”

Psychological Review, vol. 8, no. 2, pp. 145-157, Mar. 1901

[6]. M. A. Just and A. P. Carpenter, “A theory of reading: from eye fixation to comprehension,” Psychological Review, vol. 87, no. 4, pp. 329-354, Jul. 1980 [7]. I. M. Posner, “Orienting of attention,” Quarterly Journal of Experimental

Psychology, vol. 32, no. 1, pp. 3-25, May 1980

[8]. Z. Zhu and Q. Ji, “Eye and gaze tracking for interactive graphic display,”

Machine Vision and Applications, vol. 15, no. 3, pp. 139-148, Jun. 2004

[9]. T.E. Hutchinson, K. P. White Jr., K. C. Reichert, and L. A. Frey,

“Human-computer interaction using eye-gaze input,” IEEE Trans. on System,

Man, and Cybernetics, vol. 19, no. 6, pp. 1527-1533, Aug. 1989

[10]. Y. Ebisawa, M. Ohtani, and A. Sugioka, “Proposal of a zoom and focus control method using an ultrasonic distance-meter for video-based eye-gaze detection under free-hand condition,” in Proc. of the 18th Annual Int. Conf. of the IEEE

Eng. in Medicine and Biology Society, 1996

[11]. C. H. Morimoto, D. Koons, A. Amir, and M. Flickner, “Frame-rate pupil detector and gaze tracker,” IEEE ICCV’99 Frame-rate Workshop, 1999

[12]. Yoshinobu Ebisawa, “Improved video-based eye-gaze detection method,” IEEE

Trans. on Instrumentation and Measurement, vol. 47, no. 4, Aug. 1998

[13]. Craig Hennessey and Peter Lawrence, “Fixation precision in high-speed noncontact eye-gaze tracking,” IEEE Trans. on System, Man, and Cyberneics –

Part B : Cybernetics, vol. 38, no. 2, pp. 289-298, Apr. 2008

[14]. Z. Zhu and Q. Ji, “Novel eye gaze tracking techniques under natural head movement,” IEEE Trans. on Biomedical Engineering, vol. 54, no. 12, pp.

2246-2260, Dec. 2007

[15]. Craig Hennessey and Peter Lawrence, “Noncontact binocular eye-gaze tracking for point- of gaze estimation in three dimensions,” IEEE Trans. on Biomedical

Engineering, vol. 56, no. 3, pp. 790-799, Mar. 2009

[16]. Yung-Lung Kuo, Jiann-Shu Lee and Sho-Tsung Kao, “Eye tracking in visible environment,” IEEE Int. Conf. on Intelligent Information Hiding and

Multimedia Signal Processing, Kyoto, Japan, Sep. 2009, pp. 114-117

[17]. Nyguyen Huu Cuong and Huynh Thai Hoang, “Eye-gaze detection with a single webcam based on geometry features extraction,” IEEE Int. Conf. on Control,

Automation, Robotics and Vision, Singapore, Dec. 2010, pp. 2507-2512

[18]. Jose Sigut and Sid-Ahmed Sidha, “Iris center corneal reflection method for gaze tracking using visible light,” IEEE Trans. on Biomedical Engineering, vol. 58, no. 2, pp. 411-419, Feb. 2011

[19]. M. Sanjeev Arulampalam, Simon Maskell, Neil Gordon, and Tim Clapp, “A tutorial on particle filters for online nonlinear/non-gaussian bayesian tracking,”

IEEE Trans. on Signal Processing, vol. 50. no. 2, pp. 174-188, Feb. 2002

[20]. N. Maillot, M. Thonnat and C. Hudelot, “Ontology based object learning and recognition: application to image retrieval,” in Proc. IEEE Int. Conf. on Tools

with Artificial Intelligence, Boca Raton, Florida, US, Nov. 2004, pp.620- 625

[21]. C. Harris and M. Stephens, “A combined corner and edge detector,” in Proc. of

the 4th Alvey Vision Conference,1988, pp. 147-151.

[22]. G. Derpanis, “The Harris corner detector,” York University, Oct. 2004.

[23]. P.Viola and M. J. Jones, “Robust real-time face detection,” Int. J. Comput. Vis., vol. 57, no. 2, pp. 137–154, May 2004.

[24]. J. Canny, “A computational approach to edge detection,” IEEE Trans. on

Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679-698,

Jan. 1986

[25]. Martin A. Fischler and Robert C. Bolles, “Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,” Commun. Ass. Comput. Mach., vol. 24, no. 6, pp. 381-395, Jun.

1981

[26]. D. A. Forsyth and J. Ponce, Computer Vision A Modern Approach, Prentice Hall, 2002

[27]. K. P. White, Jr., T. E. Hutchinson, and J. M. Carley, “Spatially dynamic calibration of an eye-tracking system,” IEEE Trans. Syst., Man, Cybern., vol. 23, no. 4, pp. 1162–1168, Jul./Aug. 1993.

[28]. K. H. Tan, D. J. Kriegman, and N. Ahuja, “Appearance-based eye gaze estimation,” in Proc. IEEE Workshop on Appl. Comput. Vis., Orlando, Florida, US, Dec. 2002, pp. 191–195

[29]. D. Beymer and M. Flickner, “Eye gaze tracking using an active stereo head,” in

Proc. Int. Conf. Comput. Vis. Pattern Recognit., Madison, Wisconsin, US, Jun.

2003, pp. 451–458.

[30]. C. H. Morimoto, D. Koons, A. Amir, and M. Flickner, “Pupil detection and tracking using multiple light sources,” Image Vis. Comput., vol. 18, no. 4, pp.

331–336, Mar. 2000.

[31]. Z. W. Zhu and Q. Ji, “Eye and gaze tracking for interactive graphic display,”

Mach. Vis. Appl., vol. 15, no. 3, pp. 139–148, Feb. 2004.

[32]. C. Hennessey, B. Norueddin and P. Lawrence. “Fixation precision in high-speed noncontact eye-gaze tracking,” IEEE Trans. on System, Man, and Cyberneics –

Part B : Cybernetics, vol. 38, no. 2, no. 289-298, Apr. 2008

[33]. D. Li, D. Windield, and D. J. Parkhurst, “Starburst: a hybrid algorithm for video-based eye tracking combining feature-based and model-based approaches,” IEEE Computer Society Conf. on Computer Vision and Pattern

Recognition (CVPRW’05) Workshops, San Diego, CA, US, Jun. 2005, pp. 79

[34]. F. Durand and J. Dorsey. “Fast bilateral filtering for the display of

high-dynamic-range images,” ACM Trans. on Graphics, vol. 21, no. 3, pp.

257-266, Jul. 2002.

[35]. Raanan Fattal, Dani Lischinski and Michael Werman, “Gradient domain high dynamic range compression,” ACM Trans. on Graphics, vol. 21, no. 3, pp.

249-256, Jul. 2002

[36]. Erik Reinhard and Kate Devlin, “Dynamic range reduction inspired by photoreceptor physiology,” IEEE Trans. on Visualization and Computer

Graphics, vol. 11, no. 1, pp. 13-24, Feb. 2005

[37]. P. E. Debevec, J. Malik, “Recovering high dynamic range radiance maps from photographs,” in Proc. ACM SIGGRAPH Int. Conf. and Exhibition on

Computer Graphics and Interactive Techniques, Los Angeles, California, USA,

Aug. 1997 pp. 369-378.

[38]. Wen-Chung Kao, Xiang-Ting Huang, Hung-Chun Wang, Chih-Chen Pan, and Feng-Che Yang, “Real-time tone reproduction for video recording, ” in Proc.

IEEE Int. Symp. on Consumer Electronics (ISCE), Harrisburg, US, Jun. 2012.

pp. 1-2

[39]. R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2^nd

edition, New

Jersey, Prentice Hall, 2002

[40]. E. Reinhard, “Parameter estimation for photographic tone reproduction,”

Journal of Graphics Tools, vol. 7, no. 1, pp. 45-52, Nov. 2002.

[41]. E. Reinhard, M. Stark, P. Shirley, and J. Ferwerda, “Photographic tone reproduction for digital images,” ACM Trans. on Graphics, vol. 21, no. 3, pp.

267-276, Jul. 2002

[42]. K. Sobottka and I. Pitas, “A novel method for automatic face segmentation, facial feature extraction and tracking,” Signal Processing: Image Comm., vol.

12, no. 3, pp. 263-281, Jun. 1998

[43]. D. Chai and K. N. Ngan, “Face segmentation using skin color map in videophone applications,” IEEE Trans. on Circuits and Systems for Video

Technology, vol. 9, no. 4, pp. 551-564, Jun. 1999

[44]. H. Li and R. Forchheimer, “Location of face using color cues,” in Proc. Picture

Coding Symp., Lausanne, Switzerland, Mar. 1993, paper 2.4

[45]. Y. J. Wang and B. Z. Yuan, “A novel approach for human face detection from color images under complex background,” Pattern Recognition, vol. 34, no. 10, pp. 1983-1992, Jun. 2001

[46]. S. L. Phung, A. Bouzerdoum, and D. Chai “Skin segmentation using color pixel classification: analysis and comparison,” IEEE Trans. on Pattern Analysis and

Machine Intelligence, vol. 27, no. 1, Jan. 2005

[47]. R. L. Hsu, M. Abdel-Mottaleb, and Anil K. Jain, “Face detection in color images,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 24, no.

5, pp. 696-706, May 2002

[48]. C. J. Lin, “A formal analysis of stopping criteria of decomposition methods for support vector machines,” IEEE Trans. on Neural Networks, vol. 13, no. 5, pp.

1045-1052, Mar. 2002

[49]. R. Gonzalez and R. Woods, Digital Image Processing, Addison Wesley, 1992, pp. 414 - 428.

[50]. W. Gander, G.H. Golub, and R. Strebel, “Least-squares fitting of circles and ellipses” BIT Numerical Mathematics, vol. 34, no. 4, pp. 558-578, Dec. 1994 [51]. V.F. Leavers, “Shape detection in computer vision using the hough transform,”

Springer-Verlag, 1992

[52]. K. P. White, Jr., T. E. Hutchinson, and J. M. Carley, “Spatially dynamic calibration of an eye-tracking system,” IEEE Trans. Syst., Man, Cybern., vol. 23, no. 4, pp. 1162–1168, Jul./Aug. 1993.

[53]. Z. R. Cherif, A. Naït-Ali, J F. Motsch, and M. O. Krebs, “An adaptive calibration of an infrared light device used for gaze tracking,” in Proc. IEEE

Instrum. Meas. Tech. Conf., Anchorage, Alaska, US, May 2002, vol. 2, pp.

1029–1033

[54]. N. Ramanauskas, “Calibration of video-oculographical eye-tracking system,”

Electron. Electr. Eng., vol. 8, no. 72, pp. 65-68, May 2006

[55]. L. N. Trefethen and D. Bau III, Numerical Linear Algebra, Philadelphia:

Society for Industrial and Applied Mathematics [56]. Casio ZR-100. [Online]. Available at:

http://www.casio-intl.com/asia/zh/dc/lineup/

[57]. OpenCV Computer Vision Library (2013). [Online]. Available at:

http://opencv.willowgarage. com/wiki

[58]. Freund, Yoav, Schapire, Robert E. “A decision-theoretic generalization of on-line learning and an application to boosting,” in Proc. of the Second

European Conference on Computational Computational Learning Theory,

Barcelona, Spain, Mar. 1995, vol. 904, pp. 23-37

[59]. SR Research. [Online] Available at: http://www.sr-research.com

自傳

【自我簡介】

我是張維德，自評為認真負責、待人誠懇、願意接受挑戰與付出的人，大學專題期間，曾有過多次的產學合作經驗，讓我體會到業界做事的效率，以及團隊合作的重要性，我自知不是天資聰穎的人，但就像古人所說勤能補拙，我願意付出加倍的努力來補足自己的不足，加上與團隊一起奮鬥合作，因此能夠順利完成專案，並在大學期間就有豐碩的成果，獲得報章媒體的青睞，將這些成果發表於 IEEE 國際知名期刊。

碩士班求學期間，便於碩一上學期，再一次將更具創意的研究成果投稿於 IEEE 國際會議，更同時帶領 2 名學弟，參加 2011 Altera 亞洲創新大賽，並獲得銅牌的殊榮(全國競賽)，並前往大陸重慶展示，並有機會參加 2012 IEEE ICCE 會議，發表我的研究成果，由於有國外發表的經驗，更讓我深刻體會到我們所面對的是來自世界各地的競爭者，同時也發現自己能力的不足，因此讓我更從中體會到傾聽、包容、團隊合作以及謙虛的道理。

即將邁入職場的我，聽從指導教授的建議，嘗試帶領學弟，一同建構較大型的系統專案，學習如何維護系統、如何適當的分配工作、如何與人溝通，培養我負責與團隊合作的能力，希望我能夠在邁入職場前的黃金半年，能夠成為一名懂得溝通、善於解決問題、思考更為周全成熟，能夠直接進入職場的一名戰士，而不是尚待訓練的實習生。

註 : 大學期間發表 1 篇期刊論文，碩士班期間共計發表 2 篇會議論文，2 篇期刊論文。

【家庭背景】

維德成長於一普通家庭，為家中長子，有一就讀高中的妹妹，父親為公務員，

母親為技術專員，由於父母皆由外地上台北求職，深感台北求職之競爭壓力，故非常重視小孩的學習狀況，並以身作則，父親從小便陪在身邊督促我讀書，更於小學讓我上英文補習班增進英文聽說讀寫能力，在這樣的生活環境下，使我在求學的起跑點上略勝同儕一籌，並從小培養閱讀習慣。

【求學過程】

在學習方面，課堂上遇到困難之處，我會主動向老師發問，作業遇到瓶頸，

也會與同學討論努力試著找出答案，不輕易放棄，正因如此，我與各求學階段的老師、同學保有良好關係。閒暇之餘，我會利用時間上網自主學習，對感興趣的議題會上圖書館找資料。自從進入研究所，讓我體會到時間分配的重要性，大小瑣事不少，幾乎一週有六天在實驗室，平常的時間多半在處理雜事與跟同儕討論問題，六日處理自己的研究與讀書，看似好像過得很辛苦，但我不這麼認為，周末的實驗室雖然空蕩蕩的，但環境很好，陽光照進實驗室，配上一杯熱咖啡，便是我六日工作的寫照，這樣的環境下，沒有其他人的打擾，能夠盡情地做實驗，

寫程式，感覺也相當不錯。

大學的求學的過程中，奠定我踏入電機工程領域的基礎，除了大學必修課程外，也建立良好的程式語言基礎，包括 C/C++語言、JAVA、MATLAB，熟悉單晶片與微處理機的設計，相關課程的完整性使我在電機領域深具信心。碩士期間參與多項國科會計畫與產學合作計畫，讓我了解與業界合作，需要精確掌握產品時程與回報進度，開發文件的撰寫與技術報告，看似瑣碎卻是缺一不可。

我很榮幸有機會參加 2011 年 Altera 亞洲創新設計大賽並獲得銅牌，並前往大陸發表，過程中，我看到大陸學生對專業知識的渴望與積極的求知態度；2012

年 1 月，前往美國拉斯維加斯參加 IEEE ICCE 並發表論文，我看到來至世界各地學生的研究發表，這些經驗讓我非常興奮，我看到其他國家的學生也積極地從事研究，讓我感到並不孤單，更讓我相信踏上電子產業的道路是對的，因為全球有許許多多的人都在追求進步，不斷的創新，將自己的想法付諸實現，獲得肯定。

【自我期許與目標】

因為有機會前往國外參加國際型會議，讓我更清楚知道未來競爭對手的實力是不容小覷的，也發現消費性電子產品為所有電子產品的大宗，放眼望去，我覺得電子系統整合將會是未來的趨勢，因此我在碩士班的最後一年，著手進行新的研究，也就是我的論文題目：適用於可見光環境下的高速眼球追蹤系統，從模組開發、程式撰寫、數據分析與程式整合並請學弟設計使用者介面，共同完成這個系統，在開發系統的過程中也讓我對色彩學與影像處理的了解更加孰悉，最後於

在文檔中適用於可見光環境之高速眼動儀系統設計 (頁 89-101)