本論文實作一個以電腦視覺為基礎之眼睛狀態追蹤系統，此系統將追蹤眼睛之狀態(張開與閉上)並且以所追蹤之眼睛的狀態去判定駕駛者是否疲勞。系統一開始是由所取得具有駕駛者臉部之影像進行臉部偵測，利用該影像之YCbCr色彩空間資訊，並設定適當CbCr的膚色範圍以將臉部部分之影像二值化，並以投影的方式來取出影像中之臉部區域，然後從取出之臉部區域再取其上方大約三分之一的區域視為眼睛存在的可能區域。利用Sobel垂直運算子及適當之門檻值已取得此眼睛存在的可能區域之垂直細節的二值影像，之後，用投影的最大值法來得到眼部區域的二值影像，再將此二值影像透過標記連通成分及藉由某些條件得到眼睛的真正位置。接著使用粒子濾波去追蹤連續畫面內之眼睛位置的變動情況，利用事先準備好的閉眼樣板與張眼樣板來評估粒子的權重，經由這些改變權重的粒子來更新目前被追蹤之眼睛的位置，系統中對於眼睛位置之追蹤會與眼睛狀態之偵測同時進行。最後，利用在某段時間之內，眼睛閉合的影格所佔的比例，以判定駕駛者是否屬於疲勞狀態。

In this thesis, a driver fatigue detection system based on tracking driver’s eye states was implemented. The system contains five parts: face detection, eye position detection, eye tracking, recognize eye state and fatigue detection. Firstly, skin color and projection methods are used to get the face area of an image. In eye position detection, the possible location area of eyes on the face area is selected and then the Sobel vertical operator is used to get the edge image of the selected subimage. Again, projection method is used for the edge image to obtain the eye’s position. Particle filtering method, according to the Gaussian distribution is adopted to perform the eyes tracking of the video frames. Two templates, eyes open and eyes closed are used to estimate the weights of the particles and to decide if the eyes are open or closed. Finally, the rate of eye closed frames within a certain period of time can be used to determine whether the driver fatigues or not. For evaluation the proposed system, 9 videos which taken in the day time with varied brightness were tested. It is shown that the system always gives a correct result.

[1] Y. Wang and B. Yuan, "A novel approach for human face detection from color images under complex background," Pattern Recognition, vol. 34, pp. 1983-1992, 2001.
[2] M. A.-m. Rein-Lien Hsu, Anil K. Jain, " Face Detection In Color Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, pp. 696-706, 2002.
[3] D. Chai and A. Bouzerdoum, "A Bayesian Approach to Skin Color Classification in YCbCr Color Space," in TENCON 2000. Proceedings, IEEE, Kuala Lumpur Malaysia. vol. 2, pp. 421-424, 2000.
[4] T. Zhichao and Q. Huabiao, "Real-time driver's eye state detection," in IEEE International Conference on Vehicular Electronics and Safety, pp. 285-289, 2005.
[5] M. J. Paul Viola, "Robust Real-time Object Detection," IEEE ICCV Workshop on Statistical and Computational Theories of Vision, July 2001.
[6] W.-B. Horng and C.-Y. Chen, "A Real-Time Driver Fatigue Detection System Based on Eye Tracking and Dynamic Template Matching," Tamkang Journal of Science and Engineering, vol. 11, pp. 65-72, 2008.
[7] J.-W. Wang and W.-Y. Chen, "Eye detection based on head contour geometry and wavelet subband projection," Optical Engineering, vol. 45, pp. 057001-1-057001-12, 2006.
[8] T. D. Orazio, M. Leo, C. Guaragnella, and A. Distante, "A visual approach for driver inattention detection," Pattern Recognition, vol. 40, pp. 2341-2355, 2007.
[9] Z. Zhiwei and J. Qiang, "Robust real-time eye detection and tracking under variable lighting conditions and various face orientations," Computer Vision and Image Understanding, vol. 98, pp. 124-154, 2005.
[10] J. Qiang, Z. Zhiwei, and P. Lan, "Real-time nonintrusive monitoring and prediction of driver fatigue," IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, vol. 53, pp. 1052-1068, 2004.
[11] J. Xiong, Z. Jiang, J. Liu, and H. Feng, "Multiple states and joint objects particle filter for eye tracking," in Automatic Target Recognition and Image Analysis; and Multispectral Image Acquisition, 2007.
[12] J. Wu and M. M. Trivedi, "Simultaneous eye tracking and blink detection with interactive particle filters," EURASIP Journal on Advance in Signal Process, vol. 2008, pp. 1-17, 2008.
[13] T. Huachun and Y.-J. Zhang, "Detecting eye blink states by tracking iris and eyelids," Pattern Recognition Letters, vol. 27, pp. 667-675, 2006.
[14] L. Hong, W. Yuwen, and Z. Hongbin, "Eye state detection from color facial image sequence," in Second International Conference on Image and Graphics, pp. 693-698, 2002.
[15] X. Cui, Z. Ying, and W. Zengfu, "Efficient eye states detection in real-time for drowsy driving monitoring system," in International Conference on Information and Automation, ICIA.,.pp. 170-174 , 2008
[16] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2nd ed. New Jersey: Prentice Hall, 2002.
[17] Y. Alper, J. Omar, and S. Mubarak, "Object tracking: A survey," ACM Computing Surveys, vol. 38, p. 13, 2006.
[18] M. Isard and A. Blake, "CONDENSATION—Conditional Density Propagation for Visual Tracking," Int. J. Comput. Vision, vol. 29, pp. 5-28, 1998.
[19] K. Nummiaro, E. Koller-Meier, and L. Van Gool, "An adaptive color-based particle filter," Image and Vision Computing, vol. 21, pp. 99-110, 2003.
[20] K. K. Ng and E. J. Delp, "New models for real-time tracking using particle filtering," in Visual Communications and Image Processing, San Jose, CA, USA, pp. 72570B-12,2009.
[21] W. W. Wierwille, S. S. Wreggit, C. L. Kim, L. A. Ellsworth, and a. R. J. Fairbanks, "Research on Vehicle-Based Driver Status/Performance Monitoring; Development, Validation, and Refinement of Algorithms For Detection of Driver Drowsiness," Washington, D. C: National Highway Traffic Safety Administration 1994.