近年來，交通意外事故頻繁；九成以上的肇事都是人為因素所導
致。在本論文中，我們提出了一個駕駛昏睡和注意力的監控系統分析駕
駛的精神況狀，其中我們偵測了駕駛的眼睛的開/閉、臉部的方向、與視
線的方向。
本系統主要分成七個部份：主動光源取像設備、眼睛偵測、眼睛追
蹤、臉部偵測、臉部方向估計、視線方向估計、和駕駛注意力判定。為
了可以在不同光源環境下正確的偵測和追蹤駕駛的眼睛，我們使用紅外
線打光取像設備來擷取駕駛的眼睛和臉部影像。之後，我們擷取可能的
眼睛區域並用支援向量機 (Support Vector Machine, SVM) 來偵測所有眼
睛區塊；最後經由一些驗證條件找出一雙眼睛，並且根據眼睛位置找出
臉部範圍。在連續三張影像偵測成功後，進入追蹤模式。在追蹤模式中，
我們使用了三階段的追蹤測試，第一階段在預測的區域內做眼睛偵測；
如果第一階段失敗，則進入第二階段用支援向量機驗證的方式追蹤；如
果第二階段也失敗，則會在我們原先所找到的臉部區域中重新搜尋眼睛。
我們在不同的光源環境下測試我們的系統；例如，夜晚或車內。從
實驗的結果中我們可以看到，我們的系統可以在不同光源環境下正確的
偵測和追蹤駕駛的眼睛位置，並且正確找出臉部範圍。最後可以正確的
分析駕駛的臉部方向、視線方向、和昏睡狀況。

Recently, the issue of driver assistance for safety becomes more
attractive. In this thesis, we propose a computer vision system for monitoring
the driver’s vigilance.
The proposed system consists of seven parts: (1) developing an active
image acquisition equipment, (2) eye detection, (3) eye tracking, (4) face
detection , (5) face orientation estimation, (6) gaze estimation, (7) vigilance
decision.
In order to deal with various ambient light conditions, we utilize an IR
camera equipped with an active IR illuminator to extract several visual cues
such as close/open, eyelid movement, gaze direction, and face direction. A
probabilistic model is developed to measure human fatigue and to determine
fatigue based on the visual cues. At first, we get face images in the same
background and illumination by utilizing Iterative thresholding to find out the
location of brighter pixels. Second, we can obtain the positions of the eyes by
the Connected-component generation. According to the location of the pupil,
we can clip the eye region to be verified by the SVM (support vector machine)
method. then if there are a fixed numbers of image frames succeeded in
detection mode, we can turn the procedure to tracking mode.
In the experiments, the proposed approaches are evaluated by several
different light conditions such at day and night. From the experiment results,
we find that the proposed approach can stably detect or track the eyes in real
time.

[1] Bae, H. and S. Kim, “Real-time face detection and recognition using
hybrid-information extracted from face space and facial features,” Image
and Vision Computing, vol.23, pp.1181-1191, 2005.
[2] Berbar, M. A., H. M. Kelash, and A. A. Kandeel, “Faces and facial
features detection in color images,” in Proc. of the Geometric Modeling
and Imaging, 2006, pp.209-214.
[3] Chang, K.-S., A Driver Drowsiness Detection Based on An Active IR
illumination, Master thesis, Computer Science and Information
Engineering Dept., National Central Univ., Chung-Li, Taiwan, 2005.
[4] Chen, Y.-R., Computer Vision-based Eye Detection and Warning System
for Driver Fatigue, Master thesis, Civil Engineering Dept., National
Taiwan Univ., Taipei, Taiwan, 2005.
[5] Cristinacce, D. and T. Cootes, "Facial feature detection using adaboost
with shape constraint," in Proc. 14th Conf. Machine Vision, British, 2003,
pp. 231-240.
[6] Garcia, C. and G. Tziritas, “Face detection using quantized skin color
regions merging and wavelet packet analysis,” IEEE Trans. on
Multimedia, vol.1, no.3, pp.264-177, 1999.
[7] Hong, K.-D., A Real-time Face and Feature Location System, Master
thesis, Computer Science Dept., National Chung Hsing University,
Taichung, Taiwan, 2006.
[8] Hong, S.-X., Hazardous Driver Behavior Analysis Using Pupil Detection
and Fatigue Variation, Master thesis, Computer Science and Information
Engineering Dept., National Central Univ., Chung-Li, Taiwan, 2005.
[9] Horng, W.-B., C.-Y. Chen, Y. Chang, and C.-H. Fan, “Driver fatigue
detection based on eye tracking and dynamic template matching,” in Proc.
Int. Conf. on Networking, Sensing & Control, Taipei, Taiwan, Mar. 21-23,2004, pp.7-12.
[10] Hsiung, C.-Y., An Attention Detection System for Vehicles, Master thesis,
Computer Science and Information Engineering Dept., National Central
Univ., Chung-Li, Taiwan, 2005.
[11] Ji, Qiang, “3D face pose estimation and tracking from a monocular
camera,” Image and Vision Computing, vol.20, pp.499-511, 2002.
[12] Kawato, S. and J. Ohya, “Two-step approach for real-time eye tracking
with a new filtering technique,” in proc. IEEE Int. Conf. on System, Man
& Cybernetics, Tennessee, Oct.8-11, 2000, pp.1366-1371.
[13] Kawato, S. and N. Tetsutani, "Circle frequency filter and its
application," in Proc. Int. Conf. Workshop on Advanced Image
Technology, Taejon, Korea, Feb.8-9, 2001, pp.217-222.
[14] Kawato, S. and N. Tetsutani, “Real-time detection of between-the-eyes
with a circle frequency filter,” in Proc. 5th Asian Conf. on Computer
Vision, Melbourne, Australia, Jan.23-25, 2002.
[15] Lee, T., S.-K. Park, and M. Park, “An effective method for detecting
facial features and face in human robot interaction,” Information
Sciences, pp3166-3189, 2005.
[16] Li, Y., X.-L. Qi, and Y.-J. Wang, “Eye detection by using fuzzy template
matching and feature-parameter-based judgement,” Pattern Recognition
Letters, vol.22, iss.10, pp.1111-1124, 2001.
[17] Lin, C.-H., Face Detection, Pose Classification, and Face Recognition
Based on Triangle Geometry and Color Features, Ph.D. dissertation,
Computer Science and Information Engineering Dept., National Central
Univ., Chung-Li, Taiwan, 2001.
[18] Lo, C.-H., An Intelligent Face Detection System for Video Retrieval,
Master thesis, Computer Science and Engineering Dept., Yuan Ze Univ.,
Chungli, Taiwan, 2006.
[19] Orazio, D., T. Leo, M. Cicirelli, G. Distante, and A. Distante, “Analgorithm for real time eye detection in face images,” in Proc. 17th Int.
Conf. on Pattern Recognition, Cambridge, UK, Aug.23-26, 2004,
pp.278-281.
[20] Siana, L., A Study of Human Tracking and Face Detection on A
Pan-Tilt-Zoom Camera,” Master thesis, Elect. and Control Eng. Dept.,
National Chiao Tung Univ., Hsinchu, Taiwan, 2005.
[21] Tan, Y.-H., A Human Face Tracker System Design Study Using the
Technology of Digital Image Processing, Master thesis, Elect. Eng.
Dept., National Cheng-Kung Univ., Tainan, Taiwan, 2000.
[22] Tsao, Y.-C., Measurement of Face Recognizability for Visual
Surveillance, Master thesis, Computer Science and Information
Engineering Dept., National Chiao Tung Univ., Hsinchu, Taiwan, 2004.
[23] Vapnik, V., The Nature of Statistical Learning Theory, Springer-Verlag,
1995.
[24] Wang, S.-W., Automatic Eye Detection and Glasses Removal, Master
thesis, Elect. and Control Eng. Dept., National Chiao Tung Univ.,
Hsinchu, Taiwan, 2004.
[25] Wang, T. and P. Shi, “Yawing detection for determining driver
drowsiness,” in Proc. IEEE Int. Workshop VLSI Design & Video Tech.,
Suzhou, China, May 28-30, 2005,pp.373-376.
[26] Yan, S., C. Liu, S. Z. Li, H. Zhang, and H. Yeung, "Face alignment
using texture-constrained active shape models," Image and Vision
Computing, vol.12, pp.69-75, 2002.
[27] Zheng, Z., J. Yang, and L. Yang, “A robust method for eye features
extraction on color image,” Pattern Recognition Letters, vol.26,
pp.2252-2261, 2005.