臺灣博碩士論文加值系統

在本篇論文中我們建造了一個監測汽車駕駛員的視線及是否打瞌睡的自動安全監視系統。這個系統的主要技術包括追蹤汽車駕駛者的眼睛位置和辨識駕駛者的視線及打瞌睡是否。為了追蹤駕駛者的眼睛位置，我們的系統首先從灰階的攝影機影像中利用一個圓形頻率濾波器 (circle-frequency filter) 找出between-eyes (所謂的between-eyes指的是雙眼中心連線的中點)，然後根據找出來的 between-eyes 本系統可利用中間穿越函數 (mean crossing function) 及中央權重函數 (central weighting function) 的特點，準確的找到 between-eyes 兩邊的眼睛。為了進行視線及打瞌睡與否的分析，將眼睛切割出來是一個重要的步驟，本系統利用蘇珊濾波器 (SUSAN filter) 找出眼睛的輪廓並從圖片中擷取出來。當左右兩隻眼睛從圖片中分割出來後，本系統使用了多層感知類神經網路 (multi-layer perceptron neural network簡稱MLP) 來作為分析駕駛員視線方向的分類器。最後，利用分割出來的眼睛影像及MLP的輸出，我們推導出一些規則來監測駕駛員視線及打瞌睡與否。根據我們實驗的結果，本系統在運用了這些規則後達到了幾乎完美的正確率。

In this thesis, we build an automatic surveillance system to monitor the gaze and dozing of car drivers. In this system, the key technologies include mainly the tracking of driver’s eyes and the recognition of driver’s gaze and dozing. To track the eyes, our system finds the “between-eyes” by applying a circle-frequency filter on the gray-level video frames first. According to the found between-eyes, the system can accurately searches the eyes on both sides of the between-eyes by using the features defined by mean crossing function and central weighting function. In order to segment the eye images for gaze and dozing analyses, the contours of eyes are extracted by using a SUSAN filter. With the segmented images of left and right eyes, the system employs a multi-layer perceptron (MLP) neural network as a classifier for driver’s different orientations of gazes. Finally, with the segmented eye images and the output of the MLP monitor, we derive some rules for monitoring the driver’s gaze and dozing. According to our experiments, the system achieves almost perfect accuracy after applying the derived rules.

致謝（Acknowledgement）ii
中文摘要（Chinese Abstract）1
Abstract2
Table of Contents3
List of Figures4
List of Tables5
1Introduction6
1.1Research Motivation6
1.2Related Works6
1.3Goal of the Research8
2The Proposed Algorithm10
2.1Facial Features Extraction12
2.1.1Between-Eyes Extraction12
2.1.2Eyes Extraction13
2.1.3Eyes Boundary Extraction16
2.2Detection Mode and Tracking Mode18
2.3Gaze Estimation19
2.4Attention Analysis22
3Experimental Results23
3.1Training Data Collection23
3.2Results25
3.2.1Testing with One User25
3.2.2Testing with Multiple Users28
4Concluding Remarks30
References31

[1]R.L. Hsu, M. Abdel-Mottaleb, and A.K. Jain, “Face Detection in Color Images”, Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol.24, Issue.5, May 2002.
[2]V. Vezhnevets, “Face and Facial Feature Tracking for Natural Human-Computer Interface”, Graphics & Media Laboratory, 2002, Dept. of Applied Mathematics and Computer Science of Moscow State University Moscow, Russia.
[3]P. Smith, M. Shah, and N. da Vitoria Lobo, “Monitoring Head/Eye Motion for Driver Alertness with One Camera”, Pattern Recognition, 2000. Proceedings, 15th International Conference on, Vol.4, 3-7 Sept,2000.
[4]M. Rizon and T. Kawaguchi, “Automatic Eye Detection Using Intensity and Edge Information”, TENCON 2000, Proceedings, Vol.2, 24-27 Sept,2000.
[5]C.H. Lin and J.L. Wu, “Automatic Facial Feature Extraction by Genetic Algorithms”, Image Processing, IEEE Transactions on, Vol.8, Issue.6, June 1999.
[6]S. Kawato and J. Ohya, “Two-step Approach for Real-time Eye Tracking with a New Filtering Technique”, 2000 IEEE, ATR Media Integration and Communications Research Laboratories.
[7]S. Kawato and J. Ohya, “Real-time Detection of Nodding and Head-shaking by Directly Detecting and Tracking ‘Between-Eyes’”, Automatic Face and Gesture Recognition, 2000. Proceedings. Fourth IEEE International Conference on. 28-30 March 2000.
[8]J.G. Wang and E. Sung, “Study on Eye Gaze Estimation”, Systems, Man and Cybernetics, Part B, IEEE Transactions on, Vol.32, Issue.3, June 2002.
[9]S. Esaki, Y. Ebisawa, A. Sugioka and M. Konishi, “Quick Menu Selection Using Eye Blink for Eye-slaved Nonverbal Communicator with Video-based Eye-gaze Detection”, Engineering in Medicine and Biology society,1997. Proceedings of the 19th Annual International Conference of the IEEE, Vol.5, 30 Oct. - 2 Nov. 1997.
[10]T. Miyake, S. Haruta, and S. Horihata, “Image Based Eye-Gaze Estimation Irrespective of Head Direction”, Industrial Electronics, 2002. ISIE 2002. Proceedings of the 2002 IEEE International Symposium on, Vol.1, 8-11 July 2002.
[11]J. Zhu, J. Yang, “Subpixel Eye Gaze Tracking”, Automatic Face and Gesture Recognition, 2002. Proceedings of the Fifth IEEE International Conference on, 20-21 May 2002.
[12]Y. Ebisawa, “Improved Video-Based Eye-Gaze Detection Method”, Instrumentation and Measurement, IEEE Transactions on, Vol.47, Issue.4, Aug 1998.
[13]L.Q. Xu, D. Machin, P. Sheppard, “A Novel Approach to Real-time Non-intrusive Gaze Finding”, British Machine Vision Conference.
[14]S. Baluja, D. Pomerleau, “Non-Intrusive Gaze Tracking Using Artificial neural Networks”, Advances in Neural Information Processing Systems (NIPS) 6. Cowan J.D., Tesauro, G. & Alspector, J. (eds.) Morgan Kaufmann Publishers, San Francisco, CA., 1994.
[15]S.M. Smith, J.M. Brady, “SUSAN — A New Approach to Low Level Image Processing”, Defence Research Agency Technical Report TR95SMS1b, 1995.
[16]Richard O. Duda, Peter E. Hart, David G. Stork, “Pattern Classification Second Edition”, Chapter 3.8.1.