在此文中，我們使用一套單眼PAN-TILT影像伺服系統，發展即時人臉追蹤技術。在此伺服系統中首先人臉偵測，再利用光流演算法，配合控制演算法，使目標樣版可以保持在影像中心。其中在控制演算法上，我們提出一套倒傳遞類神經網路的訓練方法，加入系統中，讓系統做事先的估測，預先知道目標物將來大概的位置，以達到突破以往根據人離中心位置多少，而旋轉PAN-TILT角度的方法，讓此伺服系統更有效率且更強健於追蹤方面。在最後，做一些模糊與類神經控制在影像伺服控制上的實驗，提出結果並且討論。

In this research, a single PAN-TILT image servo system has been developed with real-time face tracing technology. First, the target face is detected, and then the target template is kept at the image center with the integration of optical flow algorithm and control theory. In motion control, back-propagation neural network is taken to predict and estimate the target position. Experiments are made to analyze the performance of the video servo control system.

誌謝 I
摘要 II
Abstract III
目錄 IV
圖索引 VI
表索引 VIII
第一章 緒論 - 1 -
1.1 研究背景 - 1 -
1.2 文獻回顧 - 3 -
1.3 研究動機 - 5 -
1.4 文章架構 - 5 -
第二章 人臉偵測技術 - 6 -
2.1 灰階化 - 6 -
2.2 影像積分 - 8 -
2.3 Adaboost演算法 - 10 -
2.4 cascade演算法 - 14 -
2.5 Lucas-Kanade 演算法 - 15 -
第三章 模糊控制相關理論 - 18 -
3.1 何謂模糊控制 - 18 -
3.2 模糊控制相關基本定義 - 18 -
3.2.1 模糊集合 - 18 -
3.2.2 歸屬函數和歸屬度 - 19 -
3.3 模糊關係 - 20 -
3.3.1 何謂模糊關係 - 20 -
3.3.2 一般常用到的模糊關係 - 20 -
3.4 模糊控制規則 - 21 -
3.5 解模糊化 - 22 -
3.6 模糊控制設計流程 - 24 -
3.7 模糊控制 - 25 -
第四章 倒傳遞類神經網路 - 30 -
4.1 類神經網路簡介 - 30 -
4.2 類神經相關理論 - 32 -
4.2.1 活化函數 - 32 -
4.2.2 學習速率 - 33 -
4.2.3 倒傳遞連結加權值公式之數學推導 - 34 -
4.3 倒傳遞類神經網路 - 36 -
4.3.1 倒傳遞類神經網路簡介 - 36 -
4.3.2 倒傳遞演算法理念 - 37 -
第五章 系統架構 - 41 -
第六章 系統追蹤與實驗結果 - 47 -
6.1系統追蹤流程 - 47 -
6.2 PAN-TILT 平台 - 48 -
6.3 實驗結果 - 49 -
第七章 結論與建議 - 64 -
參考文獻 - 66 -

[1]Arsenioa, A., and Santos-Victor, J., “Robust Visual Tracking by an Active Observer,” IEEE IROS 97, Vol 3, pp.1342-1347, 1997.
[2]Baker, S., Gross, R., Matthews, I., and Ishikawa, T.,
“Lucas-Kanade 20 Years On: A Unifying Framework: Part 2,”
Robotics Institute, Carnegie Mellon University,
CMU-RI-TR-03-01,2003.
[3]Baker, S., and Matthews, I., “Lucas-Kanade 20 Years On: A Unifying Framework,” International Journal of Computer Vision, 53(3), pp.221–255, 2004.
[4]Baumberg, A.M., and Hogg, D.C., “An Efficient Method for Contour Tracking using Active Shape Models,” Motion of Non-Rigid and Articulated Objects,Proceedings of the IEEE
Workshop , pp.194-199, Nov. 1994.
[5]Hager, G.D., and Belhumeur, P.N., “Efficient Region Tracking with Parametric Models of Geometry and Illumination,” Volume 20, Issue 10, pp.1025-1039, 1998.
[6]Horn, B.K.P., and Schunck,Jr.E.J.,“Determining Optical Flow” Artificial Intelligence, Vol 17, pp.185-203, 1981.
[7]Jebara, T.S., Russell, K., and Pentland, A., “Mixtures of Eigen features for Real-time structure from
Texturem,” Proc. Sixth IEEE Int’l conf.computer Vision,pp.128-135,1998.
[8]Jing, X., Baker, S., Matthews, I., and Kanade, T., “Computer Vision and Pattern Recognition,” IEEE CVPR ,Vol. 2, pp.535-542, 2004.
[9]Kjeldsen, R., and Kender, J., “Finding Skin in Color Images,” Proc. Second Int’l Conf. Automatic Face and Gesture Recognition, pp.312-317, 1996.
[10]Kotropoulos, C. and Pitas I., “Rule-Based Face Detection in Frontal Views,” Proc. Int’l Conf.Acoustics,speech and Signal Processing,vol.4, pp.223-243, 1991.
[11]Lanits A., Taylor C.J., and Cootes T.F., “An Automatic Face Identification System Using Flexible Appearance Models,” Image and Vision Computing, vol.13, no.5, pp.393-401, 1995.
[12]Lee,Y.B., You, B.J., and Lee, S.W., “A Real-Time Color-Based Object Tracking Robust to Irregular Illumination Variations,” IEEE ICRA. Vol.2, pp.1659-1664, 2001.
[13]Lerdsudwichai, C., and Abdel-Mottaleb, M., “Algorithm for Multiple Faces Tracking,” Multimedia and Expo, ICME '03, International Conference Vol2, pp.777-780, 2003.
[14]Lienhart, R., Liang, L., and Kuranov, A., “A Detector Tree of Boosted Classifiers for Real-time Object Detection and Tracking,” IEEE ICME 2003, Vol. 2, pp.277-280, 2003.
[15]Lienhart, R., and Jochen, M., “An Extended Set of Haar-like Features for Rapid Object Detection,” IEEE ICIP 2002, Vol. 1, pp. 900-903, 2002.
[16]Li, S.Z., Zhang, Q., Shum, H., and Zhang, H.J., “FloatBoost Learning for Classification,” NIPS, 2002.
[17]Mohan, A., Papageorgiou, C., and Poggio,T., “Example-based Object Detection in Images by Components,” Pattern Analysis and Machine Intelligence, IEEE, Vol.20, pp.39-51, 1998.
[18]Murray, D., and Basu, A., “Motion Tracking with an Active Camera,” IEEE, Pattern Analysis and Machine Intelligence,Vol 16, pp.449-459, 1994.
[19]Rowley, H.A., Baluja, S., and Kanade, T., “Neural Network-Based Face Detection,” IEEE CVPR , pp.203-208, 1996.
[20]Sun,Y.B., Kim, J.T., and Lee, W.H., “Extraction of Face Objects Using Skin Color Information,” Communications, Circuits and Systems and West Sino Expositions, Vol 2, pp.1136-1140, 2002.
[21]Paul V., and Michael, J.J., “Rapid Object Detection Using a Boosted Cascade of Simple Features,” IEEE CVPR ,Vol. 1, NO.2, pp.511-518,2001.
[22]Paul V., and Michael, J.J., “Fast and Robust Classification
using Asymmetric AdaBoost and a Detector Cascade,” NIPS, pp.1311-1318, 2001
[23]Wangand, H.,and Chang, S.F., “AHighly Efficient System for AutomaticFace Region Detection in MPEG Video,” IEEE Trans. Circuits andSystems for Video Technology, vol. 7, no. 4, pp. 615-628, 1997.
[24]Wu,J., Rehg, J.M., Mullin,M.D., “Learning a Rare Event Detection Cascade by Direct Feature Selection,” NIPS, 2003.
[25]Yang, M.H., David, J. K., and Ahuja, N., “Detecting Faces in Images: A Survey,” IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL.24, NO.1,pp.34-58, 2002.
[26]Zhang, Z.Q., Zhu, L., Li, S.Z., and Zhang,H.J.,“Real-time Multi-View Face Detection,”Automatic Face and Gesture Recognition Proceedings. Fifth IEEE International Conference pp.140-147, 2002.
[27]井上洋, 天笠美知夫原著; 陳耀茂, “模糊理論,” 五南圖書公司, 1999.
[28]古國松, 賴炎生, 林俊民, “倒傳遞類神經網路在冰水機節能控制上之應用,” 國立台北科技大學電機工程研究所, 2004.
[29]葉怡成, “應用類神經網路,” 儒林圖書公司, 1997.
[30]閻平凡, 黃端旭, “人工神經網絡模型分析與應用,” 安徽教育出版社, 1993.
[31]謝哲光, 夏郭賢, 朱弘仁, “模糊微分對局簡介,” 全華科技圖書公司, 1993.
[32]謝耀璋, “利用主動式攝影機進行即時人臉追蹤之研究,” 國立中山大學機械與機電工程研究所, 2001.
[33]譚永恆, “以數位影像處裡技術做人臉自動追蹤系統之研究,” 國立成功大學電機工程研究所, 2001.
[34]Woods R.E., Gonzalez R.C.著; 繆紹綱, “數位影像處理,” 普林斯頓國際有限公司, 2002.
[35] Microsoft Visual C++ 6.0 Processor Pack.