本研究目的為發展出自動化的錄製演講系統，利用PTZ攝影機來模擬真實攝影師所錄製的方式，在演講過程中根據不同事件的發生，攝影機做出對應的動作，來拍攝出效果較佳的影像。本系統主要分為前處理、取得演講資訊以及攝影機動作，前處理主要工作分為講者偵測與布幕偵測，取得演講資訊則為講者追蹤與布幕追蹤，取得演講資訊後，系統依照不同的演講情境下對PTZ攝影機下達合適的動作。
在前處理中的布幕偵測部份，由於在演講環境當中，為了使演講者準備的投影片所投影出來的布幕能夠更清晰更明亮，會將現場的燈光調整較暗，我們便藉此環境特性，使用Otsu’s 方法，將布幕在畫面中的區塊取出，再求得布幕座標的資訊。講者偵測部份，則是使用Adaboost之人臉偵測方法來偵測演講者在畫面中臉部的區塊。
在取得演講資訊中，為了在演講過程中，不斷的取得演講者狀態與布幕位置，我們便分別的對布幕與演講者進行追蹤，布幕追蹤方面，由於布幕位置在空間中的位置不會改變，因此可以藉由攝影機變動的參數來預測布幕在下一個時間點畫面中的位置。在講者追蹤方面，我們將講者偵測程序中所偵測出來的講者臉部區塊當作樣版影像，再對下一張的輸入影像進行樣板比對，比對的方式是由平均位移(mean shift)演算法來進行來。
攝影機動作方面，我們根據攝影師建議的規則而訂定的攝影機動作表，在演講過程中，藉由取得演講資訊，得到演講者狀態與布幕位置，系統便會判斷出演講的事件，在依照控制表對PTZ攝影機下達合適的動作，拍攝出理想的畫面。

Lecture recording plays an important role in online learning and interactive distance education. Most of these recordings are achieved by a camera man or a static camera. The former method would be expensive, and the latter would produce a monotonous video. In this paper, we develop an automatic lecture recording system which let a Pan-Tilt-Zoom (PTZ) camera shoot as a camera man. There are three parts developed in our research. The first one is preprocessing for detecting the position of the lecturer and the screen. The second part is to extract the lecture information for controlling the PTZ camera in the third part.

[Bia04] Bianchi, “Automatic video production of lectures using an intelligent and aware environment. ” In Prcceedings of the 3rd International Conference on Mobile and Ubiquitous Multimedia, pp. 117-123

[Cha99] 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.

[Com00] Comaniciu D., Ramesh V., Meer P., ”Real-time tracking of non-rigid objects using mean shift” Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on Volume 2, vol.2 pp:142 - 149 2000

[Com03] Comaniciu D., Ramesh V., Meer P.,”Kernel-based object tracking” IEEE ,Pattern Analysis and Machine Intelligence, vol 25, pp:564 – 577, 2003.

[Fen03] Feng Wang, Chong-Wah Ngo, Ting-Chuen Pong,”Synchronization of lecture videos and electronic slides by video text analysis”, ACM international conference on Multimedia, 2003

[Fle07] Fleming Lampi, Stephan Kopf, Manuel Benz, Wolfgang Effelsberg, ”An automatic cameraman in a lecture recording system” Proceedings of the international workshop on Educational multimedia and multimedia education, ACM, 2007.

[Fuk75] Fukunaga, Keinosuke, Larry D. Hostetler, "The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition". IEEE Transactions on Information Theory (IEEE) 21 (1): 32–40 1975

[Mic04] Michael Bianchi, “Automatic video production of lectures using an intelligent and aware environment” ACM, MUM '04: Proceedings of the 3rd international conference on Mobile and ubiquitous multimedia, 2004

[Oni04] Onishi M., Fukunaga, K., ”Shooting the lecture scene using computer-controlled cameras based on situation understanding and evaluation of video images” ICPR 2004. Proceedings of the 17th International Conference on vo1, pp:781 – 784, 2004.

[Qio01] Qiong Liu, Yong Rui, Anoop Gupta, J. J. Cadiz ,“Automating camera management for lecture room environments” ACM , Proceedings of the SIGCHI conference on Human factors in computing systems 2001.

[Rac07] Rachel Heck, Michael Wallick, Michael Gleicher, ”Virtual videography” ACM ,Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) , vol 3 2007

[Ron03] Ron Baecker,”A principled design for scalable internet visual communications with rich media, interactivity, and structured archives” CASCON '03: Proceedings of the 2003 conference of the Centre for Advanced Studies on Collaborative research, IBM, 2003

[Row01] ROWE, L. A, PLETCHER, P.,HARLEY,D., AND LAWRENCE, S, ”BIBS:Alecture webcasting system.” BMRC 2001.

[Rui01]Rui, Y., He, L., Gupta, A., and Liu, Q. 2001., “Building an intelligent camera management system.” In Proceedings of the ACM Multimedia, 2-11

[Sug99] Sugata Mukhopadhyay, Brian Smith,”Passive capture and structuring of lectures” ACM international conference on Multimedia, 1999

[Vio04] P. Viola and M. J. Jones, "Robust real-time face detection", in International Journal of Computer Vision, Vol. 57, no. 2, pp. 137-154, 2004.

[Wal04] Wallick, M.N., Yong Rui, Liwei He,”A portable solution for automatic lecture room camera management” IEEE International Conference, vol 2, pp:987 – 990. 2004

[Wan03] Wang, F., Ngo, C. W., and Pong, T.C. , “Synchronization of lecture videos and electronic slides by video text analysis.” In Proceedings of the ACM Multimedia, 315-318

[Wei03] Weijin Liu, Yu-Jin Zhang,”Real time object tracking using fused color and edge cues” IEEE , ISSPA,Signal Processing and Its Applications, pp:1-4 , 2007

[Yar03]Yaron Ukrainitz , Bernard Sarel, “http://www.wisdom.weizmann.ac.il/~deniss/vision_spring04/files/mean_shift/mean_shift.ppt”
[Yiz95] Yizong Cheng, “Mean shift, mode seeking, and clustering” Pattern Analysis and Machine Intelligence, IEEE Transactions on Volume 17, Issue 8, Aug. 1995 Page(s):790 - 799

[Yok05] Yokoi, T., Fujiyoshi, H.,”Virtual camerawork for generating lecture video from high resolution images” IEEE International Conference on 2005

[Yon01] Yong Rui, Liwei He, Anoop Gupta, Qiong Liu, “Building an intelligent camera management system” International Multimedia Conference; vol. 9 pp: 2 – 11,2001.

[Yon03] Yong Rui, Anoop Gupta, Jonathan Grudin,”Videography for telepresentations” ACM, Proceedings of the SIGCHI conference on Human factors in computing systems, 2003.

[Yon08] Cha Zhang, Yong Rui, Jim Crawford, Li-Wei He, ” An automated end-to-end lecture capture and broadcasting system” ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) , vol 4, 2008.

[Zha05] Zhang, C., Rui, Y., He, L. Wallick, M, “Hybrid speaker tracking in an automated lecture room” IEEE International Conference, pp.4, 2005.

[簡04] 簡隆至 “即時移動物體偵測及自動追蹤系統”國立台灣科技大學 電機工程學系 國家圖書館 全國博碩士論文資訊網