非即時自動導播技術研究

A Research of Off-line Automatic Virtual Director for Lecture Video

黃帝維(Di-Wei Huang)

指導教授 ： 李忠謀

國立臺灣師範大學/理學院/資訊工程研究所/碩士(2010年)

摘要

隨著科技的進步、網路頻寬的快速提升，以網路為基礎的網路教學、會議影片的傳輸及其應用越來越受企業界、學術界的重視。雖然目前有許多系統能夠線上觀看會議及上課的影片、投影片，但往往內容是無趣的。因此如何呈現給觀眾想看的內容，播放的內容是有意義、有趣的，能讓觀眾看重要的影片內容顯得相當重要。目前有不少自動化上課錄影系統，但很少提到能夠選擇適合的內容給觀眾看的方法。本篇提出的方法，在偵測事件發生後，能搭配有限狀態機的序列，選擇何時該播放哪一台攝影機的內容給使用者觀看並給使用者重點提示。
在實作方面，我們對影片的內容做分析，在影像部分，分析了講者的行為及布幕的事件偵測，聲音部分分析音源方向。接著，評估各事件的重要程度及發生順序，搭配有限狀態機產生的狀態序列選擇播放哪台攝影機的內容，另一方面，在適當的時間加入合適的圖示來提示觀看者可能有重點。
在實驗結果中顯示我們攝影機切換的時間點、切換到哪一台，都有不錯的效果，能夠讓教學影片內容更有趣、更有意義。

關鍵字

教學影片編輯 ； 教學影片產生 ； 教學影片內容分析 ； 虛擬導演

並列摘要

As technology advances and rapid upgrading network bandwidth, business and the academic attract attention by conference video transmission and internet-based online education video. Although there are many systems could watch online conferences or course video, the content maybe boring. How to present contents to audience what they want. Let audience see meaningful and interesting video is very important.
In practical implementation, we analyze the contents of video, the image part, analyze the behavior of speakers and the curtain of event detection, analysis of the voice part of the sound source. Then evaluate the importance of the event and the order, use finite state machines generated sequence of states choose the play contents of which camera. On the other hand, add visual hints at the appropriate time to prompt the viewer may be focused.
The experimental results show that our camera switching time, switch to which one had good results. Let teaching video content more interesting and more meaningful.

並列關鍵字

Lecture video ； video composition ； lecture video content analysis ； virtual director

參考文獻

[2] C. Zhang, Y. Rui, J. Crawford, and L. W. He , “An Automated End-to-End Lecture Capture and Broadcasting System”, ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 4, no. 2, pp.601-623, Jan. 2008.

[5] M. Bianchi, “Automatic Video Production of Lectures Using an Intelligent and Aware Environment”, Proceedings of the 3rd international conference on Mobile and ubiquitous multimedia, College Park, Maryland U.S.A, pp.117-123, 2004.

[7] J. Wang, C. Xu, E. Chng, H. Lu, and Q. Tian, “Automatic Composition of Broadcast Sports Video”, Multimedia Systems, vol 14, no. 4, pp. 179-193, Mar. 2008.

[9] F. Choi, R. Beales, J. Hearn, S. E. Middleton, M. Addis, and C. Mangos, “A Feature-Augmented Grammar for Automated Media Production”, 2nd International Conference on Automated Production of Cross Media Content for Multi-channel Distribution, Leeds, UK, pp. 315-318, Dec. 2006.

[10] B. Yu, C. Zhang, Y. Rui, and K. Nahrstedt, “A Three Layer Virtual Director Model for Supporting Automated Multi-site Distributed Education” , IEEE International Conference on Multimedia and Expo, Toronto, Ontario, Canada, pp. 637-640, Jul. 2006.