政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/32711

政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/32711

English | 正體中文 | 简体中文 | Post-Print筆數 : 27 | Items with full text/Total items : 113451/144438 (79%)
Visitors : 51288133 Online Users : 870

RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

Scope

please add "double quotation mark" for query phrases to get precise results

please goto advance search for comprehansive author search

Adv. Search

Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer

Goto mobile version

政大典藏 > College of Informatics > Department of Computer Science > Theses > Item 140.119/32711

Please use this identifier to cite or link to this item: https://nccur.lib.nccu.edu.tw/handle/140.119/32711

Title:	影片動跡剪輯
Authors:	王智潁 Wang, Chih-Ying
Contributors:	何瑁鎧 Hor, Maw-Kae 王智潁 Wang, Chih-Ying
Keywords:	視訊處理影片剪輯全域動作計算 video process video editing global motion estimation
Date:	2004
Issue Date:	2009-09-17 14:06:44 (UTC+8)
Abstract:	「動跡剪輯」是將多個不同內容的影片片段，根據影片中特定物體移動的關係，剪接成新的影片，使得產生的新影片能維持動作連貫及流暢的特性。本論文提出一套方法能夠自動找尋不同影片間相似的剪輯點，作為「動跡剪輯」的參考。此方法之重點在於建立影片的時空資訊，作為找尋剪輯點的依據。建立影片時空資訊的過程中，我們先將影片依偵測出的鏡頭轉換點分割成不同的影片片段，再將影片片段中前景物件的位置、大小與動作等資訊分離而成影片物件平面，並結合影片片段中的背景動作資訊與影片物件平面資訊，成為該影片片段之時空資訊，從而進行剪輯點之找尋與比對，擇其最佳點進行剪輯。運用影片時空資訊於找尋影片間之剪輯點時，是以影片物件平面作為搜尋單位，此方式有助於提升結果的正確性，同時也提供了搜尋時的靈活度。 With the rapid increasing of the multimedia applications in modern commercial and movie business, it becomes more desirable to have efficient video editing tools. However, conventional video editing requires too many manual interventions that reduce productivities as well as opportunities in better performance. In this thesis, we propose a MOtion-based Video Editing (MOVE) mechanism that can automatically select the most similar or suitable transition points from a given set of raw videos. A given video can be divided into a set of video clips using a shot detection algorithm. For each video clip, we provide an algorithm that can separate the global motions as well as the local motions using the principles of video object plane and accumulated difference. We introduce the concept of spatio-temporal information, a condensed information that associated with a video clip. We can use this information in finding a good video editing point. Since the spatio-temporal information is a concise representation of a video clip, searching in this domain will reduce the complexity of the problem and achieve better performance. We implemented our mechanism with successful experiments.
Reference:	[1] Dufaux, F. and Konrad, J., “Efficient, robust, and fast global motion estimation for video coding,” IEEE Trans. Image Processing, Vol. 9, No. 3, , pp. 497 – 501, Mar. 2000. [2] Wang Y. A. and Edward H. A., “Spatio-temporal segmentation of video data,” in Proc. SPIE, Image and Video Processing II, Vol. 2182, Feb. 1994. [3] Daniel D., David D., “Video retrieval using spatio-temporal descriptors,” in Proc. ACM Conf. on Multimedia, pp. 508 – 517, Nov. 2003. [4] Del B., A., Pala, P., Tanganelli, L., “Video retrieval based on dynamics of color flows,” in Proc. Int. Conf. Pattern Recognition, Vol. 1, pp. 851 – 854, Sept. 2000. [5] Nummiaro K., Koller-Meier E. and Van G. L., “Color features for tracking non-rigid objects,” Special Issue on Visual Surveillance, Chinese Journal of Automation, Vol. 29, No. 3, pp 345-355, May 2003. [6] Forsyth D. A. and Ponce J., “Computer vision: A modern approach,” Pearson Education, part I-part IV, 2003. [7] Dufaux, F. and Moscheni, F., “Motion estimation techniques for digital TV: A review and a new contribution,” in Proc. IEEE, vol.83, pp.858-879, Jun. 1995. [8] Tse Y. T. and Baker R. L., “Global zoom/pan estimation and compensation for video compression,” in IEEE Proc. ICASSP’91, vol. IV, pp.2725-2728, May 1991. [9] Moscheni, F., Dufaux, F. and Kunt, M., “A new two-stage motion estimation based on a background/foreground segmentation,” in IEEE Proc. ICASSP’95, pp. 2261-2264, Detroit, MI, May 1995. [10] Ebrahimi T., “MPEG-4 video verification model: A video encoding/decoding algorithm based on content representation,” Signal Proc. Image Communication 9, No. 4, pp. 367-384, May 1997. [11] Sikora T., “The MPEG-4 video standard verification model,” IEEE Trans. CSVT, Vol.7, No.1, Feb. 1997. [12] Gonzalez R. C. and Woods R. E., “Digital image processing,” Prentice Hall, chapter7, pp.349-403, 2001. [13] Grigoriu, L., “Spatio-temporal compression of the motion field in video coding,” IEEE Workshop on Multimedia Signal Proc., pp. 129 – 134, Oct. 2001. [14] Lai-Man P. and Wing-Chung M., “A novel four-step search algorithm for fast block motion estimation,” IEEE Trans. CSVT, Vol. 6, No. 3, pp. 313-317, Jun. 1996. [15] Richard S., “Image Mosaicing for tele-reality applications,” Cambridge Research Laboratory Technical Report Series, May 1994. [16] Deng Y. and Manjunath B. S., “Content-based search of video using color, texture and motion,” in Proc. IEEE Int. Conf. Image Processing, volume 2, pp. 534–537, 1997. [17] Belongie S., Carson C., Greenspan H. and Malik J., “Color and texture-based image segmentation using em and its application to content based image retrieval,” in Proc. of Int. Conf. on Computer Vision, pp. 675-682, 1998. [18] Greenspan H. and Goldberger J., “Probabilistic space-time video modeling via piecewise GMM,” IEEE Pattern Analysis and Machine Intelligence, vol. 26, no. 3, 2004. [19] Memin E. and Perez P., “Dense estimation and object-based segmentation of the optical flow with robust techniques,” IEEE Trans. Image Processing, Vol. 7, No. 5, pp. 703 – 719, May 1998. [20] Eric B. and St´ephane M., “Nonlinear temporal modeling for motion-based video overviewing,” in Proc. European Conf. on Content-based Multimedia Indexing, Sept., 2003. [21] Ianeva T., Vries A. P. de and Westerveld. T., “A dynamic probabilistic retrieval model,” IEEE Int. Conf. on Multimedia and Expo (ICME), 2004. [22] Cheung, S.-C.S. and Zakhor A., “Video similarity detection with video signature clustering,” in Proc. of International Conf. on Image Processing, Vol. 2, pp. 649 – 652, Oct. 2001. [23] Bregler C., “Learning and recognizing human dynamics in video sequences,” in IEEE CVPR, June 1997.
Description:	國立政治大學資訊科學學系 91753016 93
Source URI:	http://thesis.lib.nccu.edu.tw/record/#G0917530161
Data Type:	thesis
Appears in Collections:	[Department of Computer Science ] Theses

Files in This Item:

File	Description	Size	Format
53016101.pdf		48Kb	Adobe PDF2	833	View/Open
53016102.pdf		75Kb	Adobe PDF2	1148	View/Open
53016103.pdf		66Kb	Adobe PDF2	855	View/Open
53016104.pdf		73Kb	Adobe PDF2	701	View/Open
53016105.pdf		207Kb	Adobe PDF2	1110	View/Open
53016106.pdf		103Kb	Adobe PDF2	934	View/Open
53016107.pdf		518Kb	Adobe PDF2	1202	View/Open
53016108.pdf		270Kb	Adobe PDF2	936	View/Open
53016109.pdf		767Kb	Adobe PDF2	820	View/Open
53016110.pdf		111Kb	Adobe PDF2	900	View/Open
53016111.pdf		50Kb	Adobe PDF2	671	View/Open

All items in 政大典藏 are protected by copyright, with all rights reserved.

社群 sharing

著作權政策宣告 Copyright Announcement

1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.

DSpace Software Copyright © 2002-2004 MIT & Hewlett-Packard / Enhanced by NTU Library IR team Copyright © - Feedback