請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/40256
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳炳宇 | |
dc.contributor.author | Wei-Ting Huang | en |
dc.contributor.author | 黃惟婷 | zh_TW |
dc.date.accessioned | 2021-06-14T16:43:29Z | - |
dc.date.available | 2008-08-14 | |
dc.date.copyright | 2008-08-14 | |
dc.date.issued | 2008 | |
dc.date.submitted | 2008-07-31 | |
dc.identifier.citation | [BA93] Michael J. Black and P. Anandan. A framework for the robust estimation of
optical flow. In Proceedings of 1993 IEEE International Conference on Computer Vision, pages 231–236, 1993. [BA96] Michael J. Black and P. Anandan. The robust estimation of multiple motions: parametric and piecewise-smooth flow fields. Computer Vision and Image Understanding, 63(1):75–104, 1996. [BBM01] Chris Buehler, Michael Bosse, and Leonard McMillan. Non-metric image-based rendering for video stabilization. In IEEE Computer Vision and Pattern Recognition 2001 Conference Proceedings, volume 2, pages 609–614, 2001. [BSCB00] Marcelo Bertalmio, Guillermo Sapiro, Vincent Caselles, and Coloma Ballester. Image inpainting. In ACM SIGGRAPH 2000 Conference Proceedings, pages 417– 424, 2000. [CPT03] Antonio Criminisi, Patrick Perez, and Kentaro Toyama. Object removal by exemplar-based inpainting. In IEEE Computer Vision and Pattern Recognition 2003 Conference Proceedings, volume 2, pages 721–728, 2003. [CRM] D. Comaniciu, V. Ramesh, and P. Meer. Real-time tracking of non-rigid objects using mean shift. pages 142–151. [FB81] Martin A. Fischler and Robert C. Bolles. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6):381–395, 1981. [GL07] Michael Gleicher and Feng Liu. Re-cinematography: improving the camera dynamics of casual video. In ACM Multimedia, pages 27–36, 2007. [IB96] Michael Isard and Andrew Blake. Contour tracking by stochastic propagation of conditional density. In ECCV (1), pages 343–356, 1996. [IB98] Michael Isard and Andrew Blake. ICONDENSATION: Unifying low-level and high-level tracking in a stochastic framework. Lecture Notes in Computer Science, 1406:893–908, 1998. [IKN98] Laurent Itti, Christof Koch, and Ernst Niebur. A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(11):1254–1259, 1998. [JWTT04] Jiaya Jia, Tai-Pang Wu, Yu-Wing Tai, and Chi-Keung Tang. Video repairing inference of foreground and background under severe occlusion. In IEEE Computer Vision and Pattern Recognition 2004 Conference Proceedings, volume 1, pages 364–371, 2004. [Lin07] Jung-Shan Lin. Full-frame video stabilization by considering capturing intention. NTU master thesis, 2007. [LKK03] Andrew Litvin, Janusz Konrad, and William C. Karl. Probabilistic video stabilization using Kalman filtering and mosaicking. In Proceedings of 2003 SPIE Conference on Electronic Imaging, volume 5022, pages 663–674, 2003. [Low99] David G. Lowe. Object recognition from local scale-invariant features. In Proceedings of 1999 IEEE International Conference on Computer Vision, pages 1150– 1157, 1999. [LZW03] Anat Levin, Assaf Zomet, and Yair Weiss. Learning how to inpaint from global image statistics. In Proceedings of 2003 IEEE International Conference on Computer Vision, volume 1, pages 305–312, 2003. [MOTS05] Yasuyuki Matsushita, Eyal Ofek, Xiaoou Tang, and Heung-Yeung Shum. Fullframe video stabilization. In IEEE Computer Vision and Pattern Recognition 2005 Conference Proceedings, volume 1, pages 50–57, 2005. [PN04] Zailiang Pan and Chong-Wah Ngo. Structuring home video by snippet detection and pattern parsing. In ACM SIGMM Multimedia Information Retrieval 2004 Conference Proceedings, pages 69–76, 2004. [PRAP08] Yael Pritch, Alex Rav-Acha, and Shmuel Peleg. Non-chronological video synopsis and indexing. IEEE, 2008. [PSB07] Kedar A. Patwardhan, Guillermo Sapiro, and Marcelo Bertalmio. Video inpainting under constrained camera motion. IEEE Transactions On Image Processing, 16(2):545–553, 2007. [SBF00] Hedvig Sidenbladh, Michael J. Black, and David J. Fleet. Stochastic tracking of 3d human figures using 2d image motion. In ECCV (2), pages 702–718, 2000. [SMTK06] Takaaki Shiratori, Yasuyuki Matsushita, Xiaoou Tang, and Sing Bing Kang. Video completion by motion field transfer. In IEEE Computer Vision and Pattern Recognition 2006 Conference Proceedings, volume 1, pages 411–418, 2006. [WSI04] Y. Wexler, E. Shechtman, and M. Irani. Space-time video completion. In IEEE Computer Vision and Pattern Recognition 2004 Conference Proceedings, volume 1, pages 120–127, 2004. [YTHB00] Yiming Ye, John K. Tsotsos, Eric Harley, and Karen Bennet. Tracking a person with pre-recorded image database and a pan, tilt, and zoom camera. Mach. Vision Appl., 12(1):32–43, 2000. [ZS06] Yun Zhai and Mubarak Shah. Visual attention detection in video sequences using spatiotemporal cues. In ACM Multimedia 2006 Conference Proceedings, pages 815–824, 2006. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/40256 | - |
dc.description.abstract | 一般徒手拍攝的影片之中,或多或少會受外力的干擾而造成影片的不規則晃動,對於日益成熟的影片穩定系統雖有不錯的成果,但由於其適用的情況在於影片主題佔據畫面部分較小的情況之下方可得到較完美的結果。換言之,前景的區域大時,或是相對於前景,背景的場景不夠完整時,可能會造成影片在對齊的過程之中參考區域的誤判,造成影片的不連續。
本篇論文針對此情況提出一新的修正技術,目的於確保使用者的拍攝主體頗大時,或是背景常景較不完整時,經過本系統作些適當的修正後也能有其穩定畫面的效果。本系統運用optical flow計算出連續兩個影格之間每個像素相對移動的垂直及水平方向變化量,進而以k-means clustering方式適當地分割出影格畫面中不同移動型態的區塊,繼而針對適切的區塊進行攝影路徑的擷取方可得到較為正確的路徑。藉由取得的攝影路徑,本系統利用些許直線來代替原本的攝影路定以達到畫面的平穩性。本系統針對transform matrix運用了QR decomposition 以幫助我們將位移以及角度旋轉問題分開進行改善,同時影格盡可能保持原有的大小比例。最後以內插第一對影格與最後一對影格間的角度變化以達到畫面轉動的連續性以及其穩定性。由以上的步驟,即可得出一段看起來較為舒適及穩定的影片,甚至像是利用腳架拍攝出來的結果。 | zh_TW |
dc.description.abstract | This thesis presents an approach to post-processing casually captured videos to improve
apparent camera movement. A lot of home videos have some problems about the artifacts like hand shaking when capturing without tripod. Video stabilization is an important technique to solve this problem. However, the technique does not work very well in some situations such as the larger foreground, incomplete background or other situations,etc. In this thesis,we propose a novel method of video stabilization to overcome the situations with the larger foreground, or the feature points amount of the background is less then of foreground and some camera motion such as zoom in and zoom out. This system applies a method, optical flow, to estimate the motion vector of all pixels between each pair frames. Then, we use K-means clustering to group the similar motion vectors of each frame. To select an adequate segment to estimate the global camera path of video could obtain one more correct global camera path. After motion vector segmentation and camera path estimation, we could stitch all of video frames to get a panorama and estimate the range of moving object we can recover by neighbor frames. Based on the background panorama and moving object recovered range, we could find some new paths which would lose information less. After the above operations, a full-stabilized video could be achieved. | en |
dc.description.provenance | Made available in DSpace on 2021-06-14T16:43:29Z (GMT). No. of bitstreams: 1 ntu-97-R95922037-1.pdf: 10281127 bytes, checksum: 68aa01e9bef00d64dd553e12defb0f96 (MD5) Previous issue date: 2008 | en |
dc.description.tableofcontents | 1 Introduction 1
1.1 Motivation . . . . . . . . . 2 1.2 Problem Statement . . . . . . 4 1.3 Thesis Organization and Overview . . . . . . . . . . . . . 5 2 Related work . . . . . . . . . . 9 2.1 Moving Object Detection . . . .9 2.2 Motion Path Estimation . . . . 10 2.3 Video Completion . . . . . . . 14 3 Moving Object Detection 17 3.1 Motion Segmentation . . . . .. 17 3.2 Background Detection . . . . . 20 4 Motion Path Estimation 23 4.1 Global Path Estimation . . . . 23 4.2 Motion Path Fitting . . . . . .24 5 Video Completion 31 5.1 Dynamic Region Completion . . 31 5.2 Static Region Completion . . . 34 6 Result 37 7 Conclusion and Future Work 45 Bibliography 46 | |
dc.language.iso | en | |
dc.title | 考慮具有大範圍移動物體的晃動影片之穩定與修復 | zh_TW |
dc.title | Full-Frame Video Stabilization with Large Moving Object | en |
dc.type | Thesis | |
dc.date.schoolyear | 96-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 林文杰,陳祝嵩 | |
dc.subject.keyword | 影片穩定,影片修復,手震,晃,移動物體偵測,前景背景分離, | zh_TW |
dc.subject.keyword | home video,moving object detection,optical flow,polyline,video ROI,background segmentation, | en |
dc.relation.page | 51 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2008-08-01 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-97-1.pdf 目前未授權公開取用 | 10.04 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。