Publications-Theses
Article View/Open
Publication Export
Google ScholarTM
NCCU Library
Citation Infomation
Related Publications in TAIR
| Title | 影片動跡剪輯 |
| Creator | 王智潁 Wang, Chih-Ying |
| Contributor | 何瑁鎧 Hor, Maw-Kae 王智潁 Wang, Chih-Ying |
| Key Words | 視訊處理 影片剪輯 全域動作計算 video process video editing global motion estimation |
| Date | 2004 |
| Date Issued | 17-Sep-2009 14:06:44 (UTC+8) |
| Summary | 「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. |
| 參考文獻 | [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 |
| 資料來源 | http://thesis.lib.nccu.edu.tw/record/#G0917530161 |
| Type | thesis |
| dc.contributor.advisor | 何瑁鎧 | zh_TW |
| dc.contributor.advisor | Hor, Maw-Kae | en_US |
| dc.contributor.author (Authors) | 王智潁 | zh_TW |
| dc.contributor.author (Authors) | Wang, Chih-Ying | en_US |
| dc.creator (作者) | 王智潁 | zh_TW |
| dc.creator (作者) | Wang, Chih-Ying | en_US |
| dc.date (日期) | 2004 | en_US |
| dc.date.accessioned | 17-Sep-2009 14:06:44 (UTC+8) | - |
| dc.date.available | 17-Sep-2009 14:06:44 (UTC+8) | - |
| dc.date.issued (上傳時間) | 17-Sep-2009 14:06:44 (UTC+8) | - |
| dc.identifier (Other Identifiers) | G0917530161 | en_US |
| dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/32711 | - |
| dc.description (描述) | 國立政治大學 | zh_TW |
| dc.description (描述) | 資訊科學學系 | zh_TW |
| dc.description (描述) | 91753016 | zh_TW |
| dc.description (描述) | 93 | zh_TW |
| dc.description.abstract (摘要) | 「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。 | zh_TW |
| dc.description.abstract (摘要) | 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. | en_US |
| dc.description.tableofcontents | 第一章 緒論 1.1 簡介 1.2 問題描述 1.3 研究動機 1.4 本論文的貢獻 1.5 章節架構 第二章 相關研究 第三章 影片時空資訊的取得 3.1 影片物件平面 3.2 時空資訊 3.3 動作偵測 3.3.1 動作模型 3.3.2 梯度下降法 3.3.3 全域動作偵測 3.3.4 區域動作偵測 3.4 影片物件平面建立 3.4.1 前景與背景分離 3.4.2 像素分群 3.4.3 物件平面追蹤 3.5 時空資訊與動跡剪輯 第四章 動跡剪輯系統架構 4.1 鏡頭轉換偵測 4.2 時空資訊建立 4.3 初步影片比較 4.4 影片配對評分 4.5 複雜度分析 第五章 實驗 5.1 實驗一：找尋影片間的動跡剪輯點 5.2 實驗二：全域動作偵測與鏡頭轉換偵測 第六章 總結 6.1 結論 6.2 未來展望 參考文獻 | zh_TW |
| dc.format.extent | 49485 bytes | - |
| dc.format.extent | 77270 bytes | - |
| dc.format.extent | 67590 bytes | - |
| dc.format.extent | 75121 bytes | - |
| dc.format.extent | 212198 bytes | - |
| dc.format.extent | 106151 bytes | - |
| dc.format.extent | 530768 bytes | - |
| dc.format.extent | 276728 bytes | - |
| dc.format.extent | 785658 bytes | - |
| dc.format.extent | 114683 bytes | - |
| dc.format.extent | 52168 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.format.mimetype | application/pdf | - |
| dc.format.mimetype | application/pdf | - |
| dc.format.mimetype | application/pdf | - |
| dc.format.mimetype | application/pdf | - |
| dc.format.mimetype | application/pdf | - |
| dc.format.mimetype | application/pdf | - |
| dc.format.mimetype | application/pdf | - |
| dc.format.mimetype | application/pdf | - |
| dc.format.mimetype | application/pdf | - |
| dc.format.mimetype | application/pdf | - |
| dc.language.iso | en_US | - |
| dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#G0917530161 | en_US |
| dc.subject (關鍵詞) | 視訊處理 | zh_TW |
| dc.subject (關鍵詞) | 影片剪輯 | zh_TW |
| dc.subject (關鍵詞) | 全域動作計算 | zh_TW |
| dc.subject (關鍵詞) | video process | en_US |
| dc.subject (關鍵詞) | video editing | en_US |
| dc.subject (關鍵詞) | global motion estimation | en_US |
| dc.title (題名) | 影片動跡剪輯 | zh_TW |
| dc.type (資料類型) | thesis | en |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [3] Daniel D., David D., “Video retrieval using spatio-temporal descriptors,” in Proc. ACM Conf. on Multimedia, pp. 508 – 517, Nov. 2003. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [6] Forsyth D. A. and Ponce J., “Computer vision: A modern approach,” Pearson Education, part I-part IV, 2003. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [11] Sikora T., “The MPEG-4 video standard verification model,” IEEE Trans. CSVT, Vol.7, No.1, Feb. 1997. | zh_TW |
| dc.relation.reference (參考文獻) | [12] Gonzalez R. C. and Woods R. E., “Digital image processing,” Prentice Hall, chapter7, pp.349-403, 2001. | zh_TW |
| dc.relation.reference (參考文獻) | [13] Grigoriu, L., “Spatio-temporal compression of the motion field in video coding,” IEEE Workshop on Multimedia Signal Proc., pp. 129 – 134, Oct. 2001. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [15] Richard S., “Image Mosaicing for tele-reality applications,” Cambridge Research Laboratory Technical Report Series, May 1994. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [21] Ianeva T., Vries A. P. de and Westerveld. T., “A dynamic probabilistic retrieval model,” IEEE Int. Conf. on Multimedia and Expo (ICME), 2004. | zh_TW |
| dc.relation.reference (參考文獻) | [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. | zh_TW |
| dc.relation.reference (參考文獻) | [23] Bregler C., “Learning and recognizing human dynamics in video sequences,” in IEEE CVPR, June 1997. | zh_TW |