請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/43573
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 洪一平(Yi-Ping Hung) | |
dc.contributor.author | Po-Yu Huang | en |
dc.contributor.author | 黃柏瑜 | zh_TW |
dc.date.accessioned | 2021-06-15T02:23:40Z | - |
dc.date.available | 2012-08-20 | |
dc.date.copyright | 2009-08-20 | |
dc.date.issued | 2009 | |
dc.date.submitted | 2009-08-18 | |
dc.identifier.citation | [1] H. Christopher Longuet-Higgins, A Computer Algorithm for Reconstructing a Scene From Two Projections. Nature Vol. 293, pp. 133-135, 1981
[2] R. Hartley, A. Zisserman, Multiple View Geometry in Computer Vision, Second Edition, Cambridge University Press, Cambridge, 2000. [3] R. Hartley, F. Kahl, Global Optimization Through Rotation Space Search, International Journal of Computer Vision, Vol. 82, pp. 64-79, 2009. [4] F. Kahl, R. Hartley, Multiple View Geometry under L∞-norm, IEEE Transactions on Pattern Analysis and Machine intelligence, Vol. 30, pp. 1630-1617, 2008. [5] Q. Ke and T. Kanade, A Robust Subspace Approach to Layer Extraction, Proc. IEEE Workshop Motion and Video Computing, 2002. [6] Q. Ke and T. Kanade, A Subspace Approach to Layer Extraction, Proc. IEEE Workshop Motion and Video Computing, 2002. [7] S. Khan and M. Shah, Object Based Segmentation of Video Using Color, Motion and Spatial, Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2001. [8] David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision archive, Vol. 60, pp. 91-110, 2004. [9] C.-R. Huang , C.-S. Chen, and P.-C. Chung, Contrast Context Histogram - an Efficient Discriminating Local Descriptor for Object Recognition and Image Matching, Pattern Recognition , Vol. 41, no. 10, pp. 3071-3077, 2008. [10] C.-R. Huang, C.-S. Chen, P.-C. Chung, Contrast Context Histogram – A Discriminating Local Descriptor for Image Matching, In Proceedings of 18th IAPR International Conference on Pattern Recognition , Vol. 4, pp. 53-56, 2006. [11] M.S. Lobo, L. Vandenberghe, S.P. Boyd, H. Lebret. Applications of Second-Order Cone Programming, Linear Algebra and Its Applications, Vol. 284, pp. 193-228, 1998. [12] T. Schoenemann, D. Cremers, High Resolution Motion Layer Decomposition Using Dual-Space Graph Cuts, IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-7, 2008. [13] M. Shah, J. Xiao, Motion layer extraction in the presence of occlusion using graph cuts, Proc. IEEE Conf. Computer Vision and Pattern Recognition, Vol. 27, pp. 1644-1659, 2004. [14] P. Smith, T. Drummond, and R. Cipollaa, Layered Motion Segmentation and Depth Ordering by Tracking Edges, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 26, no. 4, pp. 479-494, 2004. [15] R.W. Freund, F. Jarre, Solving the Sum-of-Ratios Problem by an Interior-Point Method, J. Glob. Opt. 19, pp. 83-102, 2001. [16] J. Wang, E. Adelson, Representing Moving Images with Layers, IEEE Transition on Image Processing, Vol. 3, no. 5, pp. 625-638, 1994. [17] Y. Weiss, Smoothness in Layers: Motion Segmentation Using Nonparametric Mixture Estimation, Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 520, 1997. [18] T. Yu-Tian, M. Shah, Recovering 3D Motion of Multiple Objects Using Adaptive Hough Transform, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, no. 10, pp. 1178-1183, 1997. [19] Z. Zhang, A Flexible New Technique for Camera Calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, no. 11, pp. 1330-1334, 2000. [20] Http://research.microsoft.com/en-us/um/people/zhang/Calib/#Application. [21] Http://www.vision.jhu.edu. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/43573 | - |
dc.description.abstract | 在資訊科學領域中,影片的動態分析一直是個很重要的議題。其可協助影片分析與歸類,使得影片的瀏覽與檢索更為迅速。傳統上,運動分割的技術,多半建立在固定相機,或是已知相機參數的基礎上,找出相鄰影像的光流並將其分類,其缺點是無法實用於一般未知相機參數的多媒體影像上。近年來,基於對應點並搭配二維的運動模型之方法被廣泛的使用。但使用二維的運動模型處理三維的運動關係還是有其限制。針對此一問題,本論文主要是採用一三維的運動模型,提出改良後的霍氏轉換,解決三維運動模型參數估計上的困難,並搭配分支限界法解決傳統霍氏轉換速度上的問題。最後經由霍氏轉換估算影片中兩種以上的運動模型,以此做為影片前後景的分割,並且由背景的運動回朔相機的運動參數,借此幫助影片的分析與歸類。
改良後的霍氏轉換,不需在所有的參數空間取樣,藉由在第一台相機焦距以及旋轉上取樣,估算出第二台相機以及位移,藉此減少取樣之維度。並在旋轉的取樣搭配分支限界法,使我們只需取樣於原旋轉空間之子空間,提高取樣之效率。實驗結果顯示,本論文所提出的方法確實能有效的分辨一般大眾化影像之前後景,並且估算出的三維運動參數也具有一定的準確度,速度上也優於傳統的霍氏轉換。 | zh_TW |
dc.description.abstract | Video motion analysis is a critical issue for multimedia signal processing. It can help video summarization and classification, which make the browsing and indexing more quickly. Clustering motions under fixed cameras or calibrated cameras has been developed recently. The drawback of these methods is it’s hard to realize on real video, which is usually un-calibrated. To deal with this problem, we propose a Hough transform based method which samples 3D motion parameters, including the focal length of the camera intrinsic matrix, the relative rotation, and translation. However, fully sampling all parameters is time consuming. We partially sample the focal length of the first camera and relative rotation. Then, we obtain the remaining parameters by solving a geometry optimization problem. The selection of multiple motion models is defined by a voting strategy. In addition, we combine a branch and bound algorithm with Hough transformation to solve high computation complexity of traditional Hough transform. The algorithm reduces sampling rotation space to its subspace by an efficient rotation space searching. The results of motion models are used to identify the dominant motion in videos. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T02:23:40Z (GMT). No. of bitstreams: 1 ntu-98-R96922133-1.pdf: 9573843 bytes, checksum: 3a80f82af675bfe691835aa52359fb79 (MD5) Previous issue date: 2009 | en |
dc.description.tableofcontents | 口試委員會審定書 i
致謝 ii 摘要 iii Abstract iv Contents v List of Figures vii List of Tables ix 1 Introduction 1 2 Preliminary 4 2.1 Two View Epipolar Geometry 4 2.2 Problem Formulation 6 3 Dominant Motion Estimation Using Hough Transform with Branch and Bound 11 3.1 Geometry of the Space of Rotation 12 3.2 Subdividing Rotation Space and Lower Bound Definition 14 3.3 Dominant Motion Estimation 18 4 Experimental Results 20 4.1 Simulation Data 20 4.2 Real Data 27 5 Conclusion and Future Works 37 Bibliography 38 | |
dc.language.iso | en | |
dc.title | 由兩張影像計算相機主要運動參數 | zh_TW |
dc.title | Dominant Motion Estimation from Two Images | en |
dc.type | Thesis | |
dc.date.schoolyear | 97-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 陳祝嵩(Chu-Song Chen) | |
dc.contributor.oralexamcommittee | 唐政元,黃于飛 | |
dc.subject.keyword | 運動參數偵測,電腦視覺, | zh_TW |
dc.subject.keyword | Motion Estimation,Computer vision, | en |
dc.relation.page | 40 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2009-08-18 | |
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-98-1.pdf 目前未授權公開取用 | 9.35 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。