請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/57703完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 歐陽明(Ming Ouhyoung) | |
| dc.contributor.author | Ming-Wei Chang | en |
| dc.contributor.author | 張洺偉 | zh_TW |
| dc.date.accessioned | 2021-06-16T06:58:55Z | - |
| dc.date.available | 2014-07-29 | |
| dc.date.copyright | 2014-07-29 | |
| dc.date.issued | 2014 | |
| dc.date.submitted | 2014-07-17 | |
| dc.identifier.citation | [1] D. Scharstein, R. Szeliski, and R. Zabih, “A taxonomy and evaluation of dense
two-frame stereo correspondence algorithms.” in Proceedings of the IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV’01), SMBV ’01, pages 131–, Washington, DC, USA, 2001. [2] Kanade, Takeo, and Masatoshi Okutomi. 'A stereo matching algorithm with an adaptive window: Theory and experiment.' Pattern Analysis and Machine Intelligence, IEEE Transactions on 16.9 (1994): 920-932. [3] Boykov, Yuri, Olga Veksler, and Ramin Zabih. 'A variable window approach to early vision.' Pattern Analysis and Machine Intelligence, IEEE Transactions on20.12 (1998): 1283-1294. [4] Yoon, Kuk-Jin, and In So Kweon. 'Adaptive support-weight approach for correspondence search.' IEEE Transactions on Pattern Analysis and Machine Intelligence 28.4 (2006): 650-656. [5] Yang, Qingxiong. 'A non-local cost aggregation method for stereo matching.'Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012. [6] Mei, Xing, et al. 'Segment-Tree based Cost Aggregation for Stereo Matching.'Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on. IEEE, 2013. [7] Boykov, Yuri, Olga Veksler, and Ramin Zabih. 'Fast approximate energy minimization via graph cuts.' Pattern Analysis and Machine Intelligence, IEEE Transactions on 23.11 (2001): 1222-1239. [8] Boykov, Yuri, and Vladimir Kolmogorov. 'An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision.' Pattern Analysis and Machine Intelligence, IEEE Transactions on 26.9 (2004): 1124-1137. 4 6 [9] Sinha, Sudipta N. 'Graph cut algorithms in vision, graphics and machine learning.' IEEE transactions on Pattern Analysis and Machine Intelligence (PAMI) 26.9 (2004): 1124-1137. [10] Hammer, Peter L., Pierre Hansen, and Bruno Simeone. 'Roof duality, complementation and persistency in quadratic 0–1 optimization.' Mathematical programming 28.2 (1984): 121-155. [11] Boros, Endre, P. L. Hammer, and X. Sun. “Network flows and minimization of quadratic pseudo-Boolean functions.” Vol. 4. No. 8. Technical Report RRR 17-1991, RUTCOR, 1991. [12] E. Boros, P. L. Hammer, and G. Tavares, “Preprocessing of Unconstrained Quadratic Binary Optimization.” Technical Report RRR 10-2006, RUTCOR Research Report, April 2006. [13] Rother, Carsten, et al. 'Optimizing binary MRFs via extended roof duality.'Computer Vision and Pattern Recognition, 2007. CVPR'07. IEEE Conference on. IEEE, 2007. [14] Kolmogorov, Vladimir, and Carsten Rother. 'Minimizing nonsubmodular functions with graph cuts-a review.' Pattern Analysis and Machine Intelligence, IEEE Transactions on 29.7 (2007): 1274-1279. [15] Lempitsky, Victor, Carsten Rother, and Andrew Blake. 'Logcut-efficient graph cut optimization for markov random fields.' Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on. IEEE, 2007. [16] Lempitsky, Victor, et al. 'Fusion moves for markov random field optimization.'Pattern Analysis and Machine Intelligence, IEEE Transactions on 32.8 (2010): 1392-1405. [17] Woodford, Oliver, et al. 'Global stereo reconstruction under second-order smoothness priors.' Pattern Analysis and Machine Intelligence, IEEE Transactions on 31.12 (2009): 2115-2128. 4 7 [18] Bleyer, Michael, and Margrit Gelautz. 'A layered stereo algorithm using image segmentation and global visibility constraints.' Image Processing, 2004. ICIP'04. 2004 International Conference on. Vol. 5. IEEE, 2004. [19] Comaniciu, Dorin, and Peter Meer. 'Mean shift: A robust approach toward feature space analysis.' Pattern Analysis and Machine Intelligence, IEEE Transactions on 24.5 (2002): 603-619. [20] Kornprobst, Pierre, and Jack Tumblin. Bilateral filtering: Theory and applications. Now Publishers Inc, 2009. [21] He, Kaiming, Jian Sun, and Xiaoou Tang. 'Guided image filtering.' Computer Vision–ECCV 2010. Springer Berlin Heidelberg, 2010. 1-14. [22] Bleyer, Michael, Christoph Rhemann, and Carsten Rother. 'PatchMatch Stereo-Stereo Matching with Slanted Support Windows.' BMVC. Vol. 11. 2011. [23] Tao, Hai, Harpreet S. Sawhney, and Rakesh Kumar. 'A global matching framework for stereo computation.' Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on. Vol. 1. IEEE, 2001. [24] Woodford, Oliver J., et al. 'On New View Synthesis Using Multiview Stereo.'BMVC. 2007. [25] Wei, Yichen, and Long Quan. 'Asymmetrical occlusion handling using graph cut for multi-view stereo.' Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 2. IEEE, 2005. [26] Kolmogorov, Vladimir, and Ramin Zabih. 'Multi-camera scene reconstruction via graph cuts.' Computer Vision—ECCV 2002. Springer Berlin Heidelberg, 2002. 82-96. [27] Kolmogorov, Vladimir, and Ramin Zabih. 'Computing visual correspondence with occlusions using graph cuts.' Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on. Vol. 2. IEEE, 2001. 4 8 [28] Veksler, Olga. 'Stereo correspondence by dynamic programming on a tree.'Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 2. IEEE, 2005. [29] Lei, Cheng, Jason Selzer, and Yee-Hong Yang. 'Region-tree based stereo using dynamic programming optimization.' Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on. Vol. 2. IEEE, 2006. [30] Birchfield, Stan, and Carlo Tomasi. 'Multiway cut for stereo and motion with slanted surfaces.' Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on. Vol. 1. IEEE, 1999. [31] Lewis, J. P. 'Fast normalized cross-correlation.' Vision interface. Vol. 10. No. 1. 1995. [32] Joe, Barry. 'Delaunay triangular meshes in convex polygons.' SIAM Journal on Scientific and Statistical Computing 7.2 (1986): 514-539. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/57703 | - |
| dc.description.abstract | 在本篇論文中，我們提出了一個創新的立體匹配技術。在我們的方法中，一張參考影像會套用Mean-Sift影像區塊分割技術，而會被分割成若干個自我顏色相似，彼此不互相重疊的區塊。我們套用局部的多視角圖片對應技術和Delaunay三角網格分割技術在特徵點上，用以產生一些在深度空間上的平面，而每一個區塊在深度空間上都能用一個平面來代表。在我們的方法中，多視角圖片對應技術的能量估計函式是以區塊作為單位，而非傳統的以像素為單位。近幾年來，圖像分割技術能夠快速地將一個能量估計函式最佳化，而我們的最佳化策略便是套用建構在以“QPBO”圖像分割為基礎上的alpha-expansion技術。在此我們提出了一個創新的方法，藉由參考影像中像素與其深度的對應關係所建造出的動態深度緩衝區，將區塊的遮擋關係考慮進“QPBO”圖像分割法中。我們拿Middlebury網站上的測試資料去評估我們所提出演算法的準確率，測試結果顯示平均的錯誤像素比例大約在百分之十之內。 | zh_TW |
| dc.description.abstract | In this paper, we propose a new method for stereo matching. In our approach, the reference image is divided into non-overlapping homogeneous segments by Mean-Shift segmentation algorithm. We apply local stereo matching methods and Delaunay triangular on feature points to generate a set of disparity plane for the scene, and each segment is represented as a plane in the disparity space. The stereo matching problem is formulated as a segment-domain energy minimization problem rather than the traditional pixel-domain in our method. The graph cut technique is used to efficiently approximate the optimal solution for energy function in recent years. Our optimization strategy is to apply the disparity plane alpha-expansion, based on “QPBO” algorithm. Therefore we propose an innovative method to approximately encode occlusion consideration into QPBO, based on a dynamic z-buffer constructed by the disparity of the warping pixels in the reference image. We evaluate our algorithm using the cases in the website “Middlebury”, and the results show that the average of bad pixels is about 10%. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T06:58:55Z (GMT). No. of bitstreams: 1 ntu-103-R01922022-1.pdf: 2579449 bytes, checksum: 3e39262f57c56ebe41e3fba5d0198bca (MD5) Previous issue date: 2014 | en |
| dc.description.tableofcontents | 致謝 ................................................................................................................................ i
中文摘要 ....................................................................................................................... ii Abstract.........................................................................................................................iii LIST OF FIGURE ........................................................................................................ vi LIST OF TABLE ......................................................................................................... vii Chapter 1 Introduction................................................................................................... 1 Chapter 2 Related Work................................................................................................. 4 Chapter 3 System Overview.......................................................................................... 9 3.1 System Flow .................................................................................................. 11 3.2 Occlusion Handling ....................................................................................... 12 Chapter 4 Pre-processing and Iterative Assignment.................................................... 15 4.1 Color Segmentation ....................................................................................... 16 4.2 Feature Point Selection and Disparity plane generation................................ 18 4.3 Segment Plane Initialization.......................................................................... 21 4.4 Energy Function ............................................................................................ 22 4.4.1 Data Term........................................................................................... 22 4.4.2 Occlusion Term................................................................................... 23 4.4.3 Smooth Term ...................................................................................... 23 4.5 Greedy algorithm........................................................................................... 24 Chapter 5 Global Assignment...................................................................................... 25 5.1 Graph Cuts in Stereo Matching ..................................................................... 26 5.2 Graph Construction ....................................................................................... 27 v 5.3 Fusion Move Algorithm ........................................................................ 32 Chapter 6 Results and Conclusion............................................................................... 33 6.1 Results and Comparison ................................................................................ 33 6.1.1 Table of Contents................................................................................ 33 6.1.2 Visual Quality Comparison ................................................................ 39 6.1.3 Initial Disparity Map and Disparity Buffer ........................................ 39 6.2 Conclusion..................................................................................................... 44 6.3 Feature Works................................................................................................ 44 Bibliography ................................................................................................................ 45 | |
| dc.language.iso | en | |
| dc.subject | 立體匹配 | zh_TW |
| dc.subject | 圖割 | zh_TW |
| dc.subject | stereo matching | en |
| dc.subject | graph cut | en |
| dc.title | 利用像素遮擋關係與圖割技術之深度影像生成 | zh_TW |
| dc.title | Occlusion-cues as Consideration for Warping in Stereo Matching Using Graph Cuts | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 102-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 傅楸善(Chiou-Shann Fuh),楊傳凱(Chuan-Kai Yang) | |
| dc.subject.keyword | 立體匹配,圖割, | zh_TW |
| dc.subject.keyword | stereo matching,graph cut, | en |
| dc.relation.page | 48 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2014-07-17 | |
| 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-103-1.pdf 未授權公開取用 | 2.52 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。