請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/41542
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 | Hong-Shang Lin | en |
dc.contributor.author | 林宏祥 | zh_TW |
dc.date.accessioned | 2021-06-15T00:22:23Z | - |
dc.date.available | 2011-08-26 | |
dc.date.copyright | 2011-08-26 | |
dc.date.issued | 2011 | |
dc.date.submitted | 2011-08-15 | |
dc.identifier.citation | [BBB+10] Thabo Beeler, Bernd Bickel, Paul Beardsley, Bob Sumner, and Markus Gross. High-quality single-shot capture of facial geometry. In ACM SIGGRAPH 2010 papers, SIGGRAPH ’10, pages 40:1–40:9, New York, NY,USA, 2010. ACM.
[BI99] Aaron F. Bobick and Stephen S. Intille. Large occlusion stereo. Int. J. Comput. Vision, 33:181–200, September 1999. [BRK10] Michael Bleyer, Carsten Rother, and Pushmeet Kohli. Surface stereo with soft segmentation. In CVPR’10, pages 1570–1577, 2010. [BRK+11] Michael Bleyer, C Rother, P Kohli, D Scharstein, and S Sinha. Object Stereo — Joint Stereo Matching and Object Segmentation, pages 3081–3088. Number 1. 2011. [BT98] Stan Birchfield and Carlo Tomasi. A pixel dissimilarity measure that is insensitive to image sampling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20:401–406, 1998. [BVZ01] Yuri Boykov, Olga Veksler, and Ramin Zabih. Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23:2001, 2001. [CM02] Dorin Comaniciu and Peter Meer. Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell., 24(5):603–619, 2002. [Col96] Robert T. Collins. A space-sweep approach to true multi-image matching.In Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR ’96), CVPR ’96, pages 358–, Washington, DC, USA,1996. IEEE Computer Society. [FH06] Pedro F. Felzenszwalb and Daniel P. Huttenlocher. Efficient belief propagation for early vision. Int. J. Comput. Vision, 70:41–54, October 2006. [GmFM+07] David Gallup, Jan michael Frahm, Philippos Mordohai, Qingxiong Yang, and Marc Pollefeys. Real-time plane-sweeping stereo with multiple sweeping directions. In Computer Vision and Pattern Recognition, 2007. [HZ00] R. I. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, ISBN: 0521623049, 2000. [KLCL05] Jae Chul Kim, Kyoung Mu Lee, Byoung Tae Choi, and Sang Uk Lee. A dense stereo matching using two-pass dynamic programming with generalized ground control points. In Proceedings IEEE International Conference on Computer Vision and Pattern Recognition, Vol. II, pages 1075–1082. IEEE Computer Society, 2005. [KS04] Sing Bing Kang and Richard Szeliski. Extracting view-dependent depth maps from a collection of images. Int. J. Comput. Vision, 58:139–163, July 2004. [KSK06] Andreas Klaus, Mario Sormann, and Konrad Karner. Segment-based stereo matching using belief propagation and a self-adapting dissimilarity mea- sure. In Proceedings of the 18th International Conference on Pattern Recognition - Volume 03, ICPR ’06, pages 15–18, Washington, DC, USA, 2006. IEEE Computer Society. [KZ01] Vladimir Kolmogorov and Ramin Zabih. Computing visual correspondence with occlusions via graph cuts. In In International Conference on Computer Vision, pages 508–515, 2001. [KZ02] Vladimir Kolmogorov and Ramin Zabih. Multi-camera scene reconstruction via graph cuts. In in European Conference on Computer Vision, pages 82–96, 2002. [Low04] David G. Lowe. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision, 60:91–110, November 2004. [LZ06] Gang Li and Steven W. Zucker. Surface geometric constraints for stereo in belief propagation. In Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2,CVPR ’06, pages 2355–2362, Washington, DC, USA, 2006. IEEE Computer Society. [OK93] M. Okutomi and T. Kanade. A multiple-baseline stereo. IEEE Trans. Pattern Anal. Mach. Intell., 15:353–363, April 1993. [SCD+06] Steven M. Seitz, Brian Curless, James Diebel, Daniel Scharstein, and Richard Szeliski. A comparison and evaluation of multi-view stereo reconstruction algorithms, 2006. [SFG04] Christoph Strecha, Rik Fransens, and Luc J. Van Gool. Wide-baseline stereo from multiple views: A probabilistic account. In CVPR (1)’04, pages 552–559, 2004. [SLByS05] Jian Sun, Yin Li, Sing Bing, and Kang Heung yeung Shum. Symmetric stereo matching for occlusion handling. In In CVPR, pages 399–406, 2005. [Smi09] Brandon M Smith. Stereo matching with nonparametric smoothness priors in feature space. IEEE Conference on Computer Vision and Pattern Recognition (2009), 0:485–492, 2009. [SSZ01] 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. IEEE Computer Society. [SySnZ03] Jian Sun, Heung yeung Shum, and Nan ning Zheng. Stereo matching using belief propagation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25:787–800, 2003. [SZS+08] Richard Szeliski, Ramin Zabih, Daniel Scharstein, Olga Veksler, Vladimir Kolmogorov, Aseem Agarwala, Marshall Tappen, and Carsten Rother. A comparative study of energy minimization methods for markov random fields with smoothness-based priors. IEEE Trans. Pattern Anal. Mach. Intell., 30:1068–1080, June 2008. [WS11] Liang Wang and Rose Street. Global stereo matching leveraged by sparse ground control points. Optimization, 2011. [WTRF09] Oliver Woodford, Philip Torr, Ian Reid, and Andrew Fitzgibbon. Global stereo reconstruction under second-order smoothness priors. IEEE Trans. Pattern Anal. Mach. Intell., 31:2115–2128, December 2009. [YWY+06] Q. Yang, L. Wang, R. Yang, H. Stew’enius, and D. Nist’er. Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling. In CVPR (2), pages 2347–2354, 2006. [ZJWB08] Guofeng Zhang, Jiaya Jia, Tien-Tsin Wong, and Hujun Bao. Recovering consistent video depth maps via bundle optimization. In CVPR’08, 2008. [ZK07] C. Lawrence Zitnick and Sing Bing Kang. Stereo for image-based rendering using image over-segmentation. International Journal of Computer Vision, 75:49–65, 2007. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/41542 | - |
dc.description.abstract | 在本篇論文中,我們提出了一個創新的多視角圖片對應技術。
首 先 , 我 們 使 用 尺 度 不 變 特 徵 轉 換(Scale-invariant feature transform 或 SIFT)在圖片之間取得初始的稀疏對應點。然後利用我們所提出的以特徵點為基礎之圖片區塊分割方法(feature graph-based image segmentation),找到更多的特徵點,並且改善特徵點之間的對應結果。 為了去除位於物體邊緣附近錯誤對應的特徵點,我們將特徵點作分群,並且在最小生成樹(minimum spanning tree 或 MST)建立過程中,對每個特徵點群集做切割,藉以找到錯誤對應的特徵點。最後,我們傳遞那些稀疏特徵點對應而得的視差值(disparity)給其他未找到適當對應的像素,產生視差值圖(disparity maps)。在視差值傳遞的過程中,我們會藉由以特徵點為基礎,在最小生成樹上面的區塊擴張(feature-based region growing on MST),決定每個像素的鄰近特徵點。我們提出的對應技術可以廣泛用於不同種類的場景,而且幾乎沒有需要使用者調整或設定的參數。我們拿 Middlebury 網站上的測試資料去評估演算法的準確率, 測試結果顯示平均的錯誤像素比例大約在百分之十。 | zh_TW |
dc.description.abstract | In this paper, we propose a robust method for stereo matching. First,we use SIFT matching to generate initial sparse correspondence between images, and then use our feature graph-based image segmentation to discover more features and refine feature matching iteratively. To find outliers near objects’ boundary, we cluster the features into groups, and divide each feature group with minimum spanning tree construction. Finally, we generate disparity maps by propagating the disparity values of those sparse features to other near-by unmatched pixels. In the propagation process, we will determine each pixel’s neighbouring features via the feature-based region growing
on the minimum spanning tree. It contains two stages: (1) local feature disparity selection and (2) global propagation using energy minimization. Our method can be applied to a wide variety of cases, only few parameters need to be adjusted or specified. We evaluate our algorithm using the cases in the website Middlebury[SSZ01], and the results show that the average of bad pixels is about 10%. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T00:22:23Z (GMT). No. of bitstreams: 1 ntu-100-R98921035-1.pdf: 4092928 bytes, checksum: 4f13e02db7e1680a2f81dcda67e77a39 (MD5) Previous issue date: 2011 | en |
dc.description.tableofcontents | 口試委員會審定書 i
致謝 ii 中文摘要 iii Abstract iv 1 Introduction 1 1.1 contributions . . . . . . . . . . . 3 1.2 overview . . . . . . . . . . . . . 3 2 Related Work 5 3 Feature Graph 8 3.1 Feature Matching Initialization . . . . . 9 3.2 Feature Graph-based Image Segmentation . . . 9 3.2.1 Feature-based Region Growing . . . . . 9 3.2.2 Additional Matching Constraints . . . . 11 3.3 Robust Refining Process . . . . . . . . 12 3.4 Coarse-to-fine Consistent Image Segmentation . . .14 4 Object Boundary Process 18 4.1 Feature Clustering . . . . . . . . . . . 20 4.1.1 Feature group initialization . . . . . . . 20 4.1.2 Boundary Dilation . . . . . . . . . . 20 4.2 Feature Group Separation . . . . . . . . . 23 4.2.1 Minimum Spanning Tree Construction . . . . . 23 4.2.2 Feature Outlier . . . . . . . . . . . 24 5 Feature Disparity Propagation 26 5.1 Pixel-wise Local Disparity Selection . . . . .28 5.2 Global Propagation . . . . . . . . . . .31 5.2.1 Energy Model . . . . . . . . . . . .32 5.2.2 Loopy Belief Propagation . . . . . . . .32 5.2.3 Energy Minimization . . . . . . . . . . 33 5.3 Optimal Disparity Maps . . . . . . . . . 34 6 Results and Conclusion 35 6.1 Results and Discussion . . . . . . . . . 35 6.1.1 Results on the Benchmark . . . . . . . . 35 6.1.2 Visual Quality Comparison . . . . . . . . 37 6.1.3 Results for other cases . . . . . . . . 42 6.2 Complexity Analysis . . . . . . . . . . 42 6.2.1 Complexity of Sparse Correspondence Construction 43 6.2.2 Complexity of Object Boundary Process . . . . 44 6.2.3 Complexity of Disparity Propagation . . . . 44 6.3 Experiment about Microsoft Kinect . . . . . 45 6.4 Conclusions . . . . . . . . . . . . . 45 Bibliography 46 | |
dc.language.iso | zh-TW | |
dc.title | 以特徵點圖形為基礎的影像切割及視差值傳遞之多視角對應方法 | zh_TW |
dc.title | Feature-graph Based Image Segmentation and Disparity
Propagation in Stereo Matching | en |
dc.type | Thesis | |
dc.date.schoolyear | 99-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 鄭士康(Shyh-Kang Jeng) | |
dc.contributor.oralexamcommittee | 陳維超(Wei-Chao Chen),張鈞法(Chun-Fa Chang) | |
dc.subject.keyword | 特徵點圖形,特徵點群集,視差值傳遞, | zh_TW |
dc.subject.keyword | feature graph,feature group,disparity propagation, | en |
dc.relation.page | 49 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2011-08-15 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
顯示於系所單位: | 電機工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-100-1.pdf 目前未授權公開取用 | 4 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。