臺灣博碩士論文加值系統

此篇論文提出將多張影像盡可能自然拼接之方法，我們的方法是將影像鋪格子後使用局部的變形模型，而目標函式被設計成可用來決定變形模型的特性，像是影像對齊及最小化變形程度，除此之外，我們增加各影像之全局相似轉換的猜測至目標函式中，此猜測限制各影像之變形，使得各影像在整體上盡可能保留猜測之相似轉換，關於全局相似轉換的猜測對於拼接結果的自然度有至關重要的影響，我們提出一些方法選擇關於相似轉換中的縮放及旋轉之猜測。所有影像的變形模型將求解於最小化所有影像的整體變形，根據各個拼接結果顯示我們的方法皆優於目前幾項最先進的方法，包含 AutoStitch、APAP、SPHP 及 ANNAP。

This thesis proposes a method for stitching multiple images together so that the stitched image looks as natural as possible. Our method adopts the local warp model and guides the warping of each image with a grid mesh. An objective function is designed for specifying the desired characteristics of the warps. In addition to good alignment and minimal local distortion, we add a global similarity prior in the objective function. This prior constrains the warp of each image so that it resembles a similarity transformation as a whole. The selection of the similarity transformation is crucial to the naturalness of the results. We propose methods for selecting the proper scale and rotation for an image. The warps of all images are solved together for minimizing the distortion globally. A comprehensive evaluation shows that the proposed method consistently outperforms several state-of-the-art methods, including AutoStitch, APAP, SPHP and ANNAP.

Contents
誌謝 .................... i
摘要 .................... ii
Abstract .................... iii
1 Introduction .................... 1
2 Related work .................... 5
3 Method .................... 7
3.1 Matching point generation by APAP .................... 8
3.2 Stitching by mesh deformation .................... 8
4 Scale and rotation selection .................... 12
4.1 Estimation of the focal length and 3D rotation .................... 12
4.2 Rotation selection .................... 13
4.2.1 Rotation selection (2D method) .................... 15
4.2.2 Rotation selection (3D method) .................... 15
5 Experiments and results .................... 17
6 Conclusions .................... 22
A Finding Images with Zero Rotation .................... 23
B All comparisons .................... 25
Bibliography .................... 68

[1] M. Brown and D. G. Lowe. Recognising panoramas. In Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2, ICCV ’03, pages 1218–, Washington, DC, USA, 2003. IEEE Computer Society.
[2] M. Brown and D. G. Lowe. Automatic panoramic image stitching using invariant features. Int. J. Comput. Vision, 74(1):59–73, Aug. 2007.
[3] R. Carroll, M. Agrawal, and A. Agarwala. Optimizing content-preserving projections for wide-angle images. ACM Transactions on Graphics, 28(3):43, 2009.
[4] C.-H. Chang, Y. Sato, and Y.-Y. Chuang. Shape-preserving half-projective warps for image stitching. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR ’14, pages 3254–3261, Washington, DC, USA, 2014. IEEE Computer Society.
[5] J. Gao, S. J. Kim, and M. S. Brown. Constructing image panoramas using dual-homography warping. In Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR ’11, pages 49–56, Washington, DC, USA, 2011. IEEE Computer Society.
[6] R. Grompone von Gioi, J. Jakubowicz, J.-M. Morel, and G. Randall. LSD: a Line Segment Detector. Image Processing On Line, 2:35–55, 2012.
[7] T. Igarashi and Y. Igarashi. Implementing as-rigid-as-possible shape manipulation and surface flattening. J. Graphics, GPU, & Game Tools, 14(1):17–30, 2009.
[8] J. Kopf, D. Lischinski, O. Deussen, D. Cohen-Or, and M. Cohen. Locally adapted projections to reduce panorama distortions. Computer Graphics Forum, 28(4):1083– 1089, 2009.
[9] J. Lezama, R. Grompone von Gioi, G. Randall, and J.-M. Morel. Finding vanishing points via point alignments in image primal and dual domains. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2014.
[10] C. Lin, S. Pankanti, K. N. Ramamurthy, and A. Y. Aravkin. Adaptive as-natural-as-possible image stitching. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7-12, 2015, pages 1155–1163, 2015.
[11] W.-Y. Lin, S. Liu, Y. Matsushita, T.-T. Ng, and L.-F. Cheong. Smoothly varying affine stitching. In Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR ’11, pages 345–352, Washington, DC, USA, 2011. IEEE Computer Society.
[12] D. Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60:91–110, 2004.
[13] Y. Nomura, L. Zhang, and S. K. Nayar. Scene collages and flexible camera arrays. In Proceedings of the 18th Eurographics Conference on Rendering Techniques, EGSR’07, pages 127–138, Aire-la-Ville, Switzerland, Switzerland, 2007. Eurographics Association.
[14] H.-Y. Shum and R. Szeliski. Panoramic image mosaics. Technical Report MSR-TR-97-23, Microsoft Research, September 1997.
[15] R. Szeliski. Image alignment and stitching: A tutorial. Found. Trends. Comput. Graph. Vis., 2(1):1–104, Jan. 2006.
[16] R. Szeliski and H.-Y. Shum. Creating full view panoramic image mosaics and environment maps. In Proceedings of the 24th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH ’97, pages 251–258, New York, NY, USA, 1997. ACM Press/Addison-Wesley Publishing Co.
[17] A. Vedaldi and B. Fulkerson. Vlfeat: An open and portable library of computer vision algorithms. In Proceedings of the 18th ACM International Conference on Multimedia, MM ’10, pages 1469–1472, New York, NY, USA, 2010. ACM.
[18] J. Zaragoza, T.-J. Chin, M. S. Brown, and D. Suter. As-projective-as-possible image stitching with moving dlt. In Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, CVPR ’13, pages 2339–2346, Washington, DC, USA, 2013. IEEE Computer Society.
[19] L. Zelnik-Manor, G. Peters, and P. Perona. Squaring the circle in panoramas. In Proceedings of ICCV 2005, volume 2, pages 1292–1299, 2005.