本篇論文探討如何經由相片集生成指定地點之全景影像。一般而言，欲產生高品質的全景影像必須使用拍攝自固定攝影點的相片以避免視差問題的產生。而本論文使用了搜尋自相片集並且靠近指定地點的相片接合成全景影像。由於在這些相片裡存在著視差問題，輸出影像將會出現可視錯誤包括鬼影、斷層。為了降低這些錯誤並維持輸出影像的品質，此論文使用了多種最佳化方法。如最佳連接縫被尋找以移除鬼影與減少畫面上的斷層，多餘的影像被移除以降低影像黏貼的次數。這使得輸出影像的主要場景能被無縫地接合。

This paper discusses the approach for generating panoramic view at a query location from photo collections. The input images used to generate panoramic image have to be taken at the position near to the canonical position to avoid parallax to output a high quality image in previous works. The photos which are near to user query location are searched from geotagged photo collections and stitched into panoramic view using bundle adjustment in this work. Due to big parallax exists in the input images, some visible errors which include ghostings and visible seams could appear in the output images. Several optimizations are applied to reduce these errors to keep the quality of the output images. To remove ghostings and reduce visible seams, the optimal stitching seams are found. To reduce the cost bring by stitching seams, the redundant images are removed to reduce the times of stitchings. The main sceneries of the generated panoramic images can be stitched seamlessly after apply above optimizations.

[1] B. Lucas, T. Kanade et al., “An iterative image registration technique with
an application to stereo vision,” in International joint conference on artificial
intelligence, vol. 3. Citeseer, 1981, pp. 674–679.
[2] P. Anandan, “A computational framework and an algorithm for the
measurement of visual motion,” International Journal of Computer Vision,
vol. 2, pp. 283–310, 1989, 10.1007/BF00158167. [Online]. Available:
http://dx.doi.org/10.1007/BF00158167
[3] R. Szeliski and H.-Y. Shum, “Creating full view panoramic image mosaics and
environment maps,” in SIGGRAPH ’97: Proceedings of the 24th annual conference
on Computer graphics and interactive techniques. New York, NY, USA:
ACM Press/Addison-Wesley Publishing Co., 1997, pp. 251–258.
[4] S. Baker and I. Matthews, “Lucas-kanade 20 years on: A unifying framework,”
International Journal of Computer Vision, vol. 56, no. 3, pp. 221–255, 2004.
[5] M. Brown and D. G. Lowe, “Automatic panoramic image stitching using invariant
features,” Int. J. Comput. Vision, vol. 74, no. 1, pp. 59–73, 2007.
[6] ——, “Recognising panoramas,” in ICCV ’03: Proceedings of the Ninth IEEE
International Conference on Computer Vision. Washington, DC, USA: IEEE
Computer Society, 2003, p. 1218.
[7] M. Brown, R. I. Hartley, and D. Nister, “Minimal solutions for panoramic
stitching,” Computer Vision and Pattern Recognition, IEEE Computer Society
Conference on, vol. 0, pp. 1–8, 2007.
[8] Y. Li, Y. Wang, W. Huang, and Z. Zhang, “Automatic image stitching using
sift,” in International Conference on Audio, Language and Image Processing,
2008. ICALIP 2008, 2008, pp. 568–571.
[9] H. Jin, “A three-point minimal solution for panoramic stitching with lens distortion,”
Computer Vision and Pattern Recognition, IEEE Computer Society
Conference on, vol. 0, pp. 1–8, 2008.
[10] T. Quack, B. Leibe, and L. Van Gool, “World-scale mining of objects and events
from community photo collections,” in Proceedings of the 2008 international
conference on Content-based image and video retrieval. ACM, 2008, pp. 47–
56.
[11] C.-C. Hsieh, W.-H. Cheng, C.-H. Chang, Y.-Y. Chuang, and J.-L. Wu, “Photo
navigator,” in MM ’08: Proceeding of the 16th ACM international conference
on Multimedia. New York, NY, USA: ACM, 2008, pp. 419–428.
[12] N. Snavely, S. M. Seitz, and R. Szeliski, “Photo tourism: Exploring photo
collections in 3d,” in ACM TRANSACTIONS ON GRAPHICS. Press, 2006,
pp. 835–846.
[13] N. Snavely, R. Garg, S. M. Seitz, and R. Szeliski, “Finding paths through the
world’s photos,” ACM Trans. Graph., vol. 27, no. 3, pp. 1–11, 2008.
[14] R. Szeliski, “Image alignment and stitching: a tutorial,” Found. Trends. Comput.
Graph. Vis., vol. 2, no. 1, pp. 1–104, 2006.
[15] R. Szeliski and S. B. Kang, “Direct methods for visual scene reconstruction,”
in Representation of Visual Scenes, 1995. (In Conjuction with ICCV’95), Proceedings
IEEE Workshop on, 24 1995, pp. 26 –33.
[16] M. Irani and P. Anandan, “About direct methods,” Vision Algorithms: Theory
and Practice, pp. 267–277, 2000.
[17] H.-Y. Shum and R. Szeliski, “Construction of panoramic image mosaics
with global and local alignment,” International Journal of Computer Vision,
vol. 48, pp. 151–152, 2002, 10.1023/A:1016051024520. [Online]. Available:
http://dx.doi.org/10.1023/A:1016051024520
[18] S. Suen, E. Lam, and K. Wong, “Photographic stitching with optimized object
and color matching based on image derivatives,” Opt. Express, vol. 15, pp.
7689–7696, 2007.
[19] R. I. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision,
2nd ed. Cambridge University Press, ISBN: 0521540518, 2004.
[20] B. Cyganek and J. Siebert, An Introduction to 3D Computer Vision Techniques
and Algorithms. Wiley, 2009.
[21] C. Wöhler, 3D Computer Vision: Efficient Methods and Applications. Springer-
Verlag New York Inc, 2009.
[22] D. Koks, Explorations in mathematical physics: the concepts behind an elegant
language. Springer Verlag, 2006.
[23] H. Bay, T. Tuytelaars, and L. V. Gool, “Surf: Speeded up robust features,” in
In ECCV, 2006, pp. 404–417.
[24] J. Morel and G. Yu, “Asift: A new framework for fully affine invariant image
comparison,” SIAM Journal on Imaging Sciences, vol. 2, no. 2, pp. 438–469,
2009.
[25] D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International
Journal of Computer Vision, vol. 60, pp. 91–110, 2004.
[26] L. Juan and O. Gwun, “A comparison of sift, pca-sift and surf,” International
Journal of Image Processing (IJIP), vol. 3, no. 5, 2010.
[27] T. Lindeberg, “Scale-space theory: A basic tool for analysing structures at
different scales,” Journal of Applied Statistics, pp. 224–270, 1994.
[28] M. De Berg, O. Cheong, M. Van Kreveld, and M. Overmars, Computational
geometry: algorithms and applications. Springer-Verlag New York Inc, 2008.
[29] B. Triggs, P. McLauchlan, R. Hartley, and A. Fitzgibbon, “Bundle adjustment
- a modern synthesis,” Vision algorithms: theory and practice, pp. 153–177,
2000.
[30] J. Nocedal and S. J. Wright, Numerical Optimization, 2nd ed. Springer, 2006,
ch. 4,5,6,7.
[31] A. Mills and G. Dudek, “Image stitching with dynamic elements,” Image
and Vision Computing, vol. 27, no. 10, pp. 1593 – 1602, 2009, special
Section: Computer Vision Methods for Ambient Intelligence. [Online].
Available: http://www.sciencedirect.com/science/article/B6V09-4VXB8T3-2/
2/0370bc1e6100c30c5f72a1980c23a699
[32] T. Cormen, Introduction to algorithms, 2001.
[33] Panoramio. [Online]. Available: http://www.panoramio.com/