本篇論文是針對多圖像進行圖像縫合技術產生全景圖縫的圖像。使用了尺度不變特徵轉換取得一幅圖中的特徵點, 這些特徵點不只具有尺度不變形, 即使改變旋轉角度，圖像亮度或拍攝視角，仍然能夠得到好的檢測效果。比起使用傳統的對應點名為 Kd-Tree, 我們利用Hybrid Spill-Tree 的演算法尋找每張圖的對應點。對應圖像可用對應點來判斷。在我們系統，利用隨機抽樣一致方法和Bundle Adjustment方法找出對應圖像的最佳區城與全城對準。為了取得無縫圖像，系統使用多分辨率融合的方法。本系統針對無序的輸入圖像找出全景的圖像．本論文基於M. Brown and D. Lowe的論文。

This thesis concerns the problem of panoramic image stitching system, which has been widely used and applied on more areas in computer vision. This thesis we formulate stitching as image matching problem, and use invariant local features to find features which is insensitive to orientation, scale, zoom, and illumination of the input images. Instead of using a traditional feature matching called Kd-Tree, we are using Hybrid Spill-Tree as our feature matching algorithm in high-dimensional features. The local registration for each pair-wise image is calculated by RANSAC and the global registration for panorama is optimized by using Bundle Adjustment. For image stitching between image matching, we are using Multi-Band Blending to get a seamless panorama. This blending method is work well in many cases. This system can recognize a panorama from un-ordered input images. This thesis based on M. Brown and D. Lowe paper.

[1] H. Bay, T. Tuytelaars and L.V. Gool, “SURF: Speeded Up Robust Features,” Computer Vision–ECCV, pp. 404-417, 2006.
[2] J. Beis and D.G. Lowe, “Shape Indexing Using Approximate Nearest-Neighbour Search in High dimensional Spaces,” Computer Vision and Pattern Recognition, pp. 1000-1006, 1997.
[3] S. Brin, “Near Neighbor Search in Large Metric Spaces,” Conference on Very Large Data Bases, pp. 574-584, 1995.
[4] M. Brown, and D. Lowe, “Recognising Panoramas,” IEEE International Conference on Computer Vision, pp. 1218-1225, 2003.
[5] M. Brown and D.G. Lowe, “Automatic Panoramic Image Stitching using Invariant Features,” International Journal of Computer Vision, 74(1), pp. 59-73, 2007.
[6] M. Brown and D.G. Lowe, “Invariant Features from Interest Point Groups,” British Machine Vision Conference, pp. 656-665, 2002.
[7] P. Burt and E. Adelson, “A Multiresolution Spline with Application to Image Mosaics,” ACM Transactions on Graphics, pp. 217-236, 1983.
[8] P.J. Burt, “Fast Filter Transforms for Image Processing,” Computer Graphics Image Processing, pp. 20-51, 1981.
[9] P.J. Burt and E.H. Adelson, “The Laplacian Pyramid as a Compact Image Code,” IEEE Transaction on Communications, pp. 532-540, 1983.
[10] M. Fischler and R. Bolles, “Random Sample Consensus: A Paradigm for Model Fitting with Application to Image Analysis and Automated Cartography,” Communication of the ACM, pp. 381-395, 1981.
[11] J.H. Friedman, J.L. Bentley, and R.A. Finkel, “An Algorithm for Finding Best Matches in Logarithmic Expected Time,” ACM Transactions on Mathematical Software, pp. 209-226, 1977.
[12] A. Gionis, P. Indyk, and R. Motwani, “Similarity Search in High Dimensions via Hashing,” The VLDB Journal, pp. 518–529, 1999.
[13] C. Harris and M. Stephens, “A Combined Corner and Edge Detector,” Fourth Alvey Vision Conference, pp. 147-151, 1988.
[14] R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision. Cambridge University Press, 2004.
[15] L. Juan and O. Gwun, “A Comparison of SIFT, PCA-SIFT and SURF,” International Journal of Image Processing, pp. 143-152, 2009.
[16] Y. Ke and R. Sukthankar, “PCA-SIFT: A More Distinctive Representation for Local Image Descriptors”, Computer Vision and Pattern Recognition, pp. 511-517, 2004.
[17] T. Liu, A.W. Moore, A. Gray, and K. Yang, “An Investigation of Practical Approximate Nearest Neighbor Algorithms,” Advances in Neural Information Processing Systems, pp. 825-832, 2004.
[18] D. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” International Journal of Computer Vision, pp. 91-110, 2004.
[19] D.G. Lowe, “Object Recognition from Local Scale-Invariant Features.” Conference on Computer Vision, pp. 1150-1157, 1999.
[20] P.J. Rousseeuw and A.M. Leroy, Robust Regression and Outlier Detection, John Wiley & Sons, 2005.
[21] H.Y. Shum and R. Szeliski, “Panoramic Image Mosaicing,” International Journal of Engineering Research and Technology, 2013.
[22] R. Szeliski, “Image Alignment and Stitching: A Tutorial,” Foundations and Trends® in Computer Graphics and Vision, pp. 1-104, 2006.
[23] W. Triggs, P. McLauchlan, R. Hartley, and A. Fitzgibbon, “Bundle Adjustment: A Modern Synthesis,” Vision Algorithms: Theory and Practice, pp. 298–373, 2000.
[24] J.K. Uhlmann, “Satisfying General Proximity/Similarity Queries with Metric Trees,” Information Processing Letters, pp. 175-179, 1991.
[25] R. Zhang, http://blog.csdn.net/abcjennifer/article/details/7639681.