影像校準是指幾何上對齊兩張影像，是許多應用的前處理，包含影像融合、變化偵測、影像拼接等。本論文主要處理兩張不同視角所拍攝相同場景之影像，此類影像在校準時容易因為局部失真而導致影像變形，因此提出一個有效的影像校準方法來解決此問題。首先，我們針對多視角影像使用二維投影轉換來描述影像之間的坐標點關係。其次，利用特徵匹配的方法來計算全域轉換的參數，透過使用加速穩健特徵來減少執行時間及記憶體負擔，並改良隨機抽樣一致性演算法快速地估算出轉換參數。最後，為了改善局部失真的問題，我們提出一種自適應切割架構，將影像分割成適當大小的區塊，並使用最小平方匹配對每一個區塊做局部參數微調。由實驗結果可以清楚地看到，我們所提出的演算法有較高的對齊精度，並能修復局部失真所造成的誤差。

Image registration geometrically aligns two images and it is a pre-process for many applications such as image fusion, change detection and image stitching. In this thesis, an efficient image registration method is proposed to register two images which are taken at different viewpoints and correct the misalignment caused by local geometric distortion. In order to register multiview images, a 2D projective transformation is used to describe the relation between two coordinates. A feature-based method is used to estimate the global transform model. SURF is used to speed up and save memory, and the modified RANSAC is proposed to quickly and accurately estimate transformation parameters. Furthermore, the adaptive partition framework is designed to correct local distortion. It divides image to properly blocks and least square matching is used to refine local parameters for each block. Experimental results show that the proposed method has high accuracy and can deal with local misalignment caused by geometric distortion.

[1]B. Zitova, J. Flusser, “Image registration methods: A survey”, Image Vis. Comput., vol. 21, no. 11, pp. 977-1000, Oct. 2003.
[2]A. Ardeshir Goshtasby, “Image Registration: Principles, Tools and Methods”, New York, NY, USA:Springer-Verlag, 2012.
[3]H. Gonçalves, L. Corte-Real, J. A. Gonçalves, “Automatic image registration through image segmentation and SIFT”, IEEE Trans. Geosci. Remote Sens., vol. 49, no. 7, pp. 2589-2600, Jul. 2011.
[4]M. Gong, S. Zhao, L. Jiao, D. Tian, S. Wang, “A novel coarse-to-fine scheme for automatic image registration based on sift and mutual information”, IEEE Trans. Geosci. Remote Sens., vol. 52, no. 7, pp. 4328-4338, Jul. 2014.
[5]M.E. Linger and A.A. Goshtasby, “Aerial image registration for tracking”, IEEE Trans. Geosci. Remote Sens., vol.53, no.4, pp. 2137-2145, 2015.
[6]Y. Huachao, Z. Shubi, W. Yongbo, “Robust and precise registration of oblique images based on scale-invariant feature transformation algorithm”, IEEE Geosci. Remote Sens. Lett., vol. 9, no. 4, pp. 783-787, Jul. 2013.
[7]Y. Han, J. Choi, Y. Byun, Y. Kim, “Parameter optimization for the extraction of matching points between high-resolution multisensor images in urban areas”, IEEE Trans. Geosci. Remote Sens., vol. 52, no. 9, Sep. 2014.
[8]C. Harris, M. Stephens, “A combined corner and edge detector”, Proceedings of the 4th Alvey Vision Conference, pp. 147-151, 1988.
[9]D. G. Lowe, “Distinctive image features from scale-invariant keypoints”, Int. J. Comput. Vis., vol. 60, no. 2, pp. 91-110, 2004.
[10]H. Bay, A. Ess, T. Tuytelaars, L. Van Gool, “SURF: Speeded up robust features”, Comput. Vis. Image Understand., vol. 110, no. 3, pp. 346-359, 2008.
[11]M. A. Fischler, R. C. Bolles, “Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography”, Commun. ACM, vol. 24, no. 6, pp. 381-395, Jun. 1981.
[12]F. Ackermann, “Digital image correlation: performance and potential application in photogrammetry”, The Photogrammetric Record, vol.11, no.64, pp. 429-439, 1984.
[13]M Muja, DG Lowe, “Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration”, VISAPP, 2009.
[14]Z. Liu, J. An and Y. Jing, “A simple and robust feature point matching algorithm based on restricted spatial order constraints for aerial image registration”, IEEE Trans. Geosci. Remote Sens., vol. 50, no. 2, pp. 514-527, Feb., 2012.
[15]K. Zhang, X. Li and J. Zhang, “A robust point-matching algorithm for remote sensing image registration”, IEEE Geosci. Remote Sens. Lett., vol. 11, no. 2, pp. 469-473, Feb., 2014.
[16]Z. Song, S. Zhou and J. Guan, “A novel image registration algorithm for remote sensing under affine transformation”, IEEE Trans. Geosci. Remote Sens., vol. 52, no. 8, pp. 4895-4912, Aug., 2014.
[17]Y. Wu, W. Ma, M. Gong, L. Su and L. Jiao, “A novel point-matching algorithm based on fast sample consensus for image registration”, IEEE Geosci. Remote Sens. Lett., vol. 12, no. 1, pp. 43-47, Jan., 2015.
[18]J. Ma, H. Zhou, J. Zhao, Y. Gao, J. Jiang and J. Tian, “Robust feature matching for remote sensing image registration via locally linear transforming”, IEEE Trans. Geosci. Remote Sens., vol. 53, no. 12, pp. 6469-6481, Dec., 2015.
[19]J. Jiang, X. Shi, “A robust point-matching algorithm based on integrated spatial structure constraint for remote sensing image registration”, IEEE Geosci. Remote Sens. Lett., vol. 13, no. 11, pp. 1716-1720, 2016.
[20]F. Meng, X. Li, J. Pei, “A feature point matching based on spatial order constraints bilateral-neighbor vote”, IEEE Transactions on Image Processing, vol. 24, no. 11, pp. 4160-4171, Nov 2015.
[21]R. Hartley, A. Zisserman, “Multiple view geometry in computer vision”, Cambridge, U.K.:Cambridge Univ. Press, 2003.
[22]B. P. Jackson, A. A. Goshtasby, “Registering aerial video images using the projective constraint”, IEEE Trans. Image Process., vol. 19, no. 3, pp. 795-804, Mar. 2010.
[23]B. Li, H. Ye, “RSCJ: Robust sample consensus judging algorithm for remote sensing image registration”, IEEE Geosci. Remote Sens. Lett., vol. 9, no. 4, pp. 574-578, Jul. 2012.
[24]K. Mikolajczyk, C. Schmid, “A performance evaluation of local descriptors”, IEEE Trans. Pattern Anal. Mach. Intell., 27 (10) (2005), pp. 1615-1630.