影像套合(Image Registration)在遙測領域上是一門重要技術，為了達到良好的套合品質以及自動化目標，而在控制點選取及匹配就顯得格外重要，其影像套合所需之控制點(CPs)宜符合三要素：數量多、正確性高以及分佈均勻等條件。
　　本研究使用QuickBird衛星影像為主影像以及航測影像在不同時期下分為兩組進行影像套合，運用不同演算法作特徵提取得到的特徵點，進行特徵匹配獲得兩張影像間共軛點位置，包括當影像具有尺度縮放、旋轉、仿射變形以及亮度變化時，仍相當穩定的SIFT演算法，和基於SIFT演算法進行模擬條件達到完全仿射不變之ASIFT演算法，以及在區域特徵上具有物理意義之MSER演算法，將兩張影像獲得之特徵點，採用K-d tree或BBF特徵匹配方法獲得共軛點為影像套合之控制點位置。
　　實驗過程得知在無影像前處理作業時，SIFT、MSER所提取的特徵點經特徵匹配產生共軛點數量甚少，因此本實驗嘗試使用影像前處理方法(直方圖指定、對比度擴展、尺度縮放)，來探討藉由改善影像的顯示品質或大小是否有利於遙感影像之特徵提取及匹配，實驗證明採用尺度縮放之影像前處理方法有助於各演算法特徵提取產生的共軛點，在正確數量以及正確率的提升；在分佈均勻條件上，本研究運用影像裁剪(Image Cropping)方法個別進行特徵提取與匹配，實驗證明可獲取更多共軛點數量，達到均勻分佈之目標。

Image Registration plays a very important role in the field of remote sensing. In order to have a better registration quality and make the automatization possible, choos ing and matching the control points from conjugate images become very important. In fact, the control points required for image registration should have following three key factors, that is, the amount, validity and distribution of control points.
　　In the study, we take QuickBird Satellite Images as the main ones; on the other hand, it conducts two groups of image registrations resulted from aerial images at various times. After detecting feature points using different algorithms, the study makes use of feature matching methods to get conjugate points between two overlapped images. The algorithms used above are SIFT, ASIFT and MESR. SIFT is an algorithm which invariant to scales, rotation, affine stretch and change in brightness. ASIFT undertakes simulations based on the theory of SIFT and thus carries out fully affine invariant. The feature points obtained from MSER have physical meaning in its location. By using feature matching algorithms like K-d tree and BBF, the matched feature points from two overlapped images would be turned into the conjugate points which can be control points for image registration.
　　During the process of image preprocessing, it is learned that the feature points detected by SIFT and MSER through feature matching are very few. Hence, this study attempts to employ histogram specification、contrast stretching and scale change methods to see if it is helpful to the feature detections and matching through change of image quality and image size. The experiment found that scale change will improve both the amount and accuracy of conjugate points detected by different algorithms. When considering distribution of the feature points, the study takes advantage of image cropping approach to conduct feature detections and matching individually. It is found that more conjugate points with uniform distribution can be obtained via image cropping technique.

目錄
摘要 I
ABSTRACT II
誌謝 IV
目錄 V
圖目錄 VIII
第一章 緒論 1
1-1 研究動機與目的 1
1-2 文獻回顧 1
1-3 研究構想與流程 5
第二章 特徵匹配之理論基礎 7
2-1 SIFT演算法之基礎理論 7
2-1-1 尺度空間之極值求取 7
2-1-2 特徵點位置最佳化 10
2-1-3 特徵點梯度方向確定 12
2-1-4 特徵描述 13
2-2 ASIFT演算法之基礎理論 14
2-2-1 仿射相機模式(Affine Camera Model) 14
2-2-2 轉態傾斜(Transition Tilts) 16
2-2-3 縱向角(latitude angle)及橫向角(longitude angle)之參數採樣 18
2-2-4 多分辨率(Multi-resolution)之策略 19
2-2-5 ASIFT之運算效率 21
2-2-6 小結 21
2-3 MSER演算法之基礎理論 23
2-3-1 MSER之分水嶺(Watershed)概念 23
2-3-2 MSER之相關定義 24
2-3-3 MSER偵測方法 26
2-3-4 MSER之區域擬合與正規化 28
2-3-5 小結 30
2-4 演算法之特性比較 31
2-5 特徵匹配方法 32
2-6 特徵點除錯機制 33
2-6-1 隨機抽樣一致性算法(RANSAC) 33
第三章 實驗成果與討論 36
3-1 實驗區資訊 36
3-2 實驗流程 39
3-3 影像前處理 42
3-3-1 直方圖指定(Histogram specification) 42
3-3-2 對比度擴展(Contrast Stretching) 45
3-3-3 尺度縮放(Scale change) 48
3-3-4 影像裁剪(Image Cropping) 50
3-4 特徵提取與特徵匹配成果比較 51
3-4-1 特徵描述之比較 51
3-4-2 特徵匹配成果之比較 52
3-4-3 特徵匹配之位置比較 54
3-5 MSER參數之設定 55
3-6 實驗數據結果與分析 63
3-6-1 特徵匹配之共軛點正確數量結果與分析 66
3-6-2 特徵匹配之共軛點正確性結果與分析 70
3-6-3 特徵匹配之共軛點分佈狀態結果與分析 73
3-6-4 特徵提取及匹配之運算時間結果與分析 77
第四章 結論與建議 78
4-1 結論 78
4-2 建議 80
參考文獻 81
附錄一 程式列表 85

[1] 王永明、王貴錦，圖像局部不變性特徵與描述，國防工業出版社，北京，2010。
[2] 孫樹國，應用不變量區域描述元進行影像之表示、比對及辨識，博士論文，國立交通大學資訊科學與工程研究所，2009。
[3] 張庭榮，SIFT演算法於立體對影像匹配與影像檢索應用之研究，碩士倫文，國立高雄應用科技大學土木工程與防災科技研究所，2008。
[4] 黃漢哲，SIFT演算法應用於航測影像拼接之研究，碩士論文，國立中山大學海洋環境及工程學研究所，2009。
[5] 劉銘哲，研究不同資源衛星影像之匹配與套合，碩士論文，國立中央大學土木工程研究所，2008。
[6] Arya, S. and Mount, D.M., Approximate nearest neighbor queries in fixed dimensions, In Fourth Annual ACM-SIAM Symposium on Discrete Algorithms (SODA’93), pp. 271-280, 1993.
[7] Arya, S. and Mount, D.M., Netanyahu N.S., Silverman R. and Wu A.Y., An optimal algorithm for approximate nearest neighbor searching, Journal of the ACM, 45:891-923., 1998.
[8] Beis, J. and Lowe, D.G., Shape indexing using approximate nearest-neighbour search in high-dimensional spaces. In Conference on Computer Vision and Pattern Recognition, Puerto Rico,pp. 1000-1006, 1997.
[9] Bentoutou, Y., Taleb, N., Kpalma, K., and Ronsin, J., An automatic image registration for applications in remote sensing, IEEE Transactions on Geoscience and Remote Sensing, Vol. 43, No. 9, pp. 2127-2137, 2005.
[10] Brown, L., A survey of image registration techniques, ACM Computer Survey, Vol.24 No.4, pp.325-376, 1992.
[11] Donoser, M. and Bischof, H., Efficient Maximally Stable Extremal Region (MSER) Tracking, CVPR, 2006.
[12] Friedman, J., Bentley, J.L. and Finkel R.A., An algorithm for finding best matches in logarithmic expected time, ACM Trans. Math. Software, 3:209–226, 1977.
[13] Forssen, P-E., Maximally Stable Colour Regions for Recognition and Matching, CVPR, 2007.
[14] Gonzalez, R C. and Woods, R E., Digital Image Processing 3rd Ed. (DIP/3e), Prentice Hall, 2008.
[15] Harris, C. and Stephens, M., A combined corner and edge detector, Proceedings of 4th Alvery vision conference, pp. 147-151, 1988.
[16] Hartley, R. and Zisserman, A., Multiple View Geometry in Computer Vision , Cambridge University Press, 2000.
[17] Heymann, S., Implementierung und Evaluierung von Video Feature Tracking auf moderner Grafik Hardware, Bauhaus Universität Weimar, 2005.
[18] Hu, M. K., Visual, Pattern Recognition by Moment Invariants, IRE Trans. Info. Theory, vol. 8, pp. 179-187, 1962.
[19] Karthik, K., Stuart, H. ,Wesley E. S. ,Halil C. ,Siamak K., A new feature based image registration algorithm,North Carolina State University, 2008.
[20] Lindeberg, T., Scale-space theory: A basic tool for analysing structures at different scales.Journal of Applied Statistics, 21(2):224-270., 1994.
[21] Lowe, D. G., Object recognition from local scale-invariant features, International Conference on Computer Vision, Corfu, Greece, pp. 1150-1157, 1999.
[22] Lowe, D. G., Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, pp. 91-110, 2004.
[23] Matas, J., Chum, O., Urban, M., and Pajdla, T., Robust wide baseline stereo from maximally stable extremal regions. In Proc. of British Machine Vision Conference, pages 384–396, 2002.
[24] Mikolajczyk, K., Detection of local features invariant to affine transformations, Ph.D. thesis, Institut National Polytechnique de Grenoble, France., 2002.
[25] Mikolajczyk, K. and Schmid, C., A performance evaluation of local descriptors, In Proceedings of Computer Vision and Pattern Recognition, 2003.
[26] Mikolajczyk, K., Tuytelaars, T., Schmid C., Zisserman A., Matas J., Schaffalitzky F., Kadir T. and Gool L.V., A Comparison of Affine Region Detectors, International Journal of Computer Vision, 2005.
[27] Moravec, H. P., Towards automatic visual obstacle avoidance, Proceedings of 5th International Joint Conference on Artificial Intelligence, pp. 584, 1977.
[28] Morel, J. M. and Yu, G., ASIFT: A New Framework for Fully Affine Invariant Image Comparison,SIAM Journal on Imaging Sciences, pp. 438-469, 2009.
[29] Morel, J. M. and Yu, G., A Fully Affine Invariant Image Comparison Method Acoustics, IEEE, pp. 1597–1600, 2009
[30] Murphy, C E and Trivedi, M., N-tree Disjoint-Set Forests for Maximally Stable Extremal Regions. BMVC, 2006.
[31] Teague, M., Image Analysis via the General Theory of Moments, Optical Society of America, 1980.
[32] Richards, John A. and Xiuping Jia, Remote Sensing Digital Image Analysis : An Introduction, 2006.
[33] Vincent, L. and Soille, P., Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(6):583–598, 1991.
[34] Zitova, B. and Flusser, J., Image registration methods: a survey, Image and Vision Computing, Vol. 21, No. 11, pp. 977-1000, 2003.