隨著科技的進步與衛星的多元化，影像套合在遙感探測領域中的影像處理方面是一個非常基本的應用，並且重要性不斷提高，後續應用包括了影像融合、變遷偵測以及影像鑲嵌等方面。因此，本論文將利用尺度不變特徵轉換、Canny特徵萃取、最小二乘匹配法等技術，進行不同遙測影像成功匹配與套合方法之研究。 首先利用人工點選或是利用尺度不變特徵轉換運算元的方式，尋找主影像與附屬影像之間的初始對應關係，接著分別利用Canny運算元萃取兩張影像的邊緣，並且利用邊界盒清理較破碎的邊緣後，利用成本函數進行邊緣點匹配。接著以匹配成功的初始共軛點為中心開?影像窗，進行影像分塊與輻射參數校正的步驟，主影像窗與校正後之附屬影像窗以最小二乘匹配法進行進一步的定位。最後將所有共軛點對利用薄板樣條法，並結合粗差濾除與方差分量估計建立套合影像。實驗結果顯示利用此方法可成功套合不同的資源衛星影像。 Image registration is a key issue in many image processing applications in remote sensing. Examples of these applications include change detection using multiple images acquired at different times, and fusion of image data from multiple sensor types. SIFT (Scale Invariant Feature Transform), Canny edge detector and Least-squares matching method are proposed in this research. At first, the initial matching point pairs are detected from manual adjustment or the SIFT algorithm, which is invariant to image scale and rotation. And then, edges in both images are located by using the Canny algorithm and petty contours are cleaned by a bounding-box. Furthermore, more matching point pairs are selected using a cost function that measures the gradient orientation and distance between all possible pairs of the points. Pairing image windows are built and segmented to get radiometric parameters, and the radiometric parameters are used here to modulate the slave image window. Finally, master image window and modulated slave image window are matched by least-squares matching, and control points are found. The Thin-Plate Splines (TPS) method is used to register master and slave images. Experimental results show that numerous matching points can be obtained correctly and automatically, and different satellite images can be registered precisely.
