中文摘要 |
現今台灣地區使用的坐標系統有許多種,在這當中最廣泛使用的為TWD67與TWD97坐標系統。由於不同時期建置的地籍資料使用不同的坐標系統,因此常需要在兩種坐標系統間進行坐標轉換。目前,國內正積極將地籍資料由TWD67坐標系統轉換為TWD97坐標系統。而如何在TWD67與TWD97坐標系統之間進行坐標轉換,整合不同坐標系統間資料之聯繫與共享,一直是國內學者致力於研究的問題。在廣泛的討論當中,最常使用的方式為利用最小二乘法四、六參數法,求解轉換參數。近年來,由於神經網路技術快速的發展,提供了我們在進行地籍資料坐標轉換研究時新的選擇。本研究目的,在於嘗試利用神經網路方式進行地籍資料TWD67與TWD97坐標轉換;同時為了提升神經網路的應用,本研究提出利用神經網路,建立網格式地籍資料TWD67與TWD97坐標轉換模式的方法。利用台灣地區與台中市地區等兩個實驗區的共同點資料,以不同方式進行坐標系統轉換。有關神經網路地籍資料坐標轉換方法、網格式地籍資料坐標轉換模式建立方法,以及相關的實驗結果將於文中介紹。
Currently, there are many coordinate systems used in Taiwan; among the most widely used systems are TWD67 (Taiwan Datum 1967) and TWD97 (Taiwan Datum 1997). Frequently it is necessary to transform from one coordinate system to another. One of the most common methods is the least-squares with affine transformations. The artificial neural network (ANN) provides a new technology for coordinate transformations of cadastral data. The popularity of this methodology is rapidly growing. In this research, coordinate transformations between TWD67 and TWD97 with the artificial neural network (ANN) and the least-squares with affine transformations were examined. Besides, algorithms of applying the artificial neural network to develop a regional grid-based coordinate transformation model were proposed. Two data sets with varied sizes from the Taiwan region were used to test the proposed algorithms. The test results show that the coordinate transformation accuracies using the ANN models are better than those of using other methods, such as, the least-Squares with affine transformations. |