標題: | 粒子群演算法於圖形偵測與震測圖形識別之應用 Particle Swarm Optimization for Pattern Detection and Seismic Applications |
作者: | 董安晉 An-Ching Tung 黃國源 Kuo-Yuan Huang 多媒體工程研究所 |
關鍵字: | 粒子群演算法;霍夫演算法;震測圖形;Particle swarm optimization;Hough transform;seismic pattern |
公開日期: | 2006 |
摘要: | 我們採用一種以粒子群演算法Particle Swarm Optimization (PSO) 為基礎的方法,用來偵測一張影像上的參數圖形 (如:圓、橢圓、雙曲線與雙曲線的漸近線) 的參數。我們定義了一個表示式來代表參數圖形,其中包含了平移及旋轉,並且定義了點到圖形的距離。我們用一個粒子來表示全部要偵測的參數圖形的參數,使用PSO在參數空間中尋找最佳的一個粒子,使影像空間上的所有影像點到此參數所代表的圖形的距離和為最小。我們先將PSO演算法應用於模擬的影像資料上,偵測模擬影像之後,再將之應用於偵測模擬的與真實的單炸點震測圖形上,偵測直接波圖形 (直線) 與反射波圖形 (雙曲線) ,對於瞭解地層特性及後續的研究有很大的幫助。 Particle Swarm Optimization (PSO) is adopted to detect parameter pattern (e.g. circle, ellipse, hyperbola and asymptote.) Each particle is represented as parameters of patterns, then swarm of particles search the optimal solution in parameter space. We define mathematical formulas to represent various kinds of parameter patterns, and define the distance from points to patterns. Experiments on simulated image get good detection. The method is also applied to detect the parameters of direct wave (line) and reflected wave pattern (hyperbola) in simulated and real one-shot seismogram, the results can improve seismic interpretation and further seismic data processing. |
URI: | http://140.113.39.130/cdrfb3/record/nctu/#GT009457528 http://hdl.handle.net/11536/82250 |
Appears in Collections: | Thesis |
Files in This Item:
If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.