進階搜尋


下載電子全文  
系統識別號 U0026-3007201121135800
論文名稱(中文) 使用尺度不變特徵轉換進行空三影像之匹配策略設計
論文名稱(英文) Designing a Method of SIFT-based Matching of AT Images
校院名稱 成功大學
系所名稱(中) 測量及空間資訊學系碩博士班
系所名稱(英) Department of Geomatics
學年度 99
學期 2
出版年 100
研究生(中文) 李明軒
研究生(英文) Ming-Shuian Lee
學號 p66984061
學位類別 碩士
語文別 中文
論文頁數 118頁
口試委員 口試委員-陳良健
口試委員-吳究
口試委員-蔡榮得
指導教授-蔡展榮
中文關鍵字 尺度不變特徵轉換  多影像匹配  光束法區域平差 
英文關鍵字 SIFT  Multi-Image Matching  Bundle Block Adjustment 
學科別分類
中文摘要 以數位影像進行空間資訊獲取的技術與應用,隨著感測器與儲存媒體的進步而日趨多樣性,而高效率且高自動化的方位計算程序即是整合這些資料進行坐標量測的首要工作,其程序中不可避免的必須量測像片三角所需之連結點,而影像匹配則帶來了自動化的可行性。一般在實務應用上所進行的多影像匹配,通常需要已知攝影瞬刻之外方位參數以核線幾何進行匹配搜尋,或是已知像片的區域參數、航帶參數來估計匹配起始值,甚至仰賴人工量測同名點來提供初始方位;本文的研究則是援引尺度不變特徵轉換演算法(Scale Invariant Feature Transform, SIFT),設計了一個不需要輸入影像重疊初始資訊之多影像匹配策略,同時針對大像幅之空照影像處理,以品質過濾法(Quality Filtering, QF)和仿射轉換預估法(Affine Transformation Prediction, AFTP)來達到較佳計算效率之連結點選點與量測的自動化,最後再以光束法區域平差估計出本研究設計的SIFT多影像匹配之量測精度可達0.2個像元,並透過高精度地面檢核點驗證了匹配點之正確性。
英文摘要 With advances in sensor and storage device, spatial information technologies and applications using digital image are provided with diversity increasingly. And processing image orientation with high efficiency and high automation is the primary work of integration with spatial information and coordinate measurement. Inevitably, tie point measurements are necessary in aerial triangulation, and that is how image matching brings the feasibility of automation. Generally, there must be some known input data for providing initial values for multi-image matching, such as block data, strip data, image overlapping information or manual tie point measurement. In this study, the Scale Invariant Feature Transform (SIFT) algorithm is utilized for designing a method of multi-image matching for aerial triangulation (AT) without the need on the aforementioned input data. To deal with a large number of large format aerial images simultaneously, this thesis proposed Quality Filtering (QF) and Affine Transformation Prediction (AFTP) for automatic tie point extraction and measurement with better efficiency. Finally, the accuracy of the automatic image matching is up to 0.2 pixels evaluated by using bundle block adjustment and high precision ground check points. The results verify the applicability of the SIFT-based multi-image matching developed in this thesis for aerial triangulation.
論文目次 中文摘要...............................................................Ⅰ
Abstract...............................................................Ⅱ
誌謝...................................................................Ⅲ
目錄...................................................................Ⅳ
圖目錄.................................................................Ⅴ
表目錄.................................................................Ⅶ
第一章 前言............................................................1
§ 1-1 研究動機與目的................................................1
§ 1-2 文獻回顧......................................................4
§ 1-3 研究方法......................................................6
第二章 方法論.........................................................12
§ 2-1 坐標系統定義.................................................12
§ 2-2 光束法平差...................................................18
§ 2-3 資料蒐評.....................................................23
§ 2-4 尺度不變特徵轉換.............................................26
第三章 SIFT多影像匹配策略設計........................................32
§ 3-1 匹配策略.....................................................32
§ 3-2 特徵點品質評估...............................................40
§ 3-3 仿射轉換預估.................................................47
§ 3-4 匹配點連結策略...............................................54
第四章 實驗與分析.....................................................59
§ 4-1 特徵點萃取與品質評估.........................................59
§ 4-2 仿射轉換預估方法之效益.......................................71
§ 4-3 匹配成果與效率評估...........................................79
§ 4-4 像片三角計算.................................................89
第五章 結論與建議....................................................105
參考文獻..............................................................109
附錄..................................................................112
參考文獻 王蜀嘉 (2006). Z/I DMC 數位相機影像幾何誤差探討. 第二十五屆測量及空間資訊研討會論文集.
王蜀嘉、張祖勛 (2006). 航測數位相機對空載雷射掃瞄帶來的衝擊. 第二十五屆測量學術及應用研討會論文集, 179-188.
吳究、張奇、劉銘哲 (2009). 基於尺度不變特徵點轉換之精密多元影像套合. 航測及遙測學刊, 14(2), 141-155.
吳俊霖、陳彥良. (2007). 一個不同曝光時間影像序列之強健特徵導向影像定位法. 資訊科學應用期刊, 3(1), 1-22.
吳建億 (2009). 使用物空間條件進行測量車相機檢定. 國立成功大學測量及空間資訊學系碩士論文.
李洢杰 (2003). 應用光流原理進行近景視訊影像同名點雲自動化追蹤與量測. 國立成功大學測量工程學系碩士論文.
李德仁 (1988). 誤差處理和可靠度理論-攝影測量平差的近代發展. 測繪出版社
林新欽 (2000). 傳統空三與GPS空三品質之比較. 國立成功大學測量工程學系碩士論文.
邱式鴻、王蜀嘉 (1996). Förstner 特徵物萃取法精確性的探討. 第十五屆測量學術及應用研討會論文集, 667-676.
徐志慧 (2009). SIFT影像比對效率與準確度之提升. 國立臺北大學通訊工程研究所碩士論文.
洪偉嘉 (1999). 自動化套合之研究. 國立交通大學土木工程研究所碩士論文.
張庭榮 (2008). SIFT演算法於立體對影像匹配與影像檢索應用之研究. 國立高雄應用科技大學土木工程與防災科技研究所碩士論文.
陳品清 (1982). 三角網之可靠度分析. 國立成功大學航測研究所碩士論文.
陳英煥 (2007). 空照數位相機拍攝高重疊影像匹配高密度點雲. 國立成功大學測量及空間資訊學系碩士論文.
曾宏正 (1985). 相片重疊及點位分佈對附加參數的影響. 國立成功大學航空測量研究所碩士論文.
劉新達、鄭宏逵. (2010). 航空攝影測量專用相機選擇及應用特性分析. 兩岸非常規攝影測量研討會.
劉銘哲 (2008). 研究不同資源衛星影像之匹配與套合. 國立中央大學土木工程學系碩士論文.
鄭心惠 (2002). 遙測影像空間品質之評估. 國立成功大學測量工程學系碩士論文.

Arai, K. (1991). Gcp Acquisition Using Simulated Sar and Evaluation of Gcp Matching Accuracy with Texture Features. International Journal of Remote Sensing, 12(11), 2389-2397.
Baarda, W. (1968). A Testing Procedure for Use in Geodetic Networks. Netherlands Geodetic Commission, Vol. 2 Nr. 5
Bentoutou, Y., Taleb, N., El Mezouar, M. C., Taleb, M., & Jetto, L. (2002). An invariant approach for image registration in digital subtraction angiography. Pattern Recognition, 35(12), 2853-2865.
Bentoutou, Y., Taleb, N., Kpalma, K., & Ronsin, J. (2005). An automatic image registration for applications in remote sensing. IEEE Transactions on Geoscience and Remote Sensing, 43(9), 2127-2137.
Dai, X. L., & Khorram, S. (1999). A feature-based image registration algorithm using improved chain-code representation combined with invariant moments. IEEE Transactions on Geoscience and Remote Sensing, 37(5), 2351-2362.
Debella-Gilo, M., & Kaab, A. (2011). Sub-pixel precision image matching for measuring surface displacements on mass movements using normalized cross-correlation. Remote Sensing of Environment, 115(1), 130-142.
Hartley, R., & Zisserman, A. (2003). Multiple view geometry in computer vision (2nd ed.). Cambridge, UK ; New York: Cambridge University Press.
Heipke, C. (1997). Special issue: Automatic image orientation - Preface. ISPRS Journal of Photogrammetry and Remote Sensing, 52(3), 101-102.
Huang, C. R., Chen, C. S., & Chung, P. C. (2008). Contrast context histogram - An efficient discriminating local descriptor for object recognition and image matching. Pattern Recognition, 41(10), 3071-3077.
Kruck, E. (1984). Ordering and Solution of Large Normal Equation Systems for Simultaneous Geodetic and Photogrammetric Adjustment. 15th ISPRS Congress, 17-29 June, 1984, Rio de Janeiro, BRASIL
Liao, M. S., Lin, H., & Zhang, Z. X. (2004). Automatic registration of INSAR data based on least-square matching and multi-step strategy. Photogrammetric Engineering and Remote Sensing, 70(10), 1139-1144.
Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91-110.
Mikolajczyk, K., & Schmid, C. (2005). A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(10), 1615-1630.
Mostafa, M. M. R., & Schwarz, K. P. (2001). Digital image georeferencing from a multiple camera system by GPS/INS. ISPRS Journal of Photogrammetry and Remote Sensing, 56(1), 1-12.
Schenk, T. (2004). From point-based to feature-based aerial triangulation. ISPRS Journal of Photogrammetry and Remote Sensing, 58(5-6), 315-329.
Wolf, P. R., & Dewitt, B. A. (2000). Elements of photogrammetry : with applications in GIS (3rd ed.). Boston: McGraw-Hill.
Zebedin, L., Klaus, A., Gruber-Geymayer, B., & Karner, K. (2006). Towards 3D map generation from digital aerial images. ISPRS Journal of Photogrammetry and Remote Sensing, 60(6), 413-427.
Zitova, B., & Flusser, J. (2003). Image registration methods: a survey. Image and Vision Computing, 21(11), 977-1000.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2012-08-03起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2012-08-03起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw