跳到主要內容

臺灣博碩士論文加值系統

(23.20.20.52) 您好!臺灣時間:2022/01/24 18:12
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:林志交
研究生(外文):Chih-Chiao Lin
論文名稱:基因演算法於模型影像套合計算之應用
論文名稱(外文):Model-image Fitting Using Genetic algorithms
指導教授:曾義星曾義星引用關係
指導教授(外文):Yi-Hsing Tseng
學位類別:碩士
校院名稱:國立成功大學
系所名稱:測量工程學系碩博士班
學門:工程學門
學類:測量工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:中文
論文頁數:106
中文關鍵詞:基因演算法模型式建物萃取建構實體幾何模型影像套合
外文關鍵詞:Model-image FittingModel-based Building ExtractionConstructive Solid GeometryGenetic Algorithms
相關次數:
  • 被引用被引用:14
  • 點閱點閱:710
  • 評分評分:
  • 下載下載:176
  • 收藏至我的研究室書目清單書目收藏:3
模型式建物萃取是目前數值攝影測量主要研究方向之一,然而在萃取過程中,人工的方式並不利於對模型與影像實行最佳套合,因此發展一套以電腦處理模型與影像最佳套合的演算法為其關鍵。最小二乘模型-影像套合法(Least-squares Model-image Fitting, LSMIF)乃目前最為嚴謹的方法,然而其缺點是需要良好近似值方能解算,且極易陷入區域最佳解(Local Optimal Solution)。基因演算法(Genetic Algorithms, GAs)是模擬自然界演化的一種最佳化搜尋方法,其特點在於擁有平行搜尋、不需對函數微分,且避免陷入區域最佳解的能力。本研究探討如何應用基因演算法來進行模型與影像的套合,研究重點在於適應函式的設計及收斂結果的評估,期能藉其優異的全域搜尋能力來改善牛頓法需要良好近似值的缺點。

本文以矩形與屋脊形元件模型來驗證基因演算法套合理論的可行性,方法為先針對欲套合的建物模型,合理地給予各模型參數範圍,根據基因演算法的群族式(Population-based)搜尋概念,將一群初始模型投影至已知外方位的像片上,再將影像萃取出的建物邊緣線像元利用已知像片-影像轉換參數轉換至像片座標,如此可計算萃取像元至投影後的線框模型邊緣線間的距離。利用此距離值的平方和為最小的目標下設計一套適應函式(Fitness Function),以判斷各模型的適應值,再經過一系列再生、交配、與突變的演化過程後,擁有最高適應值的模型即為套合結果。本文選擇數棟房屋作套合測試,實驗結果顯示基因演算法在本文所採用的適應函式下,確實能廣域搜尋得近似最佳解(Near-optimal Solution),因此應用基因演算法於模型-影像套合上,的確有其發展的潛力。
Model-based building extraction (MBBE) is currently one of the major research topic in the field of digital photogrammetry. The effectiveness of optimal model-image fitting algorithm is the key of MBBE. The previously proposed Least-squares Model-image Fitting (LSMIF) algorithm is an iterative solution using Newton’s method which needs good initial approximations of the unknown parameters and is easy to get trapped at a local optimal solution. Genetic Algorithms (GA) work with rich population and simultaneously climbs many peaks in parallel during the search process. It effectively avoids the possibility of getting trapped at a local minimum. This thesis, therefore, tailored a GA to be a new model-image fitting method for MBBE, which does not need good approximation.

In this thesis, parameterized CSG (Constructive Solid Geometry) primitives including box and gable-roof house are tested for demonstration. In the approach, the initial population is generated randomly in the predefined parameter domain. Consequently, this population of primitives are transformed to object coordinate system with pose and shape parameters and projected to photo coordinate system with the known exterior orientation parameters. We propose a concept of fitness function exploiting objective of minimization of discrepancy between the extracted edge pixels and projected model wire frame edge to evaluate each individual in population. After a series of re-product, crossover, and mutation operators, taking the model with highest fitness value as solution. Our experimental results show that GA can correctly and globally find the near-optimal solution by compared with manual measurements and LSMIF. In the conclusion, GA indeed has potential for model-image fitting.
中文摘要………………………………………Ⅰ
英文摘要………………………………………Ⅱ
誌謝……………………………………………Ⅲ
目錄……………………………………………Ⅳ
表目錄…………………………………………Ⅶ
圖目錄…………………………………………Ⅸ

第一章 前言……………………………………1
§1-1 研究動機與目的…………………………1
§1-2 文獻回顧…………………………………2
§1-2-1 模型式建物萃取………………………2
§1-2-2 套合最佳化……………………………4
§1-2-3 基因演算法……………………………5
§1-3 研究方法與流程…………………………6
§1-4 研究範疇與論文架構……………………8
第二章 模型式建物萃取理論與最佳套合…10
§2-1 模型式建物萃取之流程…………………10
§2-2 模型式建物萃取之架構…………………12
§2-2-1 建物模型建置…………………………13
§2-2-2 模型-影像套合…………………………15
§2-2-3 模型約制與人工編修…………………16
§2-3 模型與影像套合的方法…………………18
§2-3-1 Clustering 法…………………………18
§2-3-2 Snake-like法…………………………19
§2-3-3 LSMIF法…………………………………21
第三章 基因演算法…………………………26
§3-1 基因演算法架構…………………………26
§3-1-1 染色體編碼……………………………26
§3-1-2 染色體解碼與適應函式………………27
§3-1-3 基本運算………………………………28
§3-1-4 控制參數與終止規則…………………30
§3-2 基因演算法演算流程……………………32
§3-3 基因演算法與傳統演算法之比較………33
§3-4 基因演算法基本理論……………………35
第四章 應用基因演算法於模型與影像套合…40
§4-1模型與影像套合之概念……………………40
§4-1-1 元件模型的座標轉換…………………41
§4-1-2 影像特徵物之選擇考量………………44
§4-2 適應函式之設計…………………………45
§4-2-1 最佳化目標……………………………46
§4-2-2 適應函式………………………………48
§4-2-3 環域(Buffer)的選擇考量……………53
§4-3 基因演算法於模型-影像套合之參數設定…53
§4-3-1 模型參數範圍…………………………54
§4-3-2 基因參數設定…………………………57
§4-4 影像遮蔽問題的處理……………………66
§4-5 演算架構與流程…………………………68
第五章 實驗結果與分析…………………70
§5-1 實驗資料與實驗設計……………………70
§5-1-1 實驗資料與檢核資料…………………70
§5-1-2 程式說明與實驗設計…………………73
§5-2 不同適應函式之套合成果比較…………74
§5-3 套合過程中參數收斂性之檢視…………76
§5-4 不同像片數之套合成果…………………83
§5-5 遮蔽影像之套合分析……………………85
§5-6 套合實例…………………………………88
§5-7 綜合分析…………………………………97
第六章 結論與建議………………………100
參考文獻………………………………………103
附錄一 實驗像片之外方位元素……………107
1.王正忠,「以近景攝影測量進行模型式建物重建」,國立成功大學測量工程學系碩士論文,2002。

2.邱式鴻,「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,台北市,pp.667-676,1996。

3.林文棋,「半自動化建物萃取之建物模型建置與操作」,國立成功大學測量工程學系碩士論文,2001。

4.周宏達,「以最小二乘法進行參數式模型與影像之最佳套合」,國立成功大學測量工程研究所碩士論文,2001。

5.張崑宗,「數值影像中線形地物萃取之研究」,國立交通大學土木研究所博士論文,1998。

6.曾義星、王聖鐸,「結合CAD與攝影測量之三維城市模型建置」,中華地理資訊學會GIS 2000學術研討會論文集,民國89年12月,台南國立成功大學,pp.40-48,2000。

7.Kass, M., Witkin, A. and Terzopoulos, D., "Snake : Active Contour Models", International Journal of Computer Vision, 1(4), pp. 321-331, 1988.

8.Fua, P., Leclerc, Y. G., "Model driven Edge Detection", Machine Vision and Application, 3(1), pp. 45-56, 1990.

9.Fua, P., "Model-based Optimization: Accurate and Consistent Site Modeling", International Archives of Photogrammetry and Remote Sensing, Vol. 31, Part B3, pp. 222-233, 1996.

10.Förstner, W., "A Framework for Low Level Feature Extraction", Computer Vision-ECCV '94, Vol. 2, Springer-Verlag, pp. 383-394, 1994.

11.Förstner, W., "3D-City Models: Automatic and Semi-automatic Acquisition Methods", Photogrammetric Week '99, Stuttgart, Vol. 47, pp. 291-304, 1999.

12.Goldberg, D. E., Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley Pub. Com. Inc., USA, 1989.

13.Grün, A., "Automation in Building Reconstruction", Photogrammetric Week '97, Herbert Wichmann-Verlag, Heidelberg, pp. 175-188, 1997.

14.Grün, A. and Dan, H., "TOBAGO-a Topology Building for the Automated Generation of Building Models", Automatic Extraction of Man-made Objects from Aerial and Space Images(II), at Monte Vertia, pp. 149-160, 1997.

15.Gülch, E., Müller, H. and Laebe, T., "Integration of Automatic Processes into Semi-automatic Building Extraction", ISPRS Conference "Automatic Extraction of GIS Objects from Digital Imagery", München, XXXII, 1999.

16.Gülch, E., "Virtual Cities from Digital Imagery", Photogrammetric Record, 16(96), pp. 893-903, 2000.

17.Holland, J. H., Adaptation in Natural and Artificial Systems, Ann Arbor: The University of Michigan Press, 1975.

18.Ji, Q. and Zhang, Y., "Camera Calibration with Genetic Algorithms", IEEE Trans. Systems, Man, and Cybernetics, vol. 31, pp. 120-130, 2001.

19.Lowe, D.G., "Fitting Parameterized Three-Dimensional Models to Images", IEEE Trans. Pattern Analysis and Machine Intelligence, 13(5), pp. 441-450, 1991.

20.Lang, F., Löcherbach, H. and Schickler, W., "A One-eye Stereo System for Semi-automatic 3D-building Extraction", Geomatics Info Magazine, pp. 1-4, 1995.

21.Lang, F. and Förstner, W., "3D-City Modeling with a Digital One-eye Stereo System", International Archives of Photogrammetry and Remote Sensing, Vienna, Vol. 31, pp. 415-420, 1996.

22.Rottenstener, F., "Semi-automatic Building Reconstruction Integrated in Strict Bundle Block Adjustment", International Archives of Photogrammetry and Remote Sensing, Amsterdam, Vol. 33, pp. 461-468, 2000.

23.Sester, M. and Förstner, W., "Object Location Based on Uncertain Models", Mustererkennung 1989, Informatik Fachberichte 219, Springer-Verlag, pp. 457-464, 1989.
24.Suveg, I. and Vosselman, G., "3D Reconstruction of Building Models", International Archives of Photogrammetry and Remote Sensing, XXXIII, Part B2, pp. 538-545, 2000.

25.Tseng, Y. H. and Wang, S., "Experiments on CSG Model-based Building Extraction from Aerial Images", 22nd Asian Conference on Remote Sensing, 5-9 November, Singapore, pp. 1091-1096, 2001.

26.Veldhuis, H., "Performance Analysis of Two Fitting Algorithms for The Measurement of Parameterized Objects", IAPRS Commission 3, Working Group 4, vol. 32, pp. 400-407, 1998.

27.Vosselman, G., "Interactive Alignment of Parameterised Object Models to Images", IAPRS Commission 3, Working Group 3, vol. 32, pp. 272-278, 1998.

28.Vosselman, G. and Veldhuis, H., "Mapping by Dragging and Fitting of Wire-Frame Models", Photogrammetric Engineering & Remote Sensing, 65(7), pp. 769-776, 1999.

29.van den Heuvel, F. A., "Trends in CAD-Based Photogrammetric Measurement", International Archives of Photogrammetry and Remote Sensing, Amsterdam, Vol. XXXIII, Part B5, pp. 852-863, 2000.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊