跳到主要內容

臺灣博碩士論文加值系統

(3.81.172.77) 您好!臺灣時間:2022/01/21 20:09
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:陳建文
研究生(外文):Chien-Wen Chen
論文名稱:彩色影像邊緣線萃取之研究
論文名稱(外文):Edges Extraction of Color Image
指導教授:王蜀嘉王蜀嘉引用關係
指導教授(外文):Shue-Chia Wang
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:70
中文關鍵詞:邊緣線萃取空間梯度ENOVA
外文關鍵詞:Edge ExtractionSpatial GradientEstimation of Signal Dependent Noise Variance
相關次數:
  • 被引用被引用:19
  • 點閱點閱:879
  • 評分評分:
  • 下載下載:231
  • 收藏至我的研究室書目清單書目收藏:1
  近年來由於電腦資訊的普及與進步,使得各種資料的存取漸漸邁向數值化及自動化。地圖的儲存方式也不再受限於傳統的圖紙式地圖而用電腦數值化的方法,使空間資訊朝三維展示的方向進行。因此,使傳統的航空攝影測量漸漸邁向數值攝影測量的領域,其中都市區三維幾何模型(3D City Model)的建置便為數值攝影測量中一個重大的研究。

  三維幾何模型的建置則需要有完整建物萃取資訊提供後續的工作。而由方位已知的都市區航照影像中,萃取出有意義的三維線段,如建物屋頂的水平線段或斜線段,是協助都市區建物三維幾何模型自動化重建的一個重要步驟。而目前三維線段的獲取主要還是透過影像萃取的二維直線進行處理而得。因為這個原因,使萃取影像線特徵的完整性成為建物重建的一個重要問題。影像線特徵物萃取的不完整不僅無法組成有意義的三維線段,而且會導致之後無法重建完整的建物。

  由於彩色影像邊緣線偵測的演算法也越漸成熟,因此本研究期望利用彩色影像作為來源資料的處理。希望找尋比黑白影像更加完整的邊緣線段,來補足黑白影像之遺漏,並對不同形式的彩色影像邊緣線偵測的演算法進行比較其之間的差異性。
  Recently ,due to the popularity and progress of the computer technology, data access become digitized and automatic. Besides, in order to spatial information 3 dimensionally, map data is also in digital form instead of traditional paper-printed map. In order to provide 3D spatial information photogrammetrically, the automatic reconstruction of urban 3D city model is a very important research.

  The successfulness of reconstruction of 3D city model depends largely on complete extraction of edge information in imgaes. In urban aerial images with known which orientaion, extraction of meaningfull 3D lines, for example, horizontal edges and gable lines of building roofs, is a significant step for the automatic buildings reconstruction in urban area. However, up to now, 3D lines can only be mainly acquired by first extracting 2D lines in images. Thus, the completeness of extraction of 2D line features in images is an essential factor for the successfulness of building reconstruction. Incomplete extraction of 2D of line features could prevent the reconstruction of 3D lines and hence the reconstruction complete buildings.

  It is generally know that multispectral images have more information than single band images, therefore it is the goal of this paper to investigate the advantages of color images. In expectation that more complete edges could be found from color images than from monochrome images. In additional to that different kinds of algorithm for edge detection of color image are investigated to compare their suitability for practical usage.
目錄……………………………………………………………………I
圖目錄…………………………………………………………………Ⅲ
表目錄…………………………………………………………………Ⅵ

第一章 緒論…………………………………………………………1
  1-1 研究動機……………………………………………………1
  1-2 文獻回顧……………………………………………………3
  1-3 研究方法……………………………………………………5
  1-4 論文架構……………………………………………………6
第二章 空間梯度整合方法的原理…………………………………7
  2-1 邊緣線萃取的一般原則……………………………………7
  2-2 空間梯度的概念……………………………………………10
第三章 雜訊變方加權整合方法的原理……………………………16
  3-1 ENOVA雜訊估計模型 ………………………………………16
    3-1-1 影像和物體的模型…………………………………16
    3-1-2 訊號和雜訊的模型…………………………………18
    3-1-3 均勻度指標和其統計性質…………………………21
  3-2 雜訊變方估計的方法………………………………………22
    3-2-1 β 的估計……………………………………………24
    3-2-2 估計的偏差改正……………………………………26
  3-3 多光譜影像的波段加權……………………………………30
第四章 邊緣線萃取…………………………………………………33
  4-1 彩色和彩色彩色模型………………………………………33
    4-1-1 RGB 彩色模型………………………………………33
    4-1-2 HSI 彩色模型偏差改正……………………………34
  4-2 彩色影像的邊緣線萃取……………………………………36
    4-2-1 利用空間梯度整合方法……………………………36
    4-2-2 雜訊變方加權偵測方法……………………………42
    4-2-3 邊緣影像套合的方法………………………………44
第五章 實驗與成果分析……………………………………………47
  5-1 基本資料……………………………………………………47
  5-2 實驗影像結果………………………………………………53
第六章 結論與建議…………………………………………………65

參考文獻………………………………………………………………67
王蜀嘉、劭怡誠、邱式鴻、陳世崇,1997。小面解析立體視覺系統在邊緣線搜尋上之應用,第十六屆測量學術及應用研討會:page 695-704

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:page 667-675

邱式鴻、王蜀嘉,1997。以立體像對為基礎的線型特徵物鍊結方式,第十六屆測量學術及應用研討會:page 665-674

邱式鴻,2001。從都市區立體航照影像中萃取屋頂面的實用策略,國立成功大學測量工程學系博士論文

徐偉城,1999。空照彩色立體像對中人工建築物萃取之研究,國立中央大學土木工程研究所碩士論文

蔡玉慧,1998。以彩色資訊協助影像特徵之萃取,國立成功大學測量工程研究所碩士論文

Bignone, F.,1995.“Segment Stereo-Matching and Coplanar Grouping”, Institute of Communication Technology, Image Science Lab, ETH Zurich, Switzerland

Brügelmann, R. and W. Förstner, 1992.“Noise Estimation for Color Edge Extraction”, In Förstner, W. and S. Ruwiedel (Eds.), Robust Computer Vision: pp.90-107
Brügelmann, R. and W. Förstner, 1993.“Estimation of Signal Dependent Noise Variance”, Institute for Photogrammetry in Bonn, Technical report TB-ipb

Chio, S.-H. and S.-C. Wang,1999.“Semi-Automatic System for Roof Reconstruction Based on 3D Linear Segments”, In: the 20th Asian Conference on Remote Sensing, vol.1: pp.165-170

Chio, S.-H., S.-C. Wang and B. Wrobel, 2000.“Interactive Roof Patch Reconstruction Based on 3-D Linear Segments”, In: International Archives of Photogrammetry and Remote Sensing, vol.XXXIII: pp.177-184

Di Zenzo, S., 1986.“ A Note on the Gradient of a Multi-Image”, Computer Vision, Graphics and, Image Processing, vol. 53, no1: pp.116-125

Douglaus, D. H. and T. K. Peucker, 1973. “Algorithms for reduction of the number of points required to represent a digitized line or its caricature”, Canadian Cartographer vol.10:pp.110-122.

Drewniok, C., 1994.“Multi-Spectral Edge Detection. Some Experiments on Data from Landsat-TM”, International Journal of Remote Sensing, Vol. 15, No. 18, S: pp.3743-3765

Förstner, W., 1994.“A Framework for Low Level Feature Extraction”, In: J.O.Eklundh, J.O.Eklundhs, editors, Computer Vision, ECCV’ 94, vol.Ⅱ: pp. 383-394,Springer Verlag, Berlin
Förstner, W., 1998.“Image Preprocessing for Feature Extraction in Digital Intensity, Color and Range Images”, Summer School on {em Data Analysis and the Statistical Foundations of Geomatics} Chania, Crete, Greece, May 25-30, 1998, in Springer Lecture Notes on Earth Sciences

Fuchs, C. and S. Heuel, 1998.“Feature Extraction” in Förstner, Wolfgang (ed.) Proc. of Third Course in Digital Photogrammetry, Bonn

Gonzalez, R.C. and Wood, R.E , “Digital Image Processing”, Addison-Wiley, New York, 1933z
Haala, N., 1994.“Detection of Buildings by Fusion of Range and Image Data”, International Archives of Photogrammetry and Remote Sensing, vol30: pp341-349

Haala, N., 1995.“3D Building Reconstruction using Linear Edge Segmentgs”, In D. Fritsch and D. Hobbie, D. Fritsch and D. Hobbies, editors, Photogrammetric Week pp19-28, "Herbert Wichmann Verlag, Heidelberg

Henricsson, 0. and E. Baltsavias, 1997.“3-D Building Reconstruction with ARUBA: A Qualitative and Quantitative Evaluation”. In: A. Gruen, E. P. Baltsavias and 0. Henricsson, A. Gruen, E. P. Baltsavias and 0. Henricssons, editors, Automatic Extraction of Man-Made Objects from Aerial and Space Images (II), Birkhäuser Verlag: pp.65-76

Nevatia, R., 1977.“A color edge detector and its use in scene segmentation”, IEEE Trans. Systems Man Cybernet SMC-7: pp.820-826

Robinson, G., 1977.“Color Edge Detection”, Optical Eng ,vol. 16,no 5: pp.479-484

Ruzon M. A. “A Short History of Color Edge Detection”, in:
http://robotics.stanford.edu/~ruzon/compass/color.html

Ruzon, M. A and C. Tomasi, 2001.“Edge, Junction, and Corner Detection Using Color Distributions”, IEEE Transaction On Pattern Analysis and Machine Intelligence, VOL 23 NO.11 November : pp.1281-1295

Scholze, S., 2000.“Exploiting Color for Edge Extraction and Line Segment Stereo Matching in High-resolution Aerial Imagery”, ISPRS 2000: pp.815-822

Yang, C.K. and W.H.Tsai, 1996.“Reduction of Color Space Dimensionality by Moment-Preserving Thresholding and its Application for Edge-Detection in Color Image”, pattern Recognition Letters,vol.17, no.5: pp.481-490
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