跳到主要內容

臺灣博碩士論文加值系統

(3.235.60.144) 您好!臺灣時間:2021/07/27 00:56
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:賴泓瑞
研究生(外文):Hung-Ruei Lai
論文名稱:以模型樣版為基礎之建物三維點雲建模演算法
論文名稱(外文):Template-based 3D Point Cloud Modeling for City Buildings
指導教授:林昭宏林昭宏引用關係
指導教授(外文):Jau-Hung Lin
學位類別:碩士
校院名稱:國立成功大學
系所名稱:測量及空間資訊學系碩博士班
學門:自然科學學門
學類:地球科學學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:中文
論文頁數:90
中文關鍵詞:最小二乘法擬合點雲萃取代數型態模型樣版點雲重建
外文關鍵詞:point cloud reconstructionleast-square fittingtemplate-based modelingpoint cloud segmentation
相關次數:
  • 被引用被引用:11
  • 點閱點閱:494
  • 評分評分:
  • 下載下載:114
  • 收藏至我的研究室書目清單書目收藏:0
近年來光達掃瞄儀普遍且廣泛的被使用在量測的領域,光達掃瞄儀可以快速獲得高精度且高解析度點雲資料,因此相關點雲模型建置的技術也越來越受到重視。點雲資料模型重建面臨到的共同問題是如何處理點雲資料存在的誤差;此外模型的邊角特徵突顯(例如城市建物)也會是一個挑戰與問題,本研究提出一全新的點雲建模技術,本技術是以階層式模型樣版為基礎對三維點雲資料進行模型重建,此樣版是由三個主要基本幾何元件構成(分別為平面、圓球以及圓柱)且皆以代數式描述,階層式模型樣版的第一層皆為基本幾何元件,接著利用基本幾何元件組合出下一層簡單形狀的模型樣版,然後進一步結合前層模型樣版以建立更高階層複雜模型。本技術首先利用RANSAC方法將點雲資料萃取出數個基本幾何點雲群集,再利用模型樣版進行點雲套合,此模型樣版是以線性代數式描述而不是非線性式,因此在計算效率與演算法的強鈍性上有十足提升,此外在每一模型樣版階層加入幾何約制條件以提高建模品質。實驗結果顯示本方法比利用隱性面函式建模方法在資料誤差的抵擋與建模品質上有更佳的表現,且比一般最小二乘法相關的重建方法在視覺上擁有更佳的建模品質。
Digital scanning devices such as LiDAR (Light Detection and Ranging) have recently become affordable and available. They are capable of acquiring high-accuracy and high-resolution point clouds. Thus, the techniques for point cloud modeling have received increasingly attentions in the last decade. As the approaches reconstruct the point clouds, they face a common problem: how to handle point clouds with inherent noises. Moreover, it will be especially challenge in handing point clouds that contains sharp features, e.g., city buildings. In the thesis, a novel template-based modeling approach for 3D point clouds sampled from unknown city buildings is introduced. A hierarchy algebraic template, comprising of three types of primitive geometries (that is, plane, sphere, and cylinder), is used to fit point clouds. The algebraic template is organized in a hierarchical manner. The first-level, i.e., the lowest-level, consists of the primitive geometries which are represented in algebra form. These primitive geometries are merged into 3D objects with simple shapes in the next level. These 3D objects are further joined to form the final template model in the last level. After the point clouds are partitioned (using RANSAC algorithm) into several geometric sets, the constructed template model is used to fit them. The point cloud fitting is archived by solving a least-square linear system instead of solving a non-linear one, making the approach efficient and robust in the modeling. In addition, some geometric constraints on the primitive geometries are added in the point cloud fitting (i.e., least-square linear system) for the purpose of improving modeling quality. The experimental results show that the approach is better, in terms of sharp feature fitting and noise withstanding, than the approaches based on implicit surfaces. In addition, comparing to the general least-square fitting approaches, the template-based fitting with geometry constraints improves modeling quality with respect to human visual system.
摘要 I
Abstract II
目錄 V
表目錄 VII
圖目錄 VIII
第一章 緒論 1
1.1 前言 1
1.2 研究動機、目的與貢獻 3
1.3 論文架構 8
第二章 相關研究 9
2.1 三維點雲分類相關研究 9
2.2 三維點雲建模相關研究 11
2.2.1 資料導向 12
2.2.2 模型導向 14
第三章 研究方法 15
3.1 法向量計算 16
3.2 隨機樣本一致(RANSAC)分類 21
3.2.1 形狀預估(Shape estimation) 23
3.2.2 RANSAC 複雜性(complexity) 25
3.2.3 RANSAC 最小點雲群集樣本選取策略 26
3.2.4 得分函式 28
3.3 模型建模 34
3.3.1 平面代數式以及代數學最小二乘法計算 34
3.3.2 圓球代數式以及代數學最小二乘法計算 38
3.3.3 圓柱代數式以及代數學最小二乘法計算 43
3.3.4 階層式架構 51
3.3.5 約制條件 52
第四章 實驗結果與分析 55
4.1 模擬點雲資料建立 55
4.2 模擬資料建模成果 58
4.3 真實空載光達點雲資料 63
4.4 真實空載光達點雲資料建模成果 65
4.5 與隱性面函式建模成果比較與分析 72
4.6 代數式擬合與附有約制條件之間接平差兩者成果比較 76
第五章 結論、限制與未來工作 79
參考文獻 85
附錄 89
附錄A 多重尺度等級(Level of Detail)標準 89
Alharthy, A. and Bethel, J. 2002. Heuristic filtering and 3D feature extraction from LIDAR data. International

Archives of Phorogrammetry Remote Sensing and Spatial Information Sciences 34(3/A): 29-34.

Amenta, N. 1999. Surface reconstruction by Voronoi filtering. Discrete and Computational Geometry 22(4): 481-504.

Bernardini, F., Mittleman, J., Rushmeier, H., Silva, C. and Taubin, G. 1999. The Ball-Pivoting Algorithm for Surface Reconstruction. IEEE Transactions on Visualization and Computer Graphics: 349-359.

Bolles, R. C. and Fischler, M. A. 1981. A RANSAC-based approach to model fitting and its application to finding cylinders in range data. InProceedings of the 7th International Joint Conferenceon Artificial Intelligence (Vancouver, B.C.,Canada, Aug. 24-28). IJCAI: 637-643.

Carr, J. C., Beatson, R. K., Cherrie, J. B., Mitchell, T. J., Fright, W. R., McCallum, B. C. and Evans, T. R.. 2001. Reconstruction and representation of 3D objects with radial basis functions. Proceedings of the 28th annual conference on Computer graphics and interactive techniques: 67-76.

Chaperon, T. and Goulette, F. 2001. Extracting cylinders in full 3d data using a random sampling method and the gaussian image. Vision, Modeling and Visualization (VMV’01), Stuttgart, Germany: 35-42

Fitzgibbon, A., Pilu, M. and Fisher, R. B. 1999. Direct least square fitting of ellipses. IEEE Transactions on pattern analysis and machine intelligence 21(5): 476-480.

Fitzgibbon, A. W., Eggert, D. W. and Fisher, R. B. 1997. High-level CAD model acquisition from range images. Computer-aided design 29(4): 321-330.

Flood, M. and Gutelius, B. 1997. Commercial implications of topographic terrain mapping using scanning airborne laser radar. Photogrammetric Engineering and Remote Sensing 63(7): 780-780.

Gotardo, P., Bellon, O. and Silva, L. 2003. Range Image Segmentation by Surface Extraction Using an Improved Robust Estimator. IEEE Computer Society Conference On Computer Vision and Pattern Recognition 2:18-20.

Groger, G., Kolbe, T. H., Czerwinski, A. and Nagel, C. 2008. OpenGIS City Geography Markup Language(CityGML) Implementation Specification, 2008 Open Geospatial Consortium, Inc. http://www.opengeospatial.org/

Guennebaud, G. and Gross, M. 2007. Algebraic point set surfaces. ACM Transactions on Graphics (SIGGRAPH 2007 Proceedings) 26(3):23.1-23.9

Hough, P. V. C. 1962. Method and means for recognizing complex patterns. U.S. Patent , 3,069,654

Jiang, X. Y., Meier, U., Bunke, H. and S. O. C. 1996. Fast range image segmentation using high-level segmentation primitives. Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV 96): 83-88

Kazhdan, M., Bolitho, M. and Hoppe, H. 2006. Poisson Surface Reconstruction. In Proceedings of the Eurographics Symposium on Geometry Processing: 43-52.

Kuo, C. C. and Yau, H. T. 2005. A Delaunay-based region-growing approach to surface reconstruction from unorganized points. Computer-Aided Design 37(8): 825-835.

Kurdi, F. T., Landes, T. and Grussenmeyer, P. 2007. Hough-Transform and Extended RANSAC Algorithms for Automatic Detection of 3D Building Roof Planes from Lidar Data. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences 36(3/W52): 407-412.

Morse, B. S., Yoo, T. S., Rheingans, P., Chen, D. T. and Subramanian, K. R. 2001. Interpolating implicit surfaces from scattered surface data using compactly supported radial basis functions. In Shape Modeling International 2001: 89-98.

Myatt, D. R., Torr, P. H. S., Nasuto, S. J., Bishop, J. M. and Craddock, R. 2002. NAPSAC: High noise, high dimensional robust estimation. BMVC02, p.Computer Vision Tools: 458-467.

Ohtake, Y., Belyaev, A., Alexa, M., Turk, G. and Seidel, H. P. 2003. Multi-level partition of unity implicits. ACM Transactions on Graphics (SIGGRAPH Proc.) 22(3): 463-470.
Pauly, M., Gross, M., Kobbelt, L. P., Hochschule, E. T. and Zurich, S. 2002. Efficient simplification of point-sampled surfaces. In Proc. of IEEE Visualization, 2002. : 163-170.

Rabbani, T. and Van Den Heuvel F. 2005. Efficient Hough Transform for automatic detection of cylinders in point clouds. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences 36 (Part 3/W19), 60–65.

Rabbani, T., van den Heuvel F. and Vosselmann, G. 2006. Segmentation of point clouds using smoothness constraint. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences 36(5): 248–53.

Roth, G. and Levine, M. D. 1993. Extracting geometric primitives. Computer Vision, Graphics, and Image Processing 58(1): 1-22.

Schenk, T. 2001. Modeling and recovering systematic errors in airborne laser scanners. Proceedings of OEEPE workshop on Airborne Laserscanning and Interferometric SAR for Detailed Digital Elevation Models, Stockholm, Sweden: 40-48

Schnabel, R., Wahl, R. and Klein, R. 2007. Efficient RANSAC for Point-Cloud Shape Detection. Computer Graphics Forum 26(2):214-226.

Sithole, G. and Vosselman, G. 2003. Automatic structure detection in a point cloud of an urban landscape. Proc. 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas: 22-23, IEEE. Berlin:67-71.

Stoll, C., Karni, Z., Rossl, C., Yamauchi, H. and Seidel, H.-P. 2006. Template deformation for point cloud fitting. In Symposium on Point-Based Graphics :27-35.

Vosselman, G., Gorte, B. G. H., Sithole, G. and Rabbani, T. 2004. Recognizing structure in laser scanner point clouds. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences 46(8/W2): 33-38.

Wang, Z., Bovik, A. C., Sheikh, H. R. and Simoncelli, E. P. 2004. Image quality assessment: From error visibility to structural similarity. IEEE transactions on image processing 13(4): 600-612.

Wu, X., Yu, M. and Xia, W. Q. 2005. Implicit Fitting and Smoothing Using Radial Basis Functions with Partition of Unity. Ninth International Conference on Computer Aided Design and Computer Graphics, 2005.IEEE Computer Society : 139-148.

王聖鐸, 曾義星, 陳良健, 陳杰宗與 陳思仁. 2007. "整合空載光達資料及數值地形圖之模型式建物萃取法." 第二十六屆測量及空間資訊研討會論文集(二): 917-926頁.

王蜀嘉 與 曾義星 2003. "以空載雷射掃瞄方法產生高精度及高解析度數值地形模型及數值地表模型誤差分析.", 內政部委託研究計畫報告書.

武漢測繪科技大學測量平差教研室 1996. 測量平差基礎, 北京測繪出版社.

陳俊元 2008. "智慧型基因演算法及差分坐標應用於點雲鄰近點計算.", 國立成功大學測量及空間資訊學系碩士班論文.

湯凱佩,曾義星 2004,"以八分樹三維網格結構組織光達點雲資料並進行平面特徵萃取",第二十三屆測量學術及應用研討會論文集:143-150

劉金燁 2007. "連結長方體法之設計與初步成果之品質評估.",國立成功大學測量及空間資訊學系碩士班論文.
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