三維都市模型重建的首要工作在提取建物輪廓，從過去許多的研究中發現，最普遍應用於提取建物輪廓的方式是以邊緣偵測方法，搭配向量化與簡約化來獲得基本建物輪廓，惟所得建物輪廓常需再經複雜的正規化的演算法來改善建物邊緣彎曲不平整的情形。本研究從點、線、面是構成三維建物基本要素的新觀點，提出基於「角點偵測」搭配「建物輪廓及角點修正」自動修補流程，針對光達高度資料或二值分類影像，以Harris及局部二位元圖形(Local Binary Pattern, LBP)演算法進行角點偵測，將獲得之建物角點以凸多邊形演算法進行連結；對於正交非矩形建物則搭配形態學之斷開及膨脹，改善因凸多邊形演算法構成不正確之輪廓線。接著以「建物輪廓及角點修正法」，將建物每個主要邊緣上之角點，以最小二乘法擬合產生較具代表性之線段，以各擬合線段交點求得建物主要角點，進而產生建物輪廓。
研究結果證明矩形建物以局部二位元圖形角點偵測法為基礎之整體精度優於以Harris角點偵測為基礎者約3.5%，整體精度可達92%，局部二位元圖形演算法之長度標準偏差為0.29m也優於Harris之0.55m；而正交非矩形之局部二位元圖形演算法整體精度可達91%。局部二位元圖形角點偵測法也優於邊緣偵測法，整體精度高出約3%，其長度標準偏差為0.37m也優於邊緣偵測的0.75m。本研究除了以數據說明角點偵測優於邊緣偵測外，所提出的「建物輪廓及角點修正」亦有助於提取出較精確之建物輪廓。

The essential procedure of constructing 3-D building models in urban areas is to extract the building boundary footprint. In the past researches, the common procedures used in extracting the building footprint are applying edge detection, vectorization, and generalization. However, the derived boundary lines occasionally occur zigzag patterns, thus, it still needs further building footprint regularization. This study proposed a new approach in the point of view that the points, lines and polygons are the essential elements in reconstructing 3-D building models. The proposed new method is based on “corner detection approach (CDA)” and “Adjustment of building footprints and corner points (ABFCO)” algorithm on Light Detection And Ranging (LiDAR) or binary classification resultant imagery. This study implements Harris and Local Binary Pattern (LBP) corner detection, afterward, connects all detected points by using convex hull algorithm. However, ortho-non-rectangle buildings would compose poor outlines after convex hull. This study combines open and dilation morphology with the find ignored point algorithm to improve any incorrect connections. Finally, performs the ABFCO algorithm to those points which belong to the same boundary to generalize a line segment, and to figure out the intersections and boundary lines of the buildings.
The experiment results have proved that the overall accuracy of LBP corner detection is about 3.5% higher than Harris corner detection, its overall accuracy is about 92% in rectangular buildings and about 91% in non-rectangular buildings, its standard deviation of boundary length is 0.29m and better than Harris’s 0.55m. We also compared LBP corner detection with edge detection. The overall accuracy of corner detection is about 3% higher than edge detection, standard deviation of boundary length 0.37m is also better than edge detection 0.75m. This study not only proved the corner detection is better than edge detection from data, but also developed ABFCO algorithm is helpful for extracting more accurate building footprint lines.

目 錄
中文摘要 I
Abstract II
誌 謝 IV
目 錄 VI
圖目錄 IX
表目錄 XIV
第一章 前言 1
1-1 研究動機與目的 1
1-2 研究方法概述 3
1-3 研究流程架構 5
第二章 文獻回顧 8
第三章 角點偵測方法 14
3-1 Harris角點演算法 16
3-1-1 Moravec運算元 16
3-1-2 Harris 角點偵測 18
3-2 局部二位元圖形 22
3-2-1 目標導向之基礎運算元 22
3-2-2 二值影像之局部二位元圖形演算法 25
3-3 凸多邊形之角點連結 26
3-4 凸多邊形造成角點遺失之補償 31
3-5 線性特徵模式評估 32
第四章 角點偵測方法應用於光達資料之建物輪廓提取 34
4-1 分類影像之前處理 35
4-1-1 連通元件分析 36
4-1-2 高度分析 37
4-1-3 面積分析 37
4-2 基於Harris角點偵測方法之建物輪廓提取 38
4-2-1 基本作業流程 38
4-2-2 各種方法於矩形建物之實作探討 40
4-3 建物輪廓修正方法 43
4-3-1 角點對應修正 43
4-3-2 最小二乘法直線擬合及線段交點 44
4-3-3 正交非矩形建物之實作探討 47
4-4 精度評估方法 56
第五章 實驗與討論 60
5-1 實驗區簡介 60
5-2 地真資料之建立程序 63
5-2-1 地真資料數化程序 63
5-2-2 地理坐標轉換影像坐標 64
5-2-3 建立地真基本資料元件 66
5-3 Harris及局部二位元圖形之精度評估比較 70
5-4 基於角點偵測之正交非矩形建物精度評估 87
5-5 基於角點偵測與基於邊緣偵測之精度評估比較 97
第六章 結論與建議 100
6-1 結論 100
6-2 建議 102
參考文獻 103
附錄一 程式列表 110

1. 李良輝 (1991). 「計算視覺方法於SPOT衛星影像之幾何特性分析」，國立中央大學土木工程研究所博士論文。
2. 邵怡誠、陳良健 (2004). 「利用二維房屋圖資及立體影像自動重建房屋外圍輪廓」，航測及遙測學刊第九卷第三期，第1-8頁。
3. 莊仁輝 (2002). 「家用機器人之電腦視覺系統研發」，行政院國家科學委員會專題研究計劃期中進度報告。
4. 黃明哲 (2007). 「應用航測影像及光達資料探討以知識庫為基礎之都市地物特徵分類之研究」，國立中山大學海洋環境及工程學系研究所博士論文。
5. 張智安、陳良健 (2006). 「利用光達資料模塑建物之研究」，航測及遙測學刊第十一卷第二期，第175-189頁。
6. 陳月淑 (2007). 「以光達與數位影像資料進行建物與樹木重疊區的地物特徵提取之研究」，國立中山大學海洋環境及工程學系研究所碩士論文。
7. 陳衍豪 (2001). 「立體航測影像直線與圓弧輪廓建物半自動之三維模型重建」，國立中央大學土木工程研究所碩士論文。
8. 曾珮婷 (2005). 「在特定車道行駛之大型車偵測與追蹤」，國立中央大學資訊工程研究所碩士論文。
9. 賴彥中 (2004). 「結合光達資料與數位空照影像重建三維建物模型」，國立中央大學土木工程研究所碩士論文。
10. Alharthy, A. and J. Bethel, (2002). Heuristic Filtering and 3D Feature Extraction fro LiDAR Data. In ISPRS Commission 3, Symposium 2002 September 9-13, Graz, Austria, Pages A-29 ff(6 pages).
11. Arefi, H., Hahn, M. and J. Lindenberger, (2003). Lidar Data Classfication with Remote Sensing Tools, Proceedings of ISPRS Commission IV Joint Workshop Challenges in Geospatial Analysis, Integration and Visualization II, September 8-9, Stuttgart, Germany, pp. 131-136.
12. Axelsson, P., (2003). Processing of Laser Scanner Data-Algorithms and Applications. ISPRS Journal of Photogrammetry and Remote Sensing, Vol.54, pp. 138-147.
13. Baillard, C., O. Dissard, O. Jamet, and H. Maitre, (1998). Extraction and textural characterization of above-ground areas from aerial stereo pairs: a quality assessment. ISPRS Journal of Photogrammetry and Remote Sensing, Vol.53, pp. 130-141.
14. Baltsavias, P. E. and A. Gruen, (2003). A Comparison of Aerial Photos, Lidar and IKONOS for Monitoring cities. Remotely Sensed Cities(Mesev, V. Editor). Taylor & Francis, New York, pp. 47-84.
15. Barber, C. B., D. P. Dobkin, and H. Huhdanpaa, (1996). The Quickhull Algorithm for Convex Hulls, ACM Transactions on Mathematical Software, Vol. 22, No. 4, pp. 469-483.
16. Canny, J., (1986). A Computational Approach to Edge Detection. IEEE Computer Society Washington, DC, USA, pp. 679-698.
17. Charaniya, A., R. Manduchi, and S. Lodha, (2004). Supervised Paramteric Classification of LiDAR Data. IEEE Workshop on Real Time 3D Sensor and Their Use, Washington DC, June, 2004.
18. Chen, L. C. and L. H. Lee, (1992). Progressive Generation of Control Frameworks for Image Registration. Photogrammetric Engineering and Remote Sensing, Vol. 58, No. 9, pp. 1321-1328.
19. Douglas, D. H. and Peucker, T. K., (1973). Algorithms for the Reduction of the Number of Points Required to Represent a Digitized Line or its Caricature (University of Ottowa/Simon Fraser University).
20. Elberink, S. O., and H. G. Mass, (2000). The Use of Anisotropic Height Texture Measurements for the Segmentation of Airborne Laser Scanner Data, International Archives of Photogrammetry and Remote Sensing, Vol. 18, Part B3, Amsterdam, pp. 678-684.
21. Filin, S., (2002). Surface Clustering from Airborne Laser Scanning Data. In ISPRS Commission 3 Symposium September 9-13, 2002, Graz, Austria, pp. A-119.
22. Gonzalez, R. C. and R. E. Woods, (2002). Digital Image Processing, Second Edition. Prentice-Hall, New Jersey, pp. 609.
23. Haala, N. and C. Brenner, (1999). Extraction of Buildings and Trees in Urban Environments. ISPRS Journal of Photogrammetry and Remote Sensing, Vol.54, pp. 130-137.
24. Harris, C and M. Stephens, (1988). A Combined Corner and Edge Detector. Proceedings of 4th Alvery Vision Conference, Manchester: The University of Sheffield Printing Unit, pp. 147-151.
25. Hill, R. A., G. M. Smith, R. M. Fuller, and N. Veitch, (2002). Landscape Modeling Using Integrated Airborne Multi-Spectral and Laser Scanning Data. International Journal of Remote Sensing, Vol. 23, No. 11, pp.2327-2334.
26. Jin, X. and C. H. Davis, (2005). Automated Building Extraction from High-Resolution Satellite Imagery in Urban Areas Using Structural, Contextual, and Spectral Information. EURASIP Journal on Applied Signal Processing, Vol. 14, pp. 2196-2206.
27. Kim, Taejung and J. P. Muller, (1996). Automated Urban Area Building Extraction from High Resolution Stereo Imagery. Image and Vision Computing, Vol. 14, pp. 115-130.
28. Lambert, T., (1998). Convex Hull Algorithms. [Online]. Available: http://www.cse.unsw.edu.au/~lambert/java/3d/hull.html
29. Lee, L. H., S. W. Shyue and M. J. Huang, (2007). Building Corner Feature Extraction Based on Fusion Technique with Airborne LiDAR Data and Aerial Imagery. IEEE The Third International Conference on Intelligent Information Hiding and Multimedia Signal Processing, November 26-28, Kaohsiung, Taiwan.
30. Lillesand, T. M. and R. W. Kiefer, (2000). Remote Sensing and Image Interpretation, Wiley & Sons, New York, pp. 724.
31. Ma, Ruijin, (2005). DEM Generation and Building Detection from LiDAR Data. Photogrammetry Engineering and Remote Sensing, Vol.71, No.7, pp. 847-854.
32. Martinez-Fonte, L., S. Gautama, and W. Philips, (2004). An Empirical Study of Corner Detection to Extract Buildings in very High Resolution Satellite Images. Proceedings of ProRISC, pp. 288-293.
33. Martinez-Fonte, L., S. Gautama, W. Philips, and W. Goeman, (2005). Evaluating Corner Detectors for the Extraction of Man-made Structures in Urban Areas. IEEE Geoscience and Remote Sensing Symposium, Vol. 1, pp. 237-240.
34. Masound, A. A. and M. M. Bayoumi, (1995). Using Local Structure for the Reliable Removal of Noise from the Output of the LoG Edge Detector. IEEE Transactions on Systems, Man, and Cybernetics, Vol. 25, No.2, pp. 328-337.
35. Mass, H. G. and G. Vosselman, (1999). Two Algorithms for Extracting Building Models from Raw Laser Altimetry Data. ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 54, pp. 153-163.
36. Moravec, H. P., (1977). Towards automatic visual obstacle avoidance. Proceedings of 5th International Joint Conference on Artificial Intelligence, Cambridge, Massachusetts, USA, pp. 584.
37. Rottensteiner, F., J. Trinder, S. Clode and K. Kubik, (2003). Building detection using LiDAR data and multi-spectral images. Proceedings of 7th Digital Image Computing: Techniques and Applications, Sun, C., Talbot, H., Ourselin, S. and Adriaansen, T. eds., Sydney, 10-12 Dec., pp. 673-682.
38. Rottensteiner, F., J. Trinder, S. Clode, and K. Kubik, (2005). Using the Dempster-Shafer method for the fusion of LiDAR Data and Multi-Spectral Images for Building Detection. Information Fusion, Vol. 6, No.4, pp. 282-300.
39. Schmid, C., R. Mohr, and C. Bauckhage, (2000). Evaluation of Interest Point Detectors. International Journal of Computer Vision, Vol. 37, No. 2, pp. 151-172.
40. Syed, S., P. Dare and S. Jones, (2005). Automatic Classification of Land Cover Features With High Resolution Imagery and Lidar Data: An Object-Oriented Approach. Proceedings of SSC2005 Spatial Intelligence, Innovation and Praxis: The National Biennial Conference of the Spatial Sciences Institute.
41. Tao, G. and Y. Yasuoka, (2002). Combining High Resolution Satellite Imagery and Airborne Laser Scanning Data for Generating bareland DEM in Urban Areas, Proceedings of International Workshop on Visualization and Animation of Landscape, International Archives of Photogrammetry, Remote Sensing and Spatial Information Science, Kunming, China, 26-28.
42. Wehr, Aloysius and U. Lohr, (1999). Airborne Laser Scanning－An Introduction and Overview. ISPRS Journal of Photogrammetry & Remote Sensing, Vol. 54, pp. 68-82.
43. Weidner, U. and W. Főrstner, (1995). Towards Automatic Building Extraction from High-Resolution Digital Elevation Models. ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 50, pp. 38-49.
44. Wikipedia, ConvexHull, [Online]. Available: http://en.wikipedia.org/wiki/Convex_hull Last access: 13:00 on 25/Dec/2007.
45. Zhang, K., J. Yan and S. C. Chen, (2006). Automatic Construction of Building Footprints From Airborne LiDAR Data. IEEE Transactions on Geoscience and Remote Sensing, Vol.41, No.9, pp. 2523-2533.