數碼城市的應用在近年內越來越普及，且廣受各界的注重。然而，
針對數據和圖資的取得管道與高額的費用，以及如何開發有效率
的三維建物模型建製之標準作業程序，皆需去克服與改進。
本研究所提出的演算法能利用網路上提供的完全免費的數據（包
含衛星、航照與街景影像）來建製三維建物模型。此特性將有助
於部份資源有限的國家或地區，在現有圖資的條件下建製出基礎
的三維建物模型。為了達成此目標，本研究提出了一個融合各類
影像的作業流程，主要分為兩個步驟：1.建築物辨識：藉由航遙
測影像偵測出建物的外輪廓線；2.不同細緻成度的三維建物模型
建造。
第一階段包括影像增揚、分類、邊緣檢測、影像形態演
算法、向量化與規則化;
第二階段則由平面區塊建立出積木模型
(BlockModel)，並針對著名地標建立包括紋理敷貼的高細緻度模
型。
研究結果顯示所提出的方法能成功且有效的利用免費的圖資與數
據建製三維建物模型，在測試區1224棟建築物影像當中，成功偵
測出1150棟建築物，達到93.94％的完成度。重建的三維模型在平
面的位置有相較合理的準確度。本研究利用開放資料及影像，開
發出相對低成本的三維建物模型建製程序，其成果適用於都市規
劃或防災演練等領域當中。

In recent years, cyber cities have become very popular and useful in many applications.
However many problems remain unaddressed, specially those related to the difficult and
expensive acquisition of the data required to create three dimensional (3D) building models
and the tedious and time consuming procedures to be carried out.
The objective of this study is to propose a procedure for creating 3D building models using
completely free data available on the internet including satellite and ground images. The
proposed approach can be used as a framework for building spatial datasets (3D building
models) for countries or regions with limited access to advanced commercial and other spatial
data sources. In order to achieve this goal, a combination of different image processing
algorithms were performed. The entire process was divided into two main parts: buildings
detection, in which the purpose is the determination of the building outlines of the city
through an object-based analysis, and the creation of the 3D building model in different levels
of detail (LOD). The first phase comprises tasks of image enhancements, classification, edge
detection, mathematical image morphology algorithms, vectorization, regularization and
refinement. The second phase includes the building modeling from floor plans, and the
creation of highly detailed models for a few landmark buildings, including textures mapping,
selection, croppig, rotation and inpainting.
The final results prove that the proposed approach is effective for creating 3D building
models using free data. A quantitative analysis indicates that 1150 buildings out of the 1224
buildings shown in the image were successfully extracted, achieving 93.94% of completeness.
The reconstructed 3D building models are also accurate in terms of location. The method
proposed in this study provides a relatively economical alternative for creating 3D city
models from freely available images and other data. The generated models can be used for
different applications such as city planning and location-based service.

1) Benner, J., Geiger, A. and Leinemann, K., 2005. Flexible Generation of Semantic 3D
Building Models. Gröger/Kolbe (Eds.), Proc of the 1st Intern. Workshop on Next
Generation 3D City Models. Forschungszentrum Karlsruhe, Institut für Angewandte
Informatik, Karlsruhe, Germany.
2) Chen, C. H. and Pau, L. F., 1998. The Handbook of Pattern Recognition and
Computer Vision (2nd Edition). P. S. P. Wang (eds.), pp. 207-248.
3) Dollner, J., Buchholz, H. and Brodersen, F., 2005. Smart Buildings- a concept for adhoc
creation and refinement of 3D building models. Groger/Kolbe (Eds.), Prod. of the
1st Intern. Workshop on Next Generation 3D City Models, Bonn 2005, EuroSDR
publication #49. Potsdam, Germany.
4) Forstner, W., 1999. 3D City Models: Automatic and Semiautomatic Acquisiton
Methods. D. Fritsch & R. Spiller, Eds., pp. 291-303, Photogrammetric week ‘99’.
Wichmann Verlag, Heidelberg, Germany.
5) Gökhan, H. and Aksoy, S., 2008. Automatic Detection of Geospatial Objects Using
Multiple Hierarchical Segmentations. IEEE Transactions on Geoscience and Remote
Sensing, vol. 46, No. 7, pp. 2097-2111.
6) Gonzales, R. C. and Woods, R. E., 2010. Digital Image Processing, third edition.
Pearson Education, Inc., NJ, USA.
7) Haala N. Bohm, J. and Kada M., 2002. Processing of 3D Builiding Models for
Location Aware Applications. IAPARS, Volume XXXIV, Germany, 2002.
8) Haala, N. and Kada, M., 2005. Panoramic Scenes for Texture Mapping of 3D City
Models. IAPARS, Volume XXXVI-5/W8, Berlin, 2005.
69
9) Huertas, A. and Nevatia, R., 1998. Detecting Buildings in Aerial Images. Computer
Vision, Graphics, and Image Processing, Vol. 41, pp. 131-152.
10) Irvin, R. B. and Mckeown, D. M., 1989. Methods for Exploiting the Relationship
Between Buildings and Their Shadows in Aerial Imagery. IEEE Transactions on
Systems. Man, And Cybernetics, Vol. 19, No. 6, pp. 1564-1575.
11) Kada, M., Klinec, D. and Haala, N., 2005. Facade Texturing for Rendering 3D City
Models. ASPRS 2005 Annual Conference, pp. 78-85.
12) Ledoux, H. and Meijers, M., 2009. Extruding Building Footprints to Create
Topologically Consistent 3D City Models. Urban and Regional Data Management -
UDMS Annual 2009, pp. 39-48.
13) Lee, S. C. and Nevatia, R., 2003. Interactive 3D Building Modeling Using a
Hierarchical Representation. First IEEE International Workshop on Higher-Level
Knowledge in 3D Modelling and Motion Analysis, pp. 58-65.
14) Lillesand, T. M., Kiefer, R. W. and Chipman, J. W., 2008. Remote Sensing and
Image Interpretation, sixth edition. John Wiley & Sons, Inc. United States of America.
15) Lin, C. and Nevatia, R., 1998. Building Detection and Description from a Single
Intensity Image. Computer Vision and Image Understanding Vol. 72, No. 2,
November, pp. 101-121.
16) Lin, C., Huertas, A. and Nevatia, R., 1994. Detection of Buildings Using Perceptual
Grouping and Shadows. IEEE Computer Society Conference on Computer Vision
and Pattern Recognition, pp. 62-69.
17) Liow, Y. T. and Pavlidis, T., 1989. Use of Shadows for Extracting Buildings in
Aerial Images. Computer Vision, Graphics and Image Processing, Vol. 49, pp. 242-
277.
70
18) Miller, D. L. and Ziders, D., 2007. Create 3D Buildings in SketchUp and Position
Them in ArcScene. ArcUser October-December, pp. 43-45.
19) Neil, C. and Lynne, L., 2001. Change Detection for Linear Features in Aerial
Photographs Using Edge-Finding. IEEE Transactions on Geoscience and Remote
Sensing, Vol. 39, No. 7, pp. 1608-1612.
20) Niederost, M., 2000. Reliable Reconstruction of Buildings for Digital Map Revision.
IAPRS, Vol. XXXIII, Amsterdam, 2000.
21) Paparoditis, N., Cord, M., Jordan, M. and Cocquerez, J., 1998. Building Detection
and Reconstruction from Mid- and High-Resolution Aerial Imagery. Computer
Vision and Image Understanding, Vol. 72, No. 2, November, pp. 122-142.
22) Santos, S. S., Dionísio, M. and Rodrigues, N., 2011. Efficient Creation of 3D Models
from Buildings Floor Plans. International Journal of Interactive Worlds, Vol. 2011,
Article ID 897069, 30 pages.
23) Stamos, I. and Allen, P.K., 2000. 3D Model Construction Using Range and Image
Data. IEEE Conference on Computer Vision and Pattern Recognition, Vol. 1, pp.
531-536.
24) Tsai, F. and Lin, H. C., 2006. Polygon-based Texture Mapping for Cyber City 3D
Building Models. International Journal of Geographical Information Science, Volume
21, Issue 9, pp. 965-981.
25) Tupin, F., Houshmand, B. and Datcu, M., 2002. Road Detection in Dense Urban
Areas Using SAR Imagery and the Usefulness of Multiple Views. IEEE Transactions
on Geosciences and Remote Sensing, Vol. 40, Issue 11, pp. 2405-2414.
26) Tupin, F. and Roux, M., 2003. Detection of Building Outlines Based on the Fusion of
SAR and Optical Features. ISPRS Journal of Photogrammetry & Remote Sensing,
Volume 58, Issues 1-2, pp. 71-82.
71
27) Vosselman, G. and Digkman, S., 2001. 3D Building Model Reconstruction from
Point Clouds and Ground Plans. International Archives of Photogrammetry and
Remote Sensing, Volume XXXIV-3/W4 Annapolis, MD, 22-24 Oct., pp. 37-43.
28) Wei, Y. F., Zhao, Z. M. and Song, J. H., 2004. Urban Building Extraction from Highresolution
Satellite Panchromatic Image Using Clustering and Edge Detection. IEEE
International Geoscience and Remote Sensing Symposium, Vol. 3, pp. 2008-2010.
29) Zhang, Y., 1999. Optimization of Building Detection in Satellite Images by
Combining Multispectral Classification and Texture Filtering. ISPRS Journal of
Photogrammetry & Remote Sensing, Vol. 54, pp. 50–60.