Automatic modelling and 3D reconstruction of urban house roofs from high resolution aerial imagery

  • Theo Moons
  • David Frère
  • Jan Vandekerckhove
  • Luc Van Gool
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1406)


Many tasks in modern urban planning require 3-dimensional (3D) spatial information, preferably in the form of 3D city models. Constructing such models requires automatic methods for reliable 3D building reconstruction. House roofs encountered in residential areas in European cities exhibit a wide variety in their shapes. This limits the use of predefined roof models for their reconstruction. The strategy put forward in this paper is, first, to construct a polyhedral model of the roof structure, which captures the topology of the roof, but which might not be very accurate in a metric sense; and then, in a second step, to improve the metric accuracy by fitting this model to the data. This decoupling of topology extraction from metric reconstruction allows a more efficient roof modelling involving less criteria. And, restricting the processing, at all stages, to one or just a few roof structures, by using a colour-based segmentation of the images, allows to use constraints that are not very tight. The approach has been tested on a state-of-the-art dataset of aerial images of residential areas in Brussels.


Line Segment Geographical Information System Aerial Image Reprojection Error Roof Structure 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    E.P. Baltsavias, W. Eckstein, E. Gülch, M. Hahn, D. Stallmann, K. Tempfli, and R. Welch (eds.), 3D Reconstruction and Modelling of Topographic Objects, Internationa] Archives of Photogrammetry and Remote Sensing, Vol. 32 Part 3-4W2, International Society of Photogrammetry and Remote Sensing, Sydney, 1997.Google Scholar
  2. 2.
    F. Bignone, O. Henricsson, P. Fua and M. Stricker, Automatic extraction of generic house roofs from high resolution aerial imagery, in: B. Buxton and R. Cipolla (eds.), Computer Vision — ECCV'96, Lecture Notes in Computer Science 1064, Springer-Verlag, Berlin, 1996, pp. 85–96.Google Scholar
  3. 3.
    R.T. Collins, A.R. Hanson, M.R. Riseman and H. Schultz, Automatic extraction of buildings and terrain from aerial images, pp. 169–178, in [8].Google Scholar
  4. 4.
    O. Faugeras, S. Laveau, L. Robert, G. Csurka and C. Zeller, 3-D reconstruction of urban scenes from sequences of images, pp. 145–168, in [8].Google Scholar
  5. 5.
    A. Fischer, T.H. Kolbe and F. Lang, F., Integration of 2D and 3D Reasoning for Building Reconstruction Using a Generic Hierarchical Model, pp. 159–180, in [6].Google Scholar
  6. 6.
    W. Förstner, F. Plümer and L. Plümer, Semantic Modeling for the Acquisition of Topographic Information from Images and Maps, Birkhäuser-Verlag, Basel, 1997.Google Scholar
  7. 7.
    E. Gülch, Application of semi-automatic building acquisition, pp. 129–138, in [9].Google Scholar
  8. 8.
    A. Grün, O. Kübler and P. Agouris, Automatic Extraction of Man-Made Objects from Aerial and Space Images, Birkhäuser-Verlag, Basel, 1995.Google Scholar
  9. 9.
    A. Grün, E.P. Baltsavias and O. Henricsson, Automatic Extraction of Man-Made Objects from Aerial and Space Images (II), Birkhäuser-Verlag, Basel, 1997.Google Scholar
  10. 10.
    N. Haala, C. Brenner and K.-H. Anders, Generation of 3D city models from Digital Surface Models and 2D GIS, pp. 68–76, in [1].Google Scholar
  11. 11.
    R. Hartley, Lines and points in three views — a unified approach, Proc. ARPA Image Understanding Workshop (IUW '94), Monterey, CA, 1994, pp. 1009–1016.Google Scholar
  12. 12.
    J. Mc Glone and J. Shuffelt, Projective and object space geometry for monocular building extraction, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR '94), Seattle, Washington, June 1994, pp. 54–61.Google Scholar
  13. 13.
    R. Nevatia, C. Lin and A. Huertas, A system for building detection from aerial images, pp. 77–86, in [9].Google Scholar
  14. 14.
    M. Roux and D. Mc Keown, Feature matching for building extraction from multiple views, Proc. ARPA Image Understanding Workshop (IUW'94), Monterey, CA, 1994, pp. 331–349.Google Scholar
  15. 15.
    M. Roux and H. MaÎtre, Three-dimensional description of dense urban areas using maps and aerial images, pp. 311–322, in [9].Google Scholar
  16. 16.
    A. Shashua, Algebraic functions for recognition, IEEE Trans. on Pattern Analysis and Artificial Intellingence (T-PAMI), Vol. 17 (1995), no. 8, pp. 779–789.CrossRefGoogle Scholar
  17. 17.
    F. Stolle, A. Hanson, C. Jaynes, E. Riseman, and H. Schultz, Scene Reconstruction research — towards an automatic system, pp. 33–42, in [9].Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Theo Moons
    • 1
  • David Frère
    • 1
  • Jan Vandekerckhove
    • 1
  • Luc Van Gool
    • 1
  1. 1.ES AT/PSIKatholieke Universiteit LeuvenLeuvenBelgium

Personalised recommendations