pairs of
itible la-
paramet-
riminant
observa-
a (unary
led as to
Optimal
the deci-
However,
tic labels
inary at-
ment im-
ire which
in such a
has max-
ibutes si-
that is, a
. There-
nantic la-
Thus, in
r geomet-
troduced
s at other
of-the-art
he image
netrically
ize corre-
segments
1e precise
quality of
ing is ap-
upper left
'onstructed
the recon-
'e detailed
all differ-
ht side of
(b) shows
ing in Fig-
ide do not
driven by
onstructed
found.
novel ap-
ling roofs.
cal imple-
ıture work
ble in the
he goal to
initialize roof models with even less evidence in 3D space.
Another research direction, which is pursued at the mo-
ment, is oriented toward the optimization of the geometric
accuracy of the models using back-projection into the in-
put images.
Acknowledgement: The authors gracefully acknowledge
support of the ETH project AMOBE II and the European
IST project CogViSys.
(a)
(b)
Figure 8: (a,b): Three-dimensional view of reconstructed
building roofs. The non-trivial roof structures are captured
to their full extent. Thin lines show the input 3D segments.
REFERENCES
Ault, H. K., 1999. Using Geometric Constraints to Cap-
ture Design Intent. Journal for Geometry and Graphics 3,
pp. 39-45.
Baillard, C. and Zisserman, A., 2000. A Plane-Sweep
Strategy for the 3D Reconstruction of Buildings from Mul-
tiple Images. In: International Archives of Photogramme-
try and Remote Sensing, Vol. 33 part B2, pp. 56-62.
Baltsavias, E., Grün, A. and Van Gool, L., 2001. Auto-
matic Extraction of Man-Made Objects from Aerial and
Space Images. Balkema Publishers, Rotterdam.
Christmas, W. J., Kittler, J. and Petrou, M., 1995. Struc-
tural Matching in Computer Vision Using Probabilistic Re-
laxation. PAMI 17, pp. 749—764.
Cord, M., Jordan, M. and Cocquerez, J.-P., 2001. Accurate
Building Structure Recovery from High Resolution Aerial
Imagery. CVIU 82(2), pp. 138-173.
Fischer, A., Kolbe, T., Lang, F., Cremers, A., Fórstner, W.,
Plümer, L. and Steinhage, V., 1998. Extracting Buildings
from Aerial Images Using Hierarchical Aggregation in 2D
and 3D. CVIU 72(2), pp. 185-203.
Fisher, R. A., 1936. The use of Multiple Measurements in
Taxonometric Problems. Ann. Eugenics 7, pp. 179-188.
Gamma, E., Helm, R., Johnson, R. and Vlissides, J., 1995.
Design Patterns. Addison-Wesley.
Griin, A., Baltsavias, E. and Henricsson, O., 1997. Au-
tomatic Extraction of Man-Made Objects from Aerial and
Space Images. Birkhäuser-Verlag, Basel / Boston / Berlin.
Grün, A., Kübler, O. and Agouris, P., 1995. Automatic
Extraction of Man-Made Objects from Aerial and Space
Images. Birkhäuser-Verlag, Basel / Boston / Berlin.
Henricsson, O., 1998. The Role of Color Attributes
and Similarity Grouping in 3-D Building Reconstruction.
CVIU 72(2), pp. 163-184.
Heuel, S. and Fórstner, W., 2001. Topological and Geo-
metrical Models for Building Reconstruction from Multi-
ple Images. In: [Baltsavias et al., 2001]
Kulschewski, K., 1997. Building Recognition with
Bayesian Networks. In: W. Fórstner and L. Plümer (eds),
SMATI.
Mayer, H., 1999. Automatic Object Extraction from Aerial
Imagery — A Survey Focusing on Buildings. CVIU 74(2),
pp. 138-149.
Moons, T., Frere, D., Vandekerckhove, J. and Van Gool,
L., 1998. Automatic Modelling and 3D Reconstruction of
Urban House Roofs from High Resolution Aerial Imagery.
ECCV 1, pp. 410-425.
Institue of Geodesy and Photogrammetry, 2001. Dataset
of Zürich Hoengg. Swiss Federal Institute of Technology
(ETH) Zürich, CH-8093 ETH Hoenggerberg, Switzerland.
Scholze, S., 2002. Bayesian Model Selection for Plane Re-
construction. Technical Report BIWI-TR-259, Commu-
nication Technology Laboratory, Computer Vision Group,
ETH, Ziirich, Switzerland.
Scholze, S., Moons, T., Ade, F. and Van Gool, L., 2000.
Exploiting Color for Edge Extraction and Line Segment
Stereo Matching. In: IAPRS, Vol. 33, pp. 815-822.
Scholze, S., Moons, T. and Van Gool, L., 2001. A prob-
abilistic approach to roof patch extraction and reconstruc-
tion. In: [Baltsavias et al., 2001]
Seybold, B., Metzger, F., Ogan, G., Bathelt, J., Collen-
berg, F., Taiber, J., Simon, K. and Engeli, M., 1997. Spatial
Modelling with Geometric Constraints. In: Proc. 3rd Inter-
national Conference of Pratical Application of Constraint
Technology, pp. 307-320.
—209—
Lt iac aU ES