i-house0067 | 0.98 || i-house0106 | 0.36
i-house0145 | 0.97 || i-house0184 | 0.93
i-house0223 | 0.84 || i-house0290 | 0.88
i-house0343 | 0.98 || i-house0410 | 0.86
i-house0449 | 0.95 || i-house0530 | 0.87
i-house0569 | 0.90 || i-house0636 | 0.64
i-house0703 | 0.95 || i-house0742 | 0.94
i-house0809 | 0.88 || i-house0848 | 0.85
i-house0887 | 0.98 || i-.block0940 | 0.79
i-block0979 | 0.90
Table 1: Model fidelity for the objects of the scene in Fig. 6
using the generic model and the context of the verified ob-
jects.
Visual inspection of the results of experiments has shown that
the measures defined for the model fidelity reflect the valu-
ations a human interpreter would qualitatively assign to the
“ given analysis state and that the presented measures can be
used successfully to guide the search in our image analysis
task. Several other factors also contribute to the success
of the analysis process, i.e. the compatibility measures com-
puted for the instances and modified concepts at the different
levels of the hierarchical model, although they are not in the
scope of this paper. We are currently extending our system
towards the recognition of composite objects like parking ar-
eas and allotments.
ACKNOWLEDGMENT
This work is supported by the Deutsche Forschungsgemein-
schaft (DFG).
REFERENCES
Findler, N. (1979). Associative Networks. Academic Press,
Orlando.
Kummert, F., Niemann, H., Prechtel, R., and Sagerer, G.
(1993). Control and explanation in a signal understand-
ing environment. Signal Processing, 32:111-145.
Matsuyama, T. and Hwang, V. (1990) SIGMA: A
Knowledge-Based Aerial Image Understanding System.
Advances in Computer Vision and Machine Intelligence.
Plenum Press, New York, London.
McKeown, D., Harvey, W., and McDermott, J. (1985). Rule
based interpretation of aerial imagery. /EEE Trans-
actions on Pattern Analysis and Machine Intelligence,
7(5):570—585.
Nicolin, B. and Gabler, R. (1987). A knowledge-based system
for the analysis of aerial images. IEEE Transactions on
Geoscience and Remote Sensing, 25(3):317-329.
Nilsson, N. (1982). Principles of artificial intelligence.
Springer-Verlag, Berlin.
Quint, F. (1995). An evidential merit function to guide
search in a semantic network based image analysis sys-
tem. Technical Report IPF-FQ-11/95, University of
Karlsruhe.
Quint, F. and Bàhr, H.-P. (1994). Feature extraction for
map based image interpretation. In Shi, X., Du, D.,
and Gao, W., editors, Third Internartional Colloquium
International Archives of Photogrammetry and Remote Sensing. Vol. XXXI, Part B3. Vienna 1996
Figure 6: Result of the image analysis process
of LIESMARS: Integration, Automation and Intelligence
in Photogrammetry, Remote Sensing and GIS, pages 1—
8, Wuhan, China.
Quint, F. and Landes, S. (1996). Colour aerial image segmen-
tation using a bayesian homogeneity predicate and map
knowledge. In Proceedings of the 18th ISPRS-Congress,
Vienna.
Quint, F. and Sties, M. (1995). Map-based semantic mo-
deling for the extraction of objects from aerial images.
In Grün, A., Kübler, O., and Agouris, P., editors, Auto-
matic Extraction of Man-Made Objects from Aerial and
Space Images, pages 307—316. Birkhäuser, Basel.
Sandakly, F. and Giraudon, G. (1994). Multispecialist system
for 3D scene analysis. In Cohn, A., editor, 11th Eu-
ropean Conference on Artificial Intelligence, ECAI 94,
pages 771-775. John Wiley & Sons, Ltd.
Shafer, G. (1976). A mathematical theory of evidence.
Princeton University Press.
Stilla, U. (1995). Map-aided structural analysis of aerial im-
ages. ISPRS Journal of Photogrammetry and Remote
Sensing, 50(4):3-10.
674
CO
KEY
ABST
Establ
especi:
of groi
bundle
This aj
only 5
results
the dis
betwee
À sig
mappi
to sca
coordi
of the
the cc
acces
prope
horizo
model
exami
neede
conve
a spar
densif
photo;
minim
points
additi
vertica
of con
Posit
adjusti
statioi
coordi
This p
groun
