ISPRS Commission II, Vol.34, Part 3A „Photogrammetric Computer Vision“, Graz, 2002
can also be used for the detection and separation of the
class settlement.
The described functions of GEOAIDA are easy to use, the
operators can solve complex grouping tasks by use of a
functional language.
4 CONCLUSIONS
The very flexible knowledge based interpretation system
GEOAIDA was introduced. GEOAIDA is based on the
functionality of existing image processing operators that
can be used context specific and can be initialized problem
specific. The arised hypothesis of the first step are grouped
and valued by use of context knowledge in the second step.
This approach enables a decision between alternative inter-
pretations and provides consistent results. The results can
be used as basis for maps or for geographic information
systems. The further development of GEOAIDA should
allow the multi-temporal interpretation of remote sensing
data. The detection of alteration can be used for environ-
mental studies, the development of urban areas and for ex-
amination of natural disasters.
REFERENCES
Aviad Z., Carnine P., 1988. Road Finding for Road-
Network Extraction. Proceedings, Computer Vision and
Pattern Recognition, IEEE, pp. 814-819.
Barzohar M., Cooper D., 1993. Automatic Finding of Main
Road in Areal Images by Using Geometric - Stochas-
tic Models and Estimation. Proceedings, Computer Vision
and Pattern Recognition, IEEE, pp. 459-464.
Baumgartner A., Eckstein W., Heipke C., Hinz S., Mayer
H., Radig B., Steger C., Wiedemann C., 1999. TUM-
Research on Road Extraction. Publisher: Christian Heipke
and Helmut Mayer, pp. 43-64.
Bückner J., Pahl M., Stahlhut O., 2000. GEOAIDA - A
Knowledge Based Automatic Image Data Analyzer for
Remote Sensing Data. CIMA 2001, Second International
ICSC Symposium on Advances in Intelligent Data Analy-
sis, June 19-22 2001, Bangor, Wales, U.K.
Bückner J., 1998. Model Based Road Extraction for the
Registration and Interpretation of Remote Sensing Data.
ISPRS Commission IV Symposium on 'GIS - Between Vi-
sions and Applications', Stuttgart, Germany, 7.9.-10.9.98.
Growe S., 2001. Wissensbasierte Interpretation multi-
temporaler Lufibilder. Dissertation, VDI Verlag GmbH,
Düsseldorf, 2001.
Tónjes, R., Growe, S., Bückner, J, Liedtke, C.-E., July
1999. Knowledge-Based Interpretation of Remote Sensing
Images Using Semantic Nets. Photogrammetric Engineer-
ing and Remote Sensing, 65(7), pp. 811-821.
Tônjes, R., 1999. Wissensbasierte Interpretation und 3D-
Rekonstruktion von Lanschafisszenen aus Lufibildern. Dis-
sertation, VDI Verlag GmbH, Düsseldorf, 1999.