International Archives of Photogrammetry and Remote Sensing, Vol. 32, Part 7-4-3 W6, Valladolid, Spain, 3-4 June, 1999 
82 
applied. As the digitizing of the new training areas is very time 
intensive, we are aiming at the derivation of the training areas 
from already existing GIS data. This can be realized, if we 
assume that the number of wrongly captured GIS objects are 
substantially less than the number of all GIS objects of the 
dataset. 
Another open problem is the homogeneous quality of the 
different data sources, which is required over the whole test area 
for the approach. This premise can for example be violated for 
the spectral data due to occlusions near buildings. At these 
regions no spectral information is available. Additionally, as 
discussed above, insufficiencies of the laser scanner can result 
in small areas, where the laser beam is not reflected. So even 
though very promising result could be achieved, additional 
effort, especially at the above mentioned regions, for data 
acquisition and processing is required. 
REFERENCES 
Baltsavias, E., Mason, S. and Stallmann, D., 1995: Use of 
DTMs/DSMs and Orthoimages to Support Building Extraction. 
In: Automatic Extraction of Man-Made Objects from Aerial and 
Space Images, Birkhäuser Verlag, Basel, pp. 199-210. 
Brunn A. and Weidner U., 1997 Extracting Buildings from 
Digital Surface Models. In: IAPRS, Vol.32, Part 3-4W2, pp. 
27-34. 
Hahn, M. and Statter, C., 1998: A scene labelling strategy for 
terrain feature extraction using multisource data. In: IAPRS, 
Vol.32, Part 3/1, pp. 435-441. 
Lillesand, T. and Kiefer, R. 1994. Remote Sensing and Image 
Interpretation. John Wiley and Sons, New York. 
Lohr U., 1997. Digital Elevation Models by Laserscanning: 
Principle and Applications. In: Proc. Third International 
Airborne Remote Sensing Conference and Exhibition, pp.174- 
180. 
Price K. and Huertas A. 1992. Using Perceptual Grouping to 
Detect Objects in Aerial Scenes. In: IAPRS, Vol.29, Part B3, 
pp. 842-855. 
Savian, F. R. and D. Landgrebe, 1991. A survey of decision tree 
classifier methodology. IEEE Transactions on Systems, Man 
and Cybernetics, Vol. 21, No. 3, pp. 660-674. 
Walter, V., 1998. Automatic Classification of Remote Sensing 
Data for GIS Database Revision. In: IAPRS Vol. 32, Part 4, pp. 
641-648. 
Weidner, U. and Forstner, W., 1995. Towards Automatic 
Building Extraction from High Resolution Digital Elevation 
Models, ISPRS Journal of Photogrammetry and Remote 
Sensing, Vol. 50, No. 1, pp. 38-49.