The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B3b. Beijing 2008 
object to a coarser resolution was given. Despite the simplicity 
of the context object model, the example indicates the capability 
of the adaptation method, as the adapted models successfully 
extract both the road and the vehicle in target resolution. 
Although the adaptation is demonstrated here only for a certain 
type of vehicles, other local context objects, such as trees or 
buildings can be incorporated in the same way by replacing the 
vehicle model with their respective model(s). 
In order to preserve the flexibility of the position of local 
context objects, the scale behaviour for the landscape object of 
interest and the context object is predicted separately. Due to 
this separation, the scale behaviour prediction is not exact for 
the local context, since no scale events between the primary 
object and the local context objects or among the context 
objects can be detected. However, manually created object 
models for a certain image resolution and the corresponding 
feature extraction operators of local context objects also cannot 
consider possible scale events of local context due to their 
extreme variability of location. Against this background, the 
presented separate adaptation approach appears reasonable. 
Nevertheless, a holistic scale behaviour approach with statistical 
prediction including both the landscape object of interest and 
the local context could improve the presented more pragmatic 
solution. 
ACKNOWLEDGEMENTS 
This study has been funded by Deutsche Forschungs 
gemeinschaft under grant HE 1822/13. The project is part of the 
bundle “Abstraction of Geoinformation in Multi-Scale Data 
Acquisition, Administration, Analysis, and Visualisation”. 
REFERENCES 
Baumgartner A., Eckstein W., Mayer H., Heipke C., Ebner H., 
1997. Context-supported road extraction. In: Grün A., 
Baltsavias E., Henricsson O. (Eds.), Automatic Extraction of 
Man-made Objects from Aerial Images (II), Birkhäuser, Basel, 
pp. 299-308. 
Butenuth, M., Straub, B., Heipke, C., and Willrich, F., 2003. 
Tree Supported Road Extraction from Arial Images Using 
Global and Local Context Knowledge. LNCS, 2626, pp. 162- 
171. 
Gerke, M., 2006. Automatic Quality Assessment of Road 
Databases Using Remotely Sensed Imagery. DGK, Series C, No. 
599, Munich, 103 p. 
Heuwold, J., 2006. Verification of a methodology for the 
automatic scale-dependent adaptation of object models. In: The 
International Archives of the Photogrammetry, Remote Sensing 
and Spatial Information Sciences, Vol. XXXVI, Part 3, pp. 
173-178. 
Heuwold, J., Pakzad, K., Heipke, C. 2007. Scale behaviour 
prediction of image analysis models for 2D landscape objects. 
In: The International Archives of the Photogrammetry, Remote 
Sensing and Spatial Information Sciences, Vol. XXXVI, Part 
3/W49A, pp. 43-49. 
Hinz, S., and Baumgartner, A., 2003. Automatic extraction of 
urban road networks from multi-view aerial imagery. ISPRS 
Journal of Photogrammetry & Remote Sensing, 58, pp. 83-98. 
Hinz, S. 2004. Automatische Extraktion urbaner Straßennetze 
aus Luftbildern. DGK, Series C, No. 580, Munich, 131 p. 
Koenderink, J., 1984. The Structure of Images. Biological 
Cybernetics, 50(5), pp. 363-370. 
Lindeberg, T., 1994. Scale-Space Theory in Computer Vision. 
Dordrecht, The Netherlands, Kluwer Academic Publishers, 
423p. 
Liu, G., Zhuge, F., Gong, L., and Haralick, R., 1999. Vehicle 
Detection in Aerial Imagery and Performance Evaluation. 
Technical Report, University of Washington, Seattle, WA. 
Mayer, H. and Steger, C., 1998. Scale-space events and their 
link to abstraction for road extraction. ISPRS Journal of 
Photogrammetry & Remote Sensing, 53(2), pp. 62-75. 
Mayer, H., 2008. Object extraction for photogrammetric image 
analysis. ISPRS Journal of Photogrammetry & Remote Sensing, 
63(2), pp. 213-222. 
Meyer, H., 2006. Extraktion von Fahrzeugen als Kontextobjekte 
in optischen Bilddaten. Bachelor thesis, University of Hannover, 
Germany, 73p., unpublished. 
Stilla, U., Michaelsen, E., Soergel, U., Hinz, S., and Ender, J. 
2004. Airborne Monitoring of Vehicle Detection in Urban 
Areas. In: The International Archives of the Photogrammetry, 
Remote Sensing and Spatial Information Sciences, Vol. XXXV, 
Part B3, pp. 973-979. 
Tönjes, R., Growe, S., Bückner, J. and Liedtke, C.-E., 1999. 
Knowledge Based Interpretation of Remote Sensing Images 
Using Semantic Nets. Photogrammetric Engineering & Remote 
Sensing, 65(7), pp. 811-821. 
Witkin, A., 1983. Scale Space Filtering. In: Proceedings of the 
8th Int. Joint Conference on Artificial Intelligence, Karlsruhe, 
pp. 1019-1022. 
Zhang, C., 2004. Towards an operational system for automated 
updating of roaddatabases by integration of imagery and 
geodata. ISPRS Journal of Photogrammetry & Remote Sensing, 
58, pp. 166-186. 
Zhao, T., and Nevatia, R., 2003. Car detection in low resolution 
aerial images. Image and Vision Computing, 21, pp. 693-703.