photo. 
and road 
ires. The 
tain input 
This type 
egment in 
e matches 
Tal Abramovich 
  
One of the important factors of the method is the selection of the membership functions of the fuzzy rules. 
Future research should concentrate on testing the sensitivity of the output value to the selection of the 
membership functions. In addition, the incorporation of more rules, which are founded on prior knowledge 
about roads and on the possible available data in the GIS and in the extracted image information, should be 
examined. It is expected that the methodology presented here will be incorporated in a general automated GIS 
updating framework. 
ACKNOWLEDGMENTS 
This research was partially supported by Technion V.P.R. Fund - M. and C. Papo Research Fund. 
REFERENCES 
Agouris, P, Gyftakis, S, Stefanidis, A., 1998. Using a fuzzy supervisor for object extraction within an integrated 
geospatial environment. International Archives of Photogrammetry and Remote Sensing, 32(3/1):191-195. 
Baumgartner, A., Steger, C., Wiedemann, C., Mayer, H., Eckstein, W. and Ebner, H., 1996. Update of roads in 
GIS from aerial imagery: verification and multi-resolution extraction. International Archives of 
Photogrammetry and Remote Sensing, 31(B3):53-58. 
Heipke, C., Mayer, H. and Wiedemann, C., 1997. Evaluation of automatic road extraction. International 
Archives of Photogrammetry and Remote Sensing, 32(3-2W3): 47-56. 
Zadeh L. A., 1973. Outline of a new approach to the analysis of complex systems and decision processes. 
IEEE Trans. on Systems, Man, and Cybernetics, vol. 3, pp. 28-44. 
  
International Archives of Photogrammetry and Remote Sensing. Vol. XXXIII, Part B3. Amsterdam 2000. 23