International Archives of Photogrammetry and Remote Sensing, Vol. 32, Part 7-4-3 W6, Valladolid, Spain, 3-4 June, 1999 
image 
radiometric 
calibration 
redefinition of 
segm. param. 
Fig. 7, Workflow of interrelated segmentation and 
classification. 
Figures 8 and 9 illustrate this workflow. Figure 8 is an 
intermediate result after the first segmentation and mixed pixel 
elimination. The category assignment comes from the seed 
pixels. Figure 9 is the final result, when all pixels have been 
assigned to a segment. In this example, fifteen categories are 
distinguished (4 types of built-up land, 6 different crop types, 2 
grassland types, wetland, water, and forest) 
5. CONCLUSIONS 
It has been demonstrated that by using a method of interrelated 
segmentation and classification in landcover mapping, better 
results can be obtained than with sequential segmentation and 
classification. 
Possible improvements of this method concern the automation 
of the radiometric self-calibration, further development of the 
spatial subpixel segmentation, as well as the refinement of the 
generic knowledge base for landcover identification. 
ACKNOWLEDGEMENTS 
This work was financed by the Austrian “Fonds zur Förderung 
der wissenschaftlichen Forschung” (FWF, project S7003) and 
by the Austrian Federal Ministry of Research and Traffic as part 
of the research programme “Sustainable Development of the 
Austrian Landscapes”. 
REFERENCES 
Bischof, H„ Schneider, W. and Pinz, A. J., 1992. Multispectral 
Classification of Landsat-Images Using Neural Networks. IEEE 
Transactions on Geoscience and Remote Sensing, 30(3), pp. 
482 - 490. 
Fu, K. S. and Mui, J. K., 1983. A Survey on Image 
Segmentation. Pattern Recognition 13, pp. 3-16. 
Gonzales, R. C., Woods, R. E., 1993. Digital Image Processing. 
Addison-Wesley, Reading, Massachusetts. 
Gorte, B„ 1998. Segmentation Pyramid Classification. In: 
International Archives of Photogrammetry and Remote Sensing, 
Vol. 32, Part B3/1, pp. 225-232. 
Haralick, R. M., Shapiro, L. G., 1992. Computer and Robot 
Vision. 2 Volumes, Addison-Wesley, Reading, Massachusetts. 
Pal, N. R. and Pal, S. K., 1993. A Review on Image 
Segmentation Techniques. Pattern Recognition 26(9), pp. 1277- 
1294. 
Schneider, W., 1993. Landuse mapping with subpixel accuracy 
from Landsat TM image data. In: Remote Sensing and Global 
Environmental Change, Proc. of the 25th ERIM Symposium, 
Vol. H, pp. 155-161. 
Settle, J. J. and Drake, N. A., 1993. Linear mixing and the 
estimation of ground cover proportions. Int. J. Remote Sensing 
14(6), pp. 1159-1177. 
Steinwendner, J. and Schneider, W., 1998. Algorithmic 
improvements in spatial subpixel analysis of remote sensing 
images. In: Schuster (Ed.), Pattern Recognition 1998, Proc. 22 nd 
OAGM Workshop, pp. 205-213. 
Steinwendner, J. and Schneider, W„ 1999. Radiometric Self- 
Calibration of Remote Sensing Images for Generic Knowledge- 
Based Image Analysis. In: Proc. 23 nd OAGM Workshop, in 
print. 
Steinwendner, J., Schneider, W. and Suppan, F., 1998. Vector 
segmentation using multiband spatial subpixel analysis for 
object extraction. In: International Archives of Photogrammetry 
and Remote Sensing, Vol. 32, Part B3/1, pp. 265-271. 
Tanre, D., Deroo, C., Duhaut, P., Herman, M., Morcrette, J.J., 
Perbos, J., Deschamps, P.Y, 1990. Description of a computer 
code to simulate the satellite signal in the solar spectrum: the 5s 
code. Int. J. Remote Sensing, 11(4), pp. 659 - 668. 
Vermote, E., Tanrd, D., Deuze, J. L., Herman, M., Morcrette, 
J.J., 1997. Second Simulation of the Satellite Signal in the Solar 
Spectrum (6S): User's Guide. Technical Report Version 2, Dept, 
of Geography, Univ. of Maryland, c/o NASA-Goddard Space 
Flight Center - Code 923, Greenbelt, MD 20771, USA. 
Vincent, L. and Soille, P., 1991. Watersheds in digital spaces: 
An efficient algorithm based on immersion simulation. IEEE 
Transactions on Pattern Analysis and Machine Intelligence, 
13(6), pp. 583-598.