ray EEE EEE 
-parametric 
with M =0 
tion regions 
figure 9 (b). 
rage and the 
nd temporal 
yy using the 
» parametric 
idy, we will 
ng to degree 
ed based on 
See’ | NSA] FT] ep | 
Yosuke Ito 
  
  
(a) LVQ with M — 6 (b) ML 
Figure 9: Classification images using C» 
ACKNOWLEDGMENTS 
The SAR data used in this study were provided by National Space Development Agency of Japan (NASDA). The authors 
would like to thank JPL, NASA, Dr Shimada at NASDA and Dr Hanaizumi at Hosei University, Japan for the inter- 
ferometric SAR software. The image processing facilities are supported by the University of London Inter-Collegiate 
Research Services. 
REFERENCES 
Fujisawa, S., Rosen, P. A., 1998. Crustal deformation measurements using repeat-pass JERS 1 synthetic aperture radar 
interferometry near the Izu Peninsula, Japan, Journal of Geophysical Research, 103(B2), pp. 2411-2426. 
Ito, Y., Omatu, S., 1997. Category classification method using a self-organizing neural network, International Journal of 
Remote Sensing, 18(4), pp. 829-845. 
Kohonen, T., 1997. Self-Organizing Maps. Springer, Berlin, pp. 203-217. 
Lee, H., Liu, J. G., 1999. Spatial decorrelation due to topography in the interferometric SAR coherence imagery. In: 
IEEE International Geoscience and Remote Sensing Symposium (IGARSS’99) Proceedings, Hamburg, Germany, Vol. 1, 
pp. 485-487. 
Richards, J. A., 1993. Remote Sensing Digital Image Analysis. Springer-Verlag, Berlin, pp. 271—275. 
Yonezawa, C., Takeuchi, S., 1999. Detection of urban damage using interferometric SAR decorrelation. In: IEEE Interna- 
tional Geoscience and Remote Sensing Symposium (IGARSS'99) Proceedings, Hamburg, Germany, Vol. 2, pp. 925-927. 
Zebker, H. A., Villasenor, J., 1992. Decorrelation in interferometric radar echoes. IEEE Transactions on Geoscience and 
Remote Sensing, 30(5), pp. 950—959. 
  
International Archives of Photogrammetry and Remote Sensing. Vol. XXXIII, Part Bl. Amsterdam 2000. 163