e no-line 
both data 
xtraction. 
ased ex- 
sirable to 
process- 
The rea- 
» twofold. 
the MRF 
el. They 
or objects 
use auto- 
)ck-snake 
  
  
  
Figure 9: Pipelines and roads extracted with ziplock snakes 
from posterior odds superimposed to interferometric SAR 
coherence. 
method has been developed for road extraction from optical 
images. It would possibly be more successful for automatic 
extraction, if it had been better adjusted to the appearance 
of the objects in its input derived from SAR data. 
ACKNOWLEDGMENTS 
The authors thank Kayser-Threde GmbH, München, for 
providing the SAR data. 
REFERENCES 
Caves, R., 1993. Automatic Matching of Features in Syn- 
thetic Aperture Radar Data to Digital Map Data. Disserta- 
tion, University of Sheffield, Dept. of Applied and Computa- 
tional Mathematics. 
Chou, P. B., Cooper, P. R., Swain, M. J., Brown, C. M. and 
Wixson, L. E., 1993. Probabilistic Network Inference for 
Cooperative High and Low Level Vision. In: R. Chellappa 
and A. Jain (eds), Markov Random Fields. Theory and Ap- 
plications, Academic Press, Boston, pp. 211—243. 
Fua, P. and Leclerc, Y., 1990. Model Driven Edge Detec- 
tion. Machine Vision and Applications 3, pp. 45—56. 
Geman, D. and Geman, S., 1984. Stochastic Relaxation, 
Gibbs Distribution, and the Bayesian Restoration of Im- 
ages. IEEE Transactions on Pattern Analysis and Machine 
Intelligence PAMI-6(6), pp. 721—741. 
Goodman, J. W., 1975. Statistical Properties of Laser 
Speckle Patterns. In: J. C. Dainty (ed.), Laser Speckle 
and Related Phenomena, Topics in Applied Physics, Vol. 9, 
Springer, Berlin, pp. 9-74. 
Hellwich, O., 1997.  Linienextraktion aus SAR-Daten 
mit einem Markoff-Zufallsfeld-Modell. Reihe C, Vol. 487, 
Deutsche Geodátische Kommission, München. 
Hellwich, O., 1998. Model Parameter Estimation Using 
Simulated Annealing. ISPRS Commission IIl Symposium, 
Columbus, Ohio, in print. 
Hellwich, O. and Streck, C., 1996. Linear Structures in SAR 
Coherence Data. In: International Geoscience and Remote 
Sensing Symposium 96, Lincoln, Vol. I, IEEE, pp. 330-332. 
Hendry, A., Quegan, S. and Wood, J., 1988. The Visibility 
of Linear Features in SAR Images. In: International Geo- 
science and Remote Sensing Symposium 88, Edinburgh, 
IEEE, pp. 1517-1520. 
Kass, M., Witkin, A. and Terzopoulos, D., 1987. Snakes: 
Active Contour Models. International Journal of Computer 
Vision 1(4), pp. 321-331. 
Koch, K.-R., 1990. Bayesian Inference with Geodetic Appli- 
cations. Lecture Notes in Earth Sciences, No. 31, Springer- 
Verlag, Berlin. 
Laptev, I., 1997. Road Extraction Based on Snakes and So- 
phisticated Line Extraction. Master's thesis, Computational 
Vision and Active Perception Lab (CVAP), Royal Institute of 
Technology, Stockholm, Schweden. 
Leberl, F. W., 1990. Radargrammetric Image Processing. 
Artech House, Norwood, MA. 
Lopes, A., Nezry, E., Touzi, R. and Laur, H., 1993. Structure 
Detection and Statistical Adaptive Speckle Filtering in SAR 
Images. International Journal of Remote Sensing 14(9), 
pp. 1735-1758. 
Neuenschwander, W., Fua, P, Székely, G. and Kübler, 
O., 1995. From Ziplock Snakes to Velcro™ Surfaces. 
In: Automatic Extraction of Man-Made Objects from Aerial 
and Space Images, Birkhäuser Verlag, Basel, Schweiz, 
pp. 105-114. 
Tough, R. J. A., Blacknell, D. and Quegan, S., 1994. Po- 
larimetric Radar: Mathematical Models and their Conse- 
quences. In: 3rd draft version, 17.03.94, submitted to the 
Proceedings of the Royal Society. 
Williams, L. and Jacobs, D., 1995. Stochastic Comple- 
tion Fields: A Neural Model of Illusory Contour Shape and 
Saliency. In: Fifth International Conference on Computer 
Vision, pp. 408—415. 
Winkler, G., 1995. Image Analysis, Random Fields and Dy- 
namic Monte Carlo Methods. Applications of Mathematics, 
Vol. 27, Springer-Verlag, Berlin. 
Intemational Archives of Photogrammetry and Remote Sensing. Vol. XXXII, Part 7, Budapest, 1998 537