In: Wagner W., Székely, B. (eds.): ISPRS TC VII Symposium - 100 Years ISPRS, Vienna, Austria, July 5-7, 2010, IAPRS, Vol. XXXVIII, Part 7B 
551 
Catrgory 
(%) 
Iteration 
0 
Accuracy 
Iteration Iteration 
1 2 
Iteration 
3 
Building 
80.75% 
88.28% 
88.92% 
89.46% 
Water 
92.12% 
92.93% 
90.26% 
90.14% 
Farmland 
39.96% 
36.86% 
34.11% 
34.11% 
Woodland 
92.03% 
95.28% 
93.97% 
93.84% 
Average 
77.89% 
80.27% 
78.84% 
78.89% 
Tabel 1. Segmentation accuracy 
5. CONCLUSIONS 
In this paper, an AdaBoost-based iterative Markov Random 
Fields (MRF) with Linear Target Prior (LTP) has been 
proposed. Applied to Synthetic Aperture Radar (SAR) images 
classification, three strategies have been provided in this model 
to improve regions edges and isolated points in classification 
results and effective performance has been obtained. Firstly, 
due to superpixels captured from ratio response map of SAR 
images instead of original SAR images, edge information has 
been utilized more effectively. In this case, classification 
experiment results show distinct edges of regions. Secondly, 
linear target prior introduces consistency information along the 
linear targets into Markov model. Combined with traditional 
neighbourhood prior information, more reasonable 
classification results have been gotten in the experiment. 
Thirdly, the employment of iterative strategy makes the 
proposed approach have self-perfection in a stated degree. And 
the experiments have a certain improvement with the increase 
of iteration times. 
Nevertheless, lots of information extracted from polarimetric 
SAR data, interferometric SAR data and polarimetric SAR 
interferometry data can be used for SAR image analysis. 
6. REFERENCES 
F. Galland, N. Bertaux, and P. Réfrégier, Minimum description 
length synthetic aperture radar image segmentation. IEEE 
Transactions Image Processing, vol. 12, no. 9, pp. 995-1006, 
Sep. 2003. 
C. Tison, J.-M. Nicolas, F. Tupin, and H. Maître, A new 
statistical model for Markovian classification of urban areas in 
high-resolution SAR images. IEEE Transactions on Geoscience 
and Remote Sensing, vol. 42, no. 10, pp. 2046-2057, Oct. 2004. 
R.F.Rocha. Use of Statistical Distribution for Segmentation of 
SAR Images of Oceanic Areas. International Society for 
Photogrammetry and Remote Sensing. Vol XXXVIII, 4/Cl, 
2008 
Zhouwen Tu, X.R. Chen, A.L. Yuille, and S.C. Zhu. unifying 
segmentation, detection and recognition. International Journal 
of Computer Vision, 63(2), 113-140, 2005. 
Verbeek. J., Triggs. B; Region Classification with Markov 
Field Aspect Models. IEEE Conference on Computer Vision 
and Pattern Recognition: 1-8, 2007. 
Stephen Gould, Jim Rodgers, David Cohen, Gal Elidan, 
Daphne Roller. Multi-Class Segmentation with Relative 
Location Prior. International Journal of Computer Vision. 1-16, 
2008. 
Dorin Comaniciu, Peter Meer, Senior Member. Mean Shift: A 
Robust Approach Toward Feature Space Analysis. IEEE 
Transactions on Pattern Analysis and Machine Intelligence, 
Vol 24, No.5: 603-613,2002. 
Jordi Inglada, Julien Michel. Qualitative Spatial Reasoning for 
High-Resolution Remote Sensing Image Analysis. IEEE 
Transactions on Geoscience and Remote Sensing, VOL. 47, NO. 
2: 599-612, FEBRUARY 2009. 
Joost van de Weijer, Cordelia Schmid. Coloring local feature 
extraction. Proceedings of the European Conference on 
Computer Vision, pages 334-348, 2006. 
B.S.Manjunath, W.Y.Ma, Texture Features for Browsing and 
Retrieval of Image Data, IEEE Transactions on Pattern 
Analysis and Machine Intelligence, vol. 18, no. 8, pp. 837-842, 
Aug. 1996. 
T. Ojala, M. Pietikainen, T. Maenpaa, Multiresolution gray 
scale and rotation invariant texture classification with local 
binary patterns, IEEE Transactions on Pattern Analysis and 
Machine Intelligence, vol. 24, no. 7, pp. 971-987, Jul. 2002. 
N. Dalai, B. Triggs. Histograms of oriented gradients for 
human detection. IEEE Conference on Computer Vision and 
Pattern Recognition 2005, volume 1, pages 886-893, 2005. 
Ahonen T, Pietikainen M. Soft histograms for local binary 
patterns. Finnish Signal Processing Symposium, Oulu, Finland. 
2007. 
S.C. Zhu and D. Mumford, A Stochastic Grammar of Images, 
Foundations and Trends in Computer Graphics and Vision, 
Vol.2, No.4, pp 259-362, 2006. 
David M. Blei, Andrew Y. Ng, Michael I. Jordan. Latent 
Dirichlet Allocation. Journal of Machine Learning Research 
2003 3: 993-1022. 2003. 
Robert E. Schapire. The boosting approach to machine learning: 
An overview. Nonlinear Estimation and Classification. 
Springer, 2003. 
Boykov Y, Veksler O, Zabih R. Fast Approximate Energy 
Minimization via Graph Cuts. IEEE Transactions on Pattern 
Analysis and Machine Intelligence, 2:1 222-1 239. 2001. 
F.Tupin, H.Maitre, J.F.Margin, etc. Detection of linear features 
in SAR images: application to road network extraction. IEEE 
Transactions on Geoscience and Remote Sensing, 36:434-453, 
1998. 
Kumar M.P., Torr P.H.S., Zisserman A. OBJ CUT. Computer 
Vision and Pattern Recognition, 20-25 June 2005, Volume 1, 
Page(s):18-25, 2005. 
7. ACKNOWLEDGMENTS 
The work was supported by the NSFC grant (No. 60702041, 
60872131, 40801183) and Hi-Tech research and development 
program of China (863) (No. 2007AA12Z155, 2007AA12Z180). 
The authors would like to thank the SPOT IMAGE Corporation 
for providing the TerraSAR image.