In: Wagner W., Székely, B. (eds.): ISPRS TC VII Symposium - 100 Years ISPRS, Vienna, Austria, July 5-7, 2010, IAPRS, Vol. XXXVIII, Part 7B 
Figure 4: Results of the classification of a large PolSAR image (RadarSat-2 polarimetrie SAR data of Flevoland in Netherlands, with 
size of 4000 x 2400 pixels) into the four semantic classes: woodland, cropland, water, building. 
REFERENCES 
Beaulieu, J. M. and Touzi, R., 2004. Segmentation of textured po- 
larimetric sar scenes by likelihood approximation. IEEE Trans 
actions on Geoscience and Remote Sensing, 42(10), pp. 2063- 
2072. 
Blei, D., Ng, A. and Jordan, M., 2003. Latent direchlet allocation. 
Journal of Machine Learning Research 3(3), pp. 993-1022. 
Clausi, D. A., 2001. Comparison and fusion of co-occurrence, 
gabor, and mrf texture features for classification of sar sea ice 
imagery. Atmosphere & Oceans, 39(4), pp. 183-194. 
Comaniciu, D. and Meer, R, 2002. Mean shift: A robust ap 
proach toward feature space analysis. IEEE Transactions on Pat 
tern Analysis and Machine Intelligence, 24(5), pp. 603-619. 
Ersahin, K., Cumming, I. G. and Ward, R. K., 2010. Segmen 
tation and classification of polarimetric sar data using spectral 
graph partitioning. IEEE Transactions on Geoscience and Re 
mote Sensing, 48(1), pp. 164-174. 
He, W. J„ Jager, M., Reigber, A. and Hellwich, O., 2008. Build 
ing extraction from polarimetric sar data using mean shift and 
conditional random fields. The 7th European Conference on Syn 
thetic Aperture Radar (EuSAR), III, pp. 439-442. 
Hofmann, T., 2001. Unsupervised learning by probabilistic latent 
semantic anaylysis. Machine Learning 42(1-2), pp. 177-196. 
Huynen, J. R., 1990. The stokes matrix parameters and their in 
terpretation in terms of physical target properties. Joumé es In 
ternationales de la Polarimétrie Radar, pp. 524-531. 
Lardeux, C., Frison, P.-L., Tison, C., Souyris, J.-C., Stoll, B., 
Fruneau, B. and Rudant, J.-P, 2009. Support vector machine for 
multifrequency sar polarimetric data classification. IEEE Trans 
actions on Geoscience and Remote Sensing, 47(12), pp. 4143- 
4152. 
Lee, J. S., Gruñes, M. R. and Kwok, R., 1994. Classification 
of multi-look polarimetric sar imagery-based on complex wishart 
distribution. International Journal of Remote Sensing, 15(11), 
pp.2299-2311. 
Lee, J. S., Gruñes, M. R. and Pottier, E., 2001. Quantitative com 
parison of classification capability: Fully polarimetric versus dual 
and single-polarization sar. IEEE Transactions on Geoscience 
and Remote Sensing 39(11), pp. 2343-2351. 
Li, F.-F. and Perona, R, 2005. A bayesian hierarchical model for 
learning natural scene categories. Proc. of IEEE Computer So 
ciety Conference on. Computer Vision and Pattern Recognition, 
pp. 524-531. 
Liénou, M., Maître, H. and Datcu, M., 2010. Semantic anno 
tation of satellite images using latent dirichlet allocation. IEEE 
Geoscience and Remote Sensing Letters, 7(1), pp. 28-32. 
Shimoni, M., Borghys, D., Heremans, R., Perneel, C. and 
Acheroy, M., 2009. Fusion of polsar and polinsar data for land 
cover classification. International Journal of Applied Earth Ob 
servation and Geoinformation, 11(3), pp. 169-180. 
Verbeek, J. and Triggs, B., 2007. Region classification with 
markov field aspect models. Proc. of IEEE Computer Society 
Conference on. Computer Vision and Pattern Recognition,. 
Wu, Y. H., Ji, K. F., Yu, W. X. and Su, Y, 2008. Region-based 
classification of polarimetric sar images using wishart mrf. IEEE 
Geoscience and Remote Sensing Letters, 5(4), pp. 668-672. 
Yedidia, J., Freeman, W. and Weiss, Y, 2005. Constructing 
free-energy approximations and generalized belief propagation 
algorithms. IEEE Transactions on Information Theory, 51(7), 
pp.2282-2312. 
Zou, T. Y, Yang, W., Dai, D. X. and Sun, H., 2010. Polarimet 
ric sar image classification using multi-features combination and 
extremely randomized clustering forests. EURASIP Journal on 
Advances in Signal Processing, 2010, pp. 1-9. 
ACKNOWLEDGEMENTS 
This work was supported in part by the National Natural Sci 
ence Foundation of China (No.40801183, 60890074), the Na 
tional High Technology Research and Development Program of 
China (No.2007AA12Z180, 155) and LIESMARS Special Re 
search Funding.