Abstract
It is very important to efficiently represent the target scattering characteristics in applications of polarimetric radar remote sensing. Three probability mass functions are introduced in this paper for target representation: using similarity parameters to describe target average scattering mechanism, using the eigenvalues of a target coherency matrix to describe target scattering randomness, and using radar received power to describe target scattering intensity. The concept of cross-entropy is employed to measure the difference between two scatterers based on the probability mass functions. Three parts of difference between scatterers are measured separately as the difference of average scattering mechanism, the difference of scattering randomness and the difference of scattering intensity, so that the usage of polarimetric data can be highly efficient and flexible. The supervised/unsupervised image classification schemes and their simplified versions are established based on the minimum cross-entropy principle. They are demonstrated to have better classification performance than the maximum likelihood classifier based on the Wishart distribution assumption, both in supervised and in unsupervised classification.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Kong, J. A., Swartz, A. A. et al., Identification of terrain cover using the optimal terrain classifier, J. Electronmagn. Waves Applicat., 1988, 2: 171–194.
Lee, J. S. et al., Classification of multi-look polarimetric SAR imagery based on complex Wishart distribution, Int. J. Remote Sensing, 1994, 15(11): 2299–2311.
Kwok, R., Hara, Y., Atkins, R. G. et al., Application of neural networks to sea ice classification using polarimetric SAR images, Proceedings of IGARSS’91, 1991, 1: 85–88.
Tzeng, Y. C., A dynamic learning neural network for remote sensing application, IEEE Trans. Geosci. Remote Sensing, 1995, 32(5): 1096–1102.
Chen, K. S., Huang, W. P. et al., Classification of multifrequency polarimtric SAR imagery using a dynamic learning neural network, IEEE Trans. Geosci. Remote Sensing, 1996, 34(3): 814–820.
Tzeng, Y. C., Chen, K. S., A fuzzy neural network to SAR image classification, IEEE Trans. Geosci. Remote Sensing, 1998, 36(1): 301–307.
Hellmann, M., Jager, G. et al., Classification of full polarimetric SAR-data using artificial neural networks and fuzzy algorithms, Proceedings of IGARSS’99, 1999, 1995–1997.
Lueneburg, E., Chandra, M., Boerner, W. M., Random target approximations, in Proc. PIERS Progress in Electromagnetic Research Symposium, Noordwijk, The Netherlands, 1994, 1366–1369.
Yang, J., Peng, Y. N., Lin, S. M., Similarity between two scattering matrices, Electron. Letters, 2001, 37(3): 193–194.
Huynen, J. R., Phenomenological theory of radar targets, Ph. D. Dissertation, 1970.
Jin, Y. Q., Cloude, S. R., Numerical eigenanalysis of the coherency matrix for a layer of random nonspherical scatters, IEEE Trans. Geosci. Remote Sensing, 1994, 32(6): 1179–1185.
Cloude, S. R. et al., An entropy based classification scheme for land applications of polarimetric SAR, IEEE Trans. Geosci. Remote Sensing, 1997, 35(1): 68–78.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xu, J., Yang, J. & Peng, Y. A new approach to dual-band polarimetric radar remote sensing image classification. Sci China Ser F 48, 747–760 (2005). https://doi.org/10.1360/04yf0301
Received:
Issue Date:
DOI: https://doi.org/10.1360/04yf0301