22 December 1997 Polarimetric SAR data classification using scattering models and neural networks
Author Affiliations +
We consider a polarimetric SAR data classification method which includes scattering models. The proposed method is an integrated neural network classifier composed of two classification procedures. First, SAR data is pre-classified into three scattering classes by individually computing the Mueller matrix and Stokes vector. Second, we construct a neural network appropriate to each scattering class in order to classify the SAR data into realistic categories. Either the competitive or back-propagation neural network is employed as a classifier. The former learns by the LVQ1 and LVQ2.1 algorithms. As a result of the procedure using SIR-C C band data, pixels in the water category will be classified almost exclusively into the odd class. The even class includes only factory and urban categories. Therefore, it can be concluded that the neural classifier contains a smaller network and a more efficient learning process since it is applied to more limited category classifications. The neural network classifier employs an eight-dimension feature vector with backscattering coefficients and pseudo relative phases between HH and VV from the L and C bands. Average accuracy of the competitive neural network is slightly higher than that of the back-propagation network.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yosuke Ito, Yosuke Ito, Sigeru Omatu, Sigeru Omatu, } "Polarimetric SAR data classification using scattering models and neural networks", Proc. SPIE 3217, Image Processing, Signal Processing, and Synthetic Aperture Radar for Remote Sensing, (22 December 1997); doi: 10.1117/12.295602; https://doi.org/10.1117/12.295602

Back to Top