POLSAR image classification using BP neural network based on Quantum Clonal Evolutionary Algorithm

Abstract

POLSAR image classification plays an important role in remote sensing. POLSAR data are a type of mass data and have more independent features which can represent different physical significances than optical image. Therefore, POLSAR image classification is actually a high dimensional nonlinear mapping problem. Because of the nonlinear mapping function of BP neural network, it can be used to classify POLSAR image. But BP neural network classifier is sensitive to initial weights and thresholds. Quantum Clonal Evolutionary Algorithm (QCEA) can converge to an optimal value quickly and can be used to optimize the initial weights and thresholds of BP neural network. Therefore, in this paper, BP classifier based on QCEA was used for POLSAR image classification. Firstly, optimize the initial weights and thresholds of BP neural network using QCEA. Secondly, train the optimized BP neural network classifier by gradient descent algorithm. Finally, classify the POLSAR image using the trained classifier. The validity test is demonstrated using Danish EMISAR L-band fully polarimetric data of Foulum Area (DK), Denmark. The preliminary result indicates that this method can classify most of the areas correctly.