A hybrid algorithm of the BP‐ANN/GA for classification of urban terrain surfaces with fused data of Landsat ETM+ and ERS‐2 SAR

Abstract

A hybrid algorithm of the back propagation artificial neural network and genetic algorithm (BP‐ANN/GA) was developed to optimize initial weights and to enable fast convergence of the BP‐ANN. This algorithm was applied to the classification of urban terrain surfaces with fused data of Landsat ETM+ and ERS‐2 SAR. An example of the Shanghai Pudong area using both Landsat ETM+ and ERS‐2 SAR image data demonstrates well the classification when applying our fusion algorithm.

Acknowledgements

This work was supported by the China State Major Basic Research Project (2001CB309401), the National Natural Science Foundation of China (60571050), and the Optical Science Project of Shanghai, China (036105012).