The Fusion Process of RS(Remote Sensing) Data Based on Wavelet Neural Network

Abstract

A wavelet network was constructed through multi-spectral, high-pixel wavelet decomposition of remote sensing image, which replaced the traditional neuron activation function with a nonlinear wavelet system. So we found a data fusion model. Multidimensional information fusion was to integrate the multi-source information characteristics of a high dimensional feature space. With the genetic search based on the natural selection, we combine effective evaluation of fusion accuracy.