Spatial-Spectral Decoupling Interaction Network for Multispectral Imagery Change Detection

We present a spatial-spectral decoupling interaction network for multispectral imagery change detection, which can exploit the underlying information of the multispectral imagery adequately through simultaneously considering the discriminative attribute of each pixel and robust spatial structure of the corresponding patch. Specifically, a 1-D convolutional neural network (1D-CNN) is applied to the spectral vector of each pixel to extract its discriminative feature, while a 2D-CNN is applied to the patch centering on the corresponding pixel to explore the spatial structure information. In addition, an interaction mechanism is incorporated into the feature fusion module to enhance the spatial-spectral consistency.

Automated summary

This article presents a spatial-spectral decoupling interaction network for multispectral imagery change detection. The network can exploit the underlying information of the multispectral imagery by simultaneously considering the discriminative attribute of each pixel and the robust spatial structure of the corresponding patch.