Spectral Knowledge Transfer for Remote Sensing Change Detection

Change detection (CD) in multispectral remote sensing (RS) imagery suffers from the low spectral resolution which can lead to degraded recognition of change information from land cover objects. Considering that natural hyperspectral imagery is much higher in spectral resolution and more accessible, using it to enhance the spectral information of RS multispectral imagery for CD can improve the performance. To achieve this, we propose a spectral knowledge transfer (SKT) framework to allow creating pseudo-hyperspectral RS images from the available RS multispectral ones without the need for the real pairs of RS multispectral and hyperspectral images, typically required by existing RS spectral enhancement methods. Specifically, an auto-encoder is firstly trained based on the available pairs of natural hyperspectral imagery and its multispectral counterparts, and then calibrated via the available RS multispectral images. The finally obtained decoder module is used to generate the pseudo-hyperspectral image from an input RS multispectral image. We further propose a multi-spectrum collaborative CD (MCCD) framework which leverages both the real multispectral images and the pseudo hyperspectral images generated from them in a collaborative way to achieve performance improvement. Extensive experiments on two large-scale RS CD data sets and eight existing deep learning-based CD methods demonstrate the stronger efficacy of the proposed method.