Graph Convolutional Networks-Based Super-Resolution Land Cover Mapping

Abstract

Super-resolution mapping (SRM) is an effective technology to solve the problem of mixed pixels because it can be used to generate fine-resolution land cover maps from coarse-resolution remote sensing images. Current methods based on deep neural networks have been successfully applied to SRM, as they can learn complex spatial patterns from training data. However, they lack the ability to learn structural information between adjacent land cover classes, which is vital in the reconstruction of spatial distribution. In this article, an SRM method based on graph convolutional networks (GCNs), named ${\rm{SR}}{{\rm{M}}_{{\rm{GCN}}}}$, is proposed to improve SRM results by capturing structure information on the graph. In ${\rm{SR}}{{\rm{M}}_{{\rm{GCN}}}}$, a supervised inductive learning strategy with mini-graphs as input is considered, which is an extension of the GCN framework. Furthermore, two operations are designed in terms of adjacency matrix construction and an information propagation rule to help reconstruct detailed information of geographical objects. Experiments on three datasets with different spatial resolutions demonstrate the qualitative and quantitative superiority of ${\rm{SR}}{{\rm{M}}_{{\rm{GCN}}}}$ over three other popular SRM methods.

Keywords

• Deep neural networks (DNNs)
• graph convolutional networks (GCNs)
• land cover
• subpixel
• super-resolution mapping (SRM)