Graph-based fusion for change detection in multi-spectral images
This addresses change detection in remote sensing, but it appears incremental as it builds on existing graph-based methods.
The paper tackles change detection in multi-spectral images by proposing a graph-based data fusion framework, which outperforms state-of-the-art methods in two real remote sensing cases.
In this paper we address the problem of change detection in multi-spectral images by proposing a data-driven framework of graph-based data fusion. The main steps of the proposed approach are: (i) The generation of a multi-temporal pixel based graph, by the fusion of intra-graphs of each temporal data; (ii) the use of Nyström extension to obtain the eigenvalues and eigenvectors of the fused graph, and the selection of the final change map. We validated our approach in two real cases of remote sensing according to both qualitative and quantitative analyses. The results confirm the potential of the proposed graph-based change detection algorithm outperforming state-of-the-art methods.