Multiscale Morphological Compressed Change Vector Analysis for Unsupervised Multiple Change Detection

A novel multiscale morphological compressed change vector analysis (M2C2VA) method is proposed to address the multiple-change detection problem (i.e., identifying different classes of changes) in bitemporal remote sensing images. The proposed approach contributes to extend the state-of-The-Art spectrum-based compressed change vector analysis (C2VA) method by jointly analyzing the spectral-spatial change information. In greater details, reconstructed spectral change vector features are built according to a morphological analysis. Thus more geometrical details of change classes are preserved while exploiting the interaction of a pixel with its adjacent regions. Two multiscale ensemble strategies, i.e., data level and decision level fusion, are designed to integrate the change information represented at different scales of features or to combine the change detection results obtained by the detector at different scales, respectively. A detailed scale sensitivity analysis is carried out to ...