A novel change detection approach for VHR remote sensing images by integrating multi-scale features

Abstract

A novel change detection (CD) method for very high-resolution images is proposed by integrating multi-scale features. First, a novel edge density matching index was designed, and the structural similarity of textures, including grey level co-occurrence matrix, Gaussian Markov random field, and Gabor features between bitemporal images, were extracted to measure changes. Then, an adaptive approach was proposed to select optimal textures based on the majority consistency between spectrum and textures. Afterward, all features were decomposed into multi-scale features and fused into initial CD maps using Dempster–Shafer evidence theory. Finally, advantage fusion was implemented to generate the final CD map by fusing initial CD maps to remove noise and preserve details. Experiments conducted on real SPOT 5 and simulated QuickBird datasets, which achieved the total error ratios of 8.74% and 2.50%, respectively, indicate the effectiveness of the proposed approach.