Multiscale Attention Network Guided With Change Gradient Image for Land Cover Change Detection Using Remote Sensing Images

Learning performance is unsatisfactory when training deep-learning networks without prior-knowledge guidance. In this letter, a multiscale change detection neural network guided by a change gradient image (CGI) was proposed. First, a multiscale information attentional module was embedded in the backbone of UNet to achieve a multiscale information fusion task of bitemporal images. Second, the position channel attention module (PCAM) was promoted to make the neural network pay more attention to the spectral and spatial information in the multiscale fused feature map. Finally, a change gradient guide module (CGGM) was proposed to optimize backpropagation and overcome the negative effects of pseudo-change. Compared with seven state-of-the-art methods using three pairs of real remote sensing images, the proposed approach could smoothen the salt-and-pepper noise from the detection maps and improve the detection accuracy. The quantitative improvements are about 1.67% and 3.00% in terms of overall accuracy (OA) and kappa coefficient, respectively, thus confirming the feasibility and superiority of the proposed approach for detecting land cover change with remotely sensed images. Code:yhttps://github.com/ImgSciGroup/MACGGNet.git.

Automated summary

In this letter, a multiscale change detection neural network guided by a change gradient image (CGI) was proposed to improve the learning performance of deep-learning networks. A multiscale information attentional module was embedded in the backbone of UNet for the fusion of bitemporal images. Additionally, a position channel attention module (PCAM) and a change gradient guide module (CGGM) were introduced to enhance the network's attention to spectral and spatial information, while overcoming the negative effects of pseudo-change. The proposed approach outperforms seven state-of-the-art methods in terms of smoothing noise and improving detection accuracy, achieving a 1.67% increase in overall accuracy (OA) and a 3.00% increase in kappa coefficient.