Multiscale Global Attention for Abnormal Geological Hazard Segmentation

Accurately segmenting geological hazard areas in high-resolution remote-sensing images (RSIs) faces challenges due to the arbitrary scopes and irregular contours of these areas. In this article, we propose a novel method for abnormal geological region segmentation in high-resolution RSIs. Specifically, the proposed method consists of two modules: a channel transformer encoder module (CTEM) and a multiscale global attention module (MSGAM). On the one hand, MSGAM is designed to effectively utilize low- and high-level features. To this end, it fuses multiscale representations extracted via dilated convolutions with varying dilation rates. To model long-range multiscale dependencies, CTEM is enabled to automatically assign importance weights to multiscale features and adapt receptive fields accordingly. In this way, our method can address the limited global context of convolutional operations. The proposed method achieves state-of-the-art (SOTA) results on the dataset of landslide and debris flow disasters. Experimental results demonstrate the effectiveness and superiority of the proposed method in handling irregular contours and shapes of abnormal geological regions.