Cross-Scale-Guided Fusion Transformer for Disaster Assessment Using Satellite Imagery
Weiwei Xiao, Jingyong Su, Yongyong Chen, Guofeng Cao
Abstract
When a disaster strikes, accurate disaster information and effective response are critical for saving lives and properties. High-resolution satellite (HRS) imagery provides valuable geographical information that can assist experts in analyzing damage levels in different areas and enacting appropriate relief plans. However, analyzing large HRS images is both time-consuming and inefficient, requiring efficient automated methods to replace expert analysis. Fortunately, deep learning methods have achieved impressive performance on HRS image processing tasks, considerably increasing automation levels. Despite this progress, most HRS-based damage assessment methods only consider a single time series of post-disaster images or simply integrate pre- and post-disaster images, lacking the integration of effective information between pre- and post-disaster images. To alleviate this problem, we propose a two-stage multi-scale fusion network that fully exploits the information contained in pre- and post-disaster images. Specifically, we employ a hierarchical Transformer to accurately locate buildings by pre-disaster images in the first stage, and then propose the guided fusion and cross-scale guided fusion modules in the second stage to efficiently utilize both pre- and post-disaster images. Our method outperforms state-of-the-art methods in building segmentation and building damage assessment on the xBD dataset, and exhibits improved generalization across diverse geographic regions and disaster types.