Building Damage Assessment Based on Siamese Hierarchical Transformer Framework
Open Access
- 1 June 2022
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 10 (11) , 1898
Abstract
The rapid and accurate damage assessment of buildings plays a critical role in disaster response. Based on pairs of pre- and post-disaster remote sensing images, effective building damage level assessment can be conducted. However, most existing methods are based on Convolutional Neural Network, which has limited ability to learn the global context. An attention mechanism helps ameliorate this problem. Hierarchical Transformer has powerful potential in the remote sensing field with strong global modeling capability. In this paper, we propose a novel two-stage damage assessment framework called SDAFormer, which embeds a symmetric hierarchical Transformer into a siamese U-Net-like network. In the first stage, the pre-disaster image is fed into a segmentation network for building localization. In the second stage, a two-branch damage classification network is established based on weights shared from the first stage. Then, pre- and post-disaster images are delivered to the network separately for damage assessment. Moreover, a spatial fusion module is designed to improve feature representation capability by building pixel-level correlation, which establishes spatial information in Swin Transformer blocks. The proposed framework achieves significant improvement on the large-scale building damage assessment dataset—xBD.Keywords
Funding Information
- National Natural Science Foundation of China (62171016, 61871413, buctrc202001)
- Fundamental Research Funds for the Central Universities (62171016, 61871413, buctrc202001)
This publication has 45 references indexed in Scilit:
- CBAM: Convolutional Block Attention Module2018
- Disaster damage detection through synergistic use of deep learning and 3D point cloud features derived from very high resolution oblique aerial images, and multiple-kernel-learningISPRS Journal of Photogrammetry and Remote Sensing, 2018
- Relation Networks for Object Detection2018
- Earthquake damage mapping: An overall assessment of ground surveys and VHR image change detection after L'Aquila 2009 earthquakeRemote Sensing of Environment, 2018
- Building damage assessment from PolSAR data using texture parameters of statistical modelComputers & Geosciences, 2018
- Change Detection Based on Deep Siamese Convolutional Network for Optical Aerial ImagesIEEE Geoscience and Remote Sensing Letters, 2017
- Earthquake-Induced Building Damage Detection with Post-Event Sub-Meter VHR TerraSAR-X Staring Spotlight ImageryRemote Sensing, 2016
- Object-based classification of earthquake damage from high-resolution optical imagery using machine learningJournal of Applied Remote Sensing, 2016
- Deep Residual Learning for Image Recognition2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015