HRTBDA: a network for post-disaster building damage assessment based on remote sensing images

被引:0
作者
Chen, Fang [1 ,2 ,3 ]
Sun, Yao [1 ,2 ]
Wang, Lei [2 ,3 ]
Wang, Ning [2 ,3 ]
Zhao, Huichen [4 ]
Yu, Bo [2 ,3 ]
机构
[1] Guilin Univ Elect Technol, Sch Comp Sci & Informat Secur, Guilin, Peoples R China
[2] Int Res Ctr Big Data Sustainable Dev Goals, Beijing 100094, Peoples R China
[3] Chinese Acad Sci, Aerosp Informat Res Inst, Key Lab Digital Earth Sci, Beijing 100094, Peoples R China
[4] Chinese Acad Sci, Inst Atmospher Phys, Key Lab Reg Climate & Environm Temperate East Asia, Beijing, Peoples R China
关键词
Building damage assessment; damage building location; deep learning; HRNet; transformers; DATASET;
D O I
10.1080/17538947.2024.2418880
中图分类号
P9 [自然地理学];
学科分类号
0705 ; 070501 ;
摘要
Efficient building damage assessment after disasters is vital for emergency response and loss evaluation, but the task is complicated by diverse building structures and complex environments. Traditional methods using Convolutional Neural Networks (CNNs) struggle to capture global contextual features, limiting damage categorization accuracy. To address this, we introduce the High-Resolution Transformer Architecture for Building Damage Assessment (HRTBDA), which enhances multi-scale feature extraction. A Cross-Attention-Based Spatial Fusion (CSF) module is proposed to utilize the attention mechanism, improving the model's ability to identify detailed associations in damaged buildings. Additionally, we propose a deep convolution network matching optimization strategy that integrates a multilayer perceptron and expands the receptive field, enhancing global feature perception. HRTBDA's performance was evaluated on two public datasets and compared with five recent frameworks. The model achieved an F1-score of 86.0% in building localization and 78.4% in damage assessment, with a 4.8% improvement in detecting minor damages. These results demonstrate HRTBDA's potential for improving building damage assessment and highlight its significant advancements over existing methods.
引用
收藏
页数:20
相关论文
共 50 条
[31]   CSA-Net: Complex Scenarios Adaptive Network for Building Extraction for Remote Sensing Images [J].
Yang, Dongjie ;
Gao, Xianjun ;
Yang, Yuanwei ;
Jiang, Minghan ;
Guo, Kangliang ;
Liu, Bo ;
Li, Shaohua ;
Yu, Shengyan .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 :938-953
[32]   Multi-branch convolutional neural network in building polygonization using remote sensing images [J].
Xu, Yajin ;
Schuegraf, Philipp ;
Bittner, Ksenia .
PFG-JOURNAL OF PHOTOGRAMMETRY REMOTE SENSING AND GEOINFORMATION SCIENCE, 2025, 93 (01) :79-100
[33]   CA-BASNet: A Building Extraction Network in High Spatial Resolution Remote Sensing Images [J].
Huang, Liang ;
Zhu, Juanjuan ;
Qiu, Mulan ;
Li, Xiaoxiang ;
Zhu, Shasha .
SUSTAINABILITY, 2022, 14 (18)
[34]   Structure-Aware Weakly Supervised Network for Building Extraction From Remote Sensing Images [J].
Chen, Hui ;
Cheng, Liang ;
Zhuang, Qizhi ;
Zhang, Ka ;
Li, Ning ;
Liu, Lei ;
Duan, Zhixin .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[35]   Automatic Identification Model for Landslide Disaster Using Remote Sensing Images Based on Improved Multiresunet [J].
Zhao, Zhenyu ;
Tan, Shucheng ;
Zhang, Qinghua ;
Chen, Hui .
IEEE ACCESS, 2025, 13 :10653-10662
[36]   Transfer Learning Based Convolutional Neural Network for Classification of Remote Sensing Images [J].
Ramasamy, Meena Prakash ;
Krishnasamy, Valarmathi ;
Ramapackiam, Shantha Selva Kumari .
ADVANCES IN ELECTRICAL AND COMPUTER ENGINEERING, 2023, 23 (04) :31-40
[37]   CamoNet: A Target Camouflage Network for Remote Sensing Images Based on Adversarial Attack [J].
Zhou, Yue ;
Jiang, Wanghan ;
Jiang, Xue ;
Chen, Lin ;
Liu, Xingzhao .
REMOTE SENSING, 2023, 15 (21)
[38]   Object Recognition in Remote Sensing Images Based on Modified Backpropagation Neural Network [J].
Raju, Manthena Narasimha ;
Natarajan, Kumaran ;
Vasamsetty, Chandra Sekhar .
TRAITEMENT DU SIGNAL, 2021, 38 (02) :451-459
[39]   Extraction network of forests and lakes along the railway based on remote sensing images [J].
Ye, Xiaoling ;
Zhang, Hu ;
Sheng, Tao ;
Zhang, Yingchao ;
Zou, Ruilin ;
Xiong, Xiong .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2024, 45 (01) :235-258
[40]   AGs-Unet: Building Extraction Model for High Resolution Remote Sensing Images Based on Attention Gates U Network [J].
Yu, Mingyang ;
Chen, Xiaoxian ;
Zhang, Wenzhuo ;
Liu, Yaohui .
SENSORS, 2022, 22 (08)