Citation :

K. S. Raghavendra Reddy, B. Sudhakar, K. Venkata Ramanaiah, "Multi-Scale Spatial-Channel Reconstruction Transformer for Automatically Assessing Building Damage in Post-Disaster Scenarios," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 10, pp. 437-456, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I10P131

Abstract

Surveying building damage in post-disaster image segmentation is a difficult problem due to noise, low contrast, and ambiguous boundaries in real-life clinical images. The existing transformer models face problems such as feature redundancy, semantic inconsistencies, and poor boundary reconstructions. To overcome such drawbacks, this study introduces a new model named Reconstruction Spatial-Pixel Fusion Multi-Scale Transformer (RSPF-MST). Specifically, the proposed architecture has three main novelties: (i) Reconstruction Spatial-Pixel Convolution (RSPC) is designed to remove redundant features with the help of spatial and channel-wise reconstructions; (ii) Channel Interaction Fusion (CIF) is designed to strengthen multi-scale semantic consistency with cross-channel attention; and (iii) Pixel-Aware Up-sampling Guidance (PAUG) aims at improving boundary accuracy by introducing pixel-level dynamic weights. Moreover, a Dynamic Receptive Multi-Scale Context (DRMSC) module is added in the decoder for capturing context information at various levels. A pruning strategy is adopted for efficiency. Experimental analysis demonstrates that the proposed model significantly improves segmentation accuracy, achieving 98.43% and 98.53%, and IoU scores of 96.13% and 96.12% on the Ida-BD and RescueNet datasets, respectively, while maintaining robustness, particularly for low-quality post-disaster images.

Keywords

Post-disaster image, Building damage, Transformer, RSPF-MST, PAUG, and Segmentation.

References

1. Zhenghang Yuan et al., “RRSIS: Referring Remote Sensing Image Segmentation,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-12, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Chen Wu et al., “UNet-Like Remote Sensing Change Detection: A Review of Current Models and Research Directions,” IEEE Geoscience and Remote Sensing Magazine, vol. 12, no. 4, pp. 305-334, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Guangliang Cheng et al., “Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review,” Remote Sensing, vol. 16, no. 13, pp. 1-36, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Dongzhe Han et al., “A Multi-Level Damage Assessment Model based on Change Detection Technology in Remote Sensing Images,” Natural Hazards, vol. 121, no. 6, pp. 7367-7388, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Wenfan Qiao et al., “Revolutionizing Building Damage Detection: A Novel Weakly Supervised Approach using High-Resolution Remote Sensing Images,” International Journal of Digital Earth, vol. 17, no. 1, pp. 1-26, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Lili Wang et al., “Deep Learning Models for Hazard-Damaged Building Detection using Remote Sensing Datasets: A Comprehensive Review,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 15301-15318, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
7. M. Sadman Sakib, and C. Emdad Haque, “Engaging Military with Domestic Disaster Response: A Comparative Study of Institutional Structure,” International Journal: Canada’s Journal of Global Policy Analysis, vol. 80, no. 3, pp. 486-512, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Hongruixuan Chen et al., “BRIGHT: A Globally Distributed Multimodal Building Damage Assessment Dataset with Very-High-Resolution for All-Weather Disaster Response,” Earth System Science Data, vol. 17, no. 11, pp. 6217-6253, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Aaqib Ali et al., “Applications of Remote Sensing Technologies to Assess Ground Displacements and Seismic Hazards: Precision, Scale, and Insight,” Arabian Journal for Science and Engineering, vol. 50, no. 20, pp. 16357-16378, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Sultan Al Shafian, and Da Hu, “Integrating Machine Learning and Remote Sensing in Disaster Management: A Decadal Review of Post-Disaster Building Damage Assessment,” Buildings, vol. 14, no. 8, pp. 1-32, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Jiancheng Gu et al., “Advances in Rapid Damage Identification Methods for Post-Disaster Regional Buildings based on Remote Sensing Images: A Survey,” Buildings, vol. 14, no. 4, pp. 1-35, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Dilum Rajapaksha et al., “Systematic Mapping of Global Research on Disaster Damage Estimation for Buildings: A Machine Learning-Aided Study,” Buildings, vol. 14, no. 6, pp. 1-26, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Tania Islam et al., “A Systematic Review of Urban Flood Susceptibility Mapping: Remote Sensing, Machine Learning, and other Modeling Approaches,” Remote Sensing, vol. 17, no. 3, pp. 1-37, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Ronny Francis Ribeiro Junior, and Guilherme Ferreira Gomes, “On the use of Machine Learning for Damage Assessment in Composite Structures: A Review,” Applied Composite Materials, vol. 31, no. 1, pp. 1-37, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Abdullah M. Braik, and Maria Koliou, “Automated Building Damage Assessment and Large-Scale Mapping by Integrating Satellite Imagery, GIS, and Deep Learning,” Computer-Aided Civil and Infrastructure Engineering, vol. 39, no. 15, pp. 2389-2404, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Lan Nguyen-Ngoc et al., “Deep Neural Network and Evolved Optimization Algorithm for Damage Assessment in a Truss Bridge,” Mathematics, vol. 12, no. 15, pp. 1-25, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Shayan Ghazimoghadam, and S.A.A. Hosseinzadeh, “A Novel Unsupervised Deep Learning Approach for Vibration-based Damage Diagnosis using a Multi-Head Self-Attention LSTM Autoencoder,” Measurement, vol. 229, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Wen Lu, Lu Wei, and Minh Nguyen, “Bitemporal Attention Transformer for Building Change Detection and Building Damage Assessment,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 4917-4935, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Masoomeh Gomroki et al., “UNet- GCViT: A UNet-based Framework with Global Context Vision Transformer Blocks for Building Damage Detection,” International Journal of Remote Sensing, vol. 46, no. 6, pp. 2587-2610, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Ehsan Govahi, Mojtaba Salkhordeh, and Reza Karami Mohammadi, “A Strengthened Convolutional Neural Network Algorithm for Identifying the Extent of Seismic Damage in Moment-Frame Buildings,” Structure and Infrastructure Engineering, pp. 1-22, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Yiming Xiao, and Ali Mostafavi, “DamageCAT: A Deep Learning Transformer Framework for Typology-based Post-Disaster Building Damage Categorization,” International Journal of Disaster Risk Reduction, vol. 128, pp. 1-21, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Bo Yu et al., “Post-Disaster Building Damage Assessment based on Gated Adaptive Multi-Scale Spatial-Frequency Fusion Network,” International Journal of Applied Earth Observation and Geoinformation, vol. 141, pp. 1-13, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Yifan Yang et al., “Hyperlocal Disaster Damage Assessment using Bi-Temporal Street-View Imagery and Pre-Trained Vision Models,” Computers, Environment and Urban Systems, vol. 121, pp. 1-14, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Jianli Zhang et al., “CMSNet: A SAM-Enhanced CNN-Mamba Framework for Damaged Building Change Detection in Remote Sensing Imagery,” Remote Sensing, vol. 17, no. 23, pp. 1-36, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Jungeun Cha, Seunghyeok Lee, and Hoe-Kyoung Kim, “Deep Learning-based Detection and Assessment of Road Damage caused by Disaster with Satellite Imagery,” Applied Sciences, vol. 15, no. 14, pp. 1-16, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
26. Chaoxian Liu, Haigang Sui, and Lihong Huang, “Minor Damage Recognition from Postearthquake Buildings with an Improved Generative Adversarial Semantic Segmentation Network,” Natural Hazards Review, vol. 26, no. 3, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Diwakar Bhardwaj et al., “Enhanced Satellite Imagery Analysis for Post-Disaster Building Damage Assessment using Integrated Resnet-U-Net Model,” Multimedia Tools and Applications, vol. 84, no. 5, pp. 2689-2714, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
28. Akila Agnes Sundaresan, and Appadurai Arun Solomon, “Post-Disaster Flooded Region Segmentation using Deeplabv3+ and Unmanned Aerial System Imagery,” Natural Hazards Research, vol. 5, no. 2, pp. 363-371, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
29. Nhut Le, Ehsan Karimi, and Maryam Rahnemoonfar, “3DAeroRelief: The First 3D Benchmark UAV Dataset for Post-Disaster Assessment,” Scientific Data, vol. 13, no. 1, pp. 1-12, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
30. Efdal Kaya, “Assessment of Building Extraction and Geometric Corrections from UAV Image using Mask R-CNN Deep Neural Network Algorithm,” European Journal of Remote Sensing, vol. 59, no. 1, pp. 1-17, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]