Dynamic atrous attention and dual branch context fusion for cross scale Building segmentation in high resolution remote sensing imagery
Authors:
Open Access
- 21 August 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-16
Abstract
Building segmentation of high-resolution remote sensing images using deep learning effectively reduces labor costs, but still faces the key challenges of effectively modeling cross-scale contextual relationships and preserving fine spatial details. Current Transformer-based approaches demonstrate superior long-range dependency modeling, but still suffer from the problem of progressive information loss during hierarchical feature encoding. Therefore, this study proposed a new semantic segmentation network named SegTDformer to extract buildings in remote sensing images. We designed a Dynamic Atrous Attention (DAA) fusion module that integrated multi-scale features from Transformer, constructing an information exchange between global information and local representational information. Among them, we introduced the Shift Operation module and the Self-Attention module, which adopt a dual-branch structure to respectively capture local spatial dependencies and global correlations, and perform weight coupling to achieve highly complementary contextual information fusion. Furthermore, we fused triplet attention with depth-wise separable convolutions, reducing computational requirements and mitigating potential overfitting scenarios. We benchmarked the model on three different datasets, including Massachusetts, INRIA, and WHU, and the results show that the model consistently outperforms existing models. Notably, on the Massachusetts dataset, the SegTDformer model achieved benchmark in mIoU, F1-score, and Overall Accuracy of 75.47%, 84.7%, and 94.61%, respectively, superseding other deep learning models. The proposed SegTDformer model exhibits enhanced precision in the extraction of urban structures from intricate environments and manifests a diminished rate of both omission and internal misclassification errors, particularly within the context of diminutive and expansive edifices.Keywords
Funding Information
- National Natural Science Foundation of China (42201077)
- Natural Science Foundation of Shandong Province (ZR2021QD074)
- China Postdoctoral Science Foundation (2023M732105)
- Youth Innovation Team Project of Higher School in Shandong Province (2024KJH087)
- State Key Laboratory of Precision Geodesy, Innovation Academy for Precision Measurement Science and Technology (SKLGED2024-3-4)
This publication has 57 references indexed in Scilit:
- Transportation mode detection through spatial attention-based transductive long short-term memory and off-policy feature selectionExpert Systems with Applications, 2024
- Differential multimodal fusion algorithm for remote sensing object detection through multi-branch feature extractionExpert Systems with Applications, 2024
- Remote sensing image semantic segmentation via class-guided structural interaction and boundary perceptionExpert Systems with Applications, 2024
- The ClearSCD model: Comprehensively leveraging semantics and change relationships for semantic change detection in high spatial resolution remote sensing imageryISPRS Journal of Photogrammetry and Remote Sensing, 2024
- Triple disentangled network with dual attention for remote sensing image fusionExpert Systems with Applications, 2024
- Building damage assessment for rapid disaster response with a deep object-based semantic change detection framework: From natural disasters to man-made disastersRemote Sensing of Environment, 2021
- End-to-End Object Detection with Transformers2020
- CBAM: Convolutional Block Attention Module2018
- Urban planning and building smart cities based on the Internet of Things using Big Data analyticsComputer Networks, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015