Building Instance Extraction via Multi-Scale Hybrid Dual-Attention Network
Buildings · 29.08.2025 · 15 (17) · 3102
DOI: 10.3390/buildings15173102 ↗Kurz gefasst
Fachartikel in der Zeitschrift Buildings, online erschienen am 29.08.2025. Verfasst von Qingqing Hu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: project FRG-25-064-FA, Research Fund of Macao University of Science and Technology (FRG-MUST).
Abstract (Originalsprache)
Accurate building instance segmentation from high-resolution remote sensing images remains challenging due to complex urban scenes featuring occlusions, irregular building shapes, and heterogeneous textures. To address these issues, we propose a novel Multi-Scale Hybrid Dual-Attention Network (MS-HDAN), which integrates a dual-stream encoder, multi-scale feature extraction, and a hybrid attention mechanism. Specifically, the encoder is designed with a Local Feature Extraction Pathway (LFEP) and a Global Context Modeling Pathway (GCMP), enabling simultaneous capture of structural details and long-range semantic dependencies. A Local-Global Collaborative Perception Enhancement Module (LG-CPEM) is introduced to fuse the outputs from both streams, enhancing contextual representation. The decoder adopts a hierarchical up-sampling structure with skip connections and incorporates a dual-attention module to refine boundary-level details and suppress background noise. Extensive experiments on benchmark urban building datasets demonstrate that MS-HDAN significantly outperforms existing state-of-the-art methods, particularly in handling densely distributed and structurally complex buildings. The proposed framework offers a robust and scalable solution for real-world applications, such as urban planning, where precise building segmentation is crucial.
Förderung
- project FRG-25-064-FA
- Research Fund of Macao University of Science and Technology (FRG-MUST)
Zitieren
APA
Hu, Q., Peng, Y., Zhang, C., Lin, Y., U, K., & Chen, J. (2025). Building Instance Extraction via Multi-Scale Hybrid Dual-Attention Network. Buildings, 15(17), 3102. https://doi.org/10.3390/buildings15173102
Vancouver
Hu Q, Peng Y, Zhang C, Lin Y, U K, Chen J. Building Instance Extraction via Multi-Scale Hybrid Dual-Attention Network. Buildings. 2025;15(17):3102. doi:10.3390/buildings15173102
BibTeX
@article{Hu2025,
author = {Hu, Qingqing and Peng, Yiran and Zhang, Chi and Lin, Yunqi and U, KinTak and Chen, Junming},
title = {Building Instance Extraction via Multi-Scale Hybrid Dual-Attention Network},
journal = {Buildings},
year = {2025},
volume = {15},
number = {17},
pages = {3102},
doi = {10.3390/buildings15173102}
}
EUVIMED