EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Building Instance Extraction via Multi-Scale Hybrid Dual-Attention Network

Qingqing Hu, Yiran Peng, Chi Zhang, Yunqi Lin, KinTak U, Junming Chen

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).

AbstractBibliografische AngabenZitierenVerwandte Studien

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}
}
Kostenlos starten →