EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AFENet: An Attention-Focused Feature Enhancement Network for the Efficient Semantic Segmentation of Remote Sensing Images

Jiarui Li, Shuli Cheng

Remote Sensing · 24.11.2024 · 16 (23) · 4392

DOI: 10.3390/rs16234392 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 24.11.2024. Verfasst von Jiarui Li und 1 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Science and Technology Major Project of China, the Project of Science and Technology Department of Xinjiang Uygur Autonomous of China, the Graduate Research and Innovation Project of Xinjiang Uygur Autonomous Region of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The semantic segmentation of high-resolution remote sensing images (HRRSIs) faces persistent challenges in handling complex architectural structures and shadow occlusions, limiting the effectiveness of existing deep learning approaches. To address these limitations, we propose an attention-focused feature enhancement network (AFENet) with a novel encoder–decoder architecture. The encoder architecture combines ResNet50 with a parallel multistage feature enhancement group (PMFEG), enabling robust feature extraction through optimized channel reduction, scale expansion, and channel reassignment operations. Building upon this foundation, we develop a global multi-scale attention mechanism (GMAM) in the decoder that effectively synthesizes spatial information across multiple scales by learning comprehensive global–local relationships. The architecture is further enhanced by an efficient feature-weighted fusion module (FWFM) that systematically integrates remote spatial features with local semantic information to improve segmentation accuracy. Experimental results across diverse scenarios demonstrate that AFENet achieves superior performance in building structure detection, exhibiting enhanced segmentation connectivity and completeness compared to state-of-the-art methods.

Förderung

  • the National Science and Technology Major Project of China
  • the Project of Science and Technology Department of Xinjiang Uygur Autonomous of China
  • the Graduate Research and Innovation Project of Xinjiang Uygur Autonomous Region of China

Zitieren

APA

Li, J., & Cheng, S. (2024). AFENet: An Attention-Focused Feature Enhancement Network for the Efficient Semantic Segmentation of Remote Sensing Images. Remote Sensing, 16(23), 4392. https://doi.org/10.3390/rs16234392

Vancouver

Li J, Cheng S. AFENet: An Attention-Focused Feature Enhancement Network for the Efficient Semantic Segmentation of Remote Sensing Images. Remote Sensing. 2024;16(23):4392. doi:10.3390/rs16234392

BibTeX
@article{Li2024,
  author = {Li, Jiarui and Cheng, Shuli},
  title = {AFENet: An Attention-Focused Feature Enhancement Network for the Efficient Semantic Segmentation of Remote Sensing Images},
  journal = {Remote Sensing},
  year = {2024},
  volume = {16},
  number = {23},
  pages = {4392},
  doi = {10.3390/rs16234392}
}
Kostenlos starten →