EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DEMANet: A dehazing enhanced multi-branch attention network for remote sensing images

Peixue Liu, Shu Liu, Pengfei He iD, Guoheng Wang

PLOS One · 2026

DOI: 10.1371/journal.pone.0354121 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Peixue Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Qingdao Huanghai University, Qingdao, Shandong, China. Hauptthemen laut MEDLINE: Remote Sensing Technology, Image Processing, Computer-Assisted, Neural Networks, Computer. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Open Project of State Key Laboratory of Synthetical Automation for Process Industries, Qingdao West Coast Principal Fund, Yantai City 2023 School-Land Integration Development Project Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Haze represents a key constraint on the application of optical remote sensing imagery. It not only impairs visual quality but also lowers the accuracy of remote sensing interpretation tasks such as classification and change detection. To tackle this issue, we present a Dehazing Enhanced Multi-branch Attention Network (DEMANet) for effective remote sensing image dehazing. The network adopts a U-Net-like structure with three hierarchical downsampling stages to implement progressive feature extraction from shallow to deep layers. Shallow and middle layers use a residual dual-path module to enhance local detailed features via a main-auxiliary dual-branch structure. Deep layers employ a dual-attention module with a two-layer attention mechanism to break the limitation of local receptive fields in traditional convolutions and accurately capture global semantics and haze features. A cross-stage feature interaction module embeds a haze-guided mechanism to locate haze regions based on edge and color differences, enabling cross-stage feature alignment and interaction between encoding and decoding. This reduces information loss during upsampling and improves detail preservation and dehazing performance. Experiments conducted on widely used public remote sensing datasets demonstrate that our innovative approach outperforms existing algorithms in haze removal, while simultaneously preserving intricate image details and color fidelity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Remote Sensing TechnologyImage Processing, Computer-AssistedNeural Networks, ComputerAlgorithms

Autor:innen und Institutionen

  • Qingdao Huanghai University, Qingdao, Shandong, China.
  • School of Physics and Electronic Information, Yantai University, Yantai, Shandong, China.
  • Shandong Data Open Innovation Application Laboratory of Smart grid Advanced Technology, Yantai University, Yantai, Shandong, China.
  • Yantai Dongfang Wisdom Electric Company Limited, Yantai, Shandong, China.

ORCID-Profile: Pengfei He

Förderung

  • Open Project of State Key Laboratory of Synthetical Automation for Process Industries
  • Qingdao West Coast Principal Fund
  • Yantai City 2023 School-Land Integration Development Project Fund
  • Science and Technology-based Small and Medium-sized Enterprise Innovation Capacity Enhancement Project of Yantai City
  • Shandong Provincial Science and Technology-based Small and Medium-sized Enterprises Innovation Capability Enhancement Engineering Plan Project

Zitieren

APA

Liu, P., Liu, S., He, P., & Wang, G. (2026). DEMANet: A dehazing enhanced multi-branch attention network for remote sensing images. PLOS One. https://doi.org/10.1371/journal.pone.0354121

Vancouver

Liu P, Liu S, He P, Wang G. DEMANet: A dehazing enhanced multi-branch attention network for remote sensing images. PLOS One. 2026. doi:10.1371/journal.pone.0354121

BibTeX
@article{Liu2026,
  author = {Liu, Peixue and Liu, Shu and He, Pengfei and Wang, Guoheng},
  title = {DEMANet: A dehazing enhanced multi-branch attention network for remote sensing images},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0354121}
}
Kostenlos starten →