EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics-Prior-Guided Feature Pyramid Network for Unified Multi-Angle Spectral–Polarimetric Cloud Detection

Shu Li, Xingyuan Ji, Xiaoxue Chu, Song Ye, Ziyang Zhang, Yongyin Gan, Xinqiang Wang, Fangyuan Wang

Remote Sensing · 12.04.2026 · 18 (8) · 1150

DOI: 10.3390/rs18081150 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 12.04.2026. Verfasst von Shu Li und 7 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Central Guidance Fund for Local Scientific and Technological Development, the Guangxi Science and Technology Program Project, the National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate cloud detection remains a significant challenge due to the spectral ambiguity between clouds and bright or heterogeneous surfaces (e.g., snow, desert). While multi-angle and polarization data offer rich information, the discriminative power of joint spectral analysis for resolving these ambiguities has been underexploited. In this work, we demonstrate that physically motivated spectral band ratios and differences can robustly enhance cloud signatures. Motivated by this insight, we propose a novel deep learning framework, the Multi-angle Polarization Feature Pyramid Structure (MP-FPS), that explicitly leverages joint spectral features as discriminative priors. Our architecture employs a dual-branch network to disentangle and adaptively fuse spectral and multi-angle polarization modalities. Within this framework, a hierarchical, multi-scale cross-channel multi-angle fusion module dynamically captures spatial–spectral–angular dependencies, enriching the structural representation of clouds. Furthermore, a channel-space dual-path attention mechanism refines sub-pixel responses, significantly improving detection accuracy in challenging regions such as cloud edges and thin cirrus. Evaluated on the global POLDER-3 dataset, MP-FPS achieves a mean Intersection over Union (mIoU) of 0.8662 across diverse surface types, surpassing the official baseline by 12.4%. This study establishes joint spectral analysis as a critical enabler for high-precision cloud masking, and demonstrates its synergistic value when integrated with multi-angle polarimetric information in a unified deep architecture.

Förderung

  • the Central Guidance Fund for Local Scientific and Technological Development
  • the Guangxi Science and Technology Program Project
  • the National Key Research and Development Program of China
  • the Graduate Education Innovation Program of Guilin University of Electronic Technology

Zitieren

APA

Li, S., Ji, X., Chu, X., Ye, S., Zhang, Z., Gan, Y., Wang, X., & Wang, F. (2026). Physics-Prior-Guided Feature Pyramid Network for Unified Multi-Angle Spectral–Polarimetric Cloud Detection. Remote Sensing, 18(8), 1150. https://doi.org/10.3390/rs18081150

Vancouver

Li S, Ji X, Chu X, Ye S, Zhang Z, Gan Y, et al. Physics-Prior-Guided Feature Pyramid Network for Unified Multi-Angle Spectral–Polarimetric Cloud Detection. Remote Sensing. 2026;18(8):1150. doi:10.3390/rs18081150

BibTeX
@article{Li2026,
  author = {Li, Shu and Ji, Xingyuan and Chu, Xiaoxue and Ye, Song and Zhang, Ziyang and Gan, Yongyin and Wang, Xinqiang and Wang, Fangyuan},
  title = {Physics-Prior-Guided Feature Pyramid Network for Unified Multi-Angle Spectral–Polarimetric Cloud Detection},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {8},
  pages = {1150},
  doi = {10.3390/rs18081150}
}
Kostenlos starten →