EUVIMEDEUVIMED entdecken
Crossref

PMDA-Net: a polarization-conditioned multi-scale dynamic attention network for polarimetric hyperspectral camouflage target classification

Lining Yan, Yunhua Cao iD, Lu Bai iD, Xing Guo

Applied Optics · 10.11.2026 · 65 (32) · 11563

DOI: 10.1364/ao.610347 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Optics, online erschienen am 06.11.2026. Verfasst von Lining Yan und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Physics, Xidian University, Xi'an, Shaanxi 710071, China. Die Arbeit nennt 27 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, Postgraduate Innovation Fund of Xidian University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To effectively fuse heterogeneous polarimetric hyperspectral data and improve the classification performance of camouflage targets in complex backgrounds, this paper proposes a polarization-conditioned multi-scale dynamic attention network (PMDA-Net). PMDA-Net adopts a dual-stream framework for modality-specific feature extraction, where spectral and polarimetric information are separately modeled. A multi-scale dynamic AoLP attention module is designed to transform geometric information encoded in the angle of linear polarization into dynamic weights. A polarization-conditioned spatial-channel attention module is designed to adaptively calibrate spectral features using polarimetric information, facilitating cross-modal interaction and complementary feature fusion. Experimental results on three self-collected datasets and one public dataset show that PMDA-Net outperforms mainstream hyperspectral deep learning models, traditional polarization-feature-based methods, and recent multimodal fusion methods on all four datasets. Compared with the model using only hyperspectral information, PMDA-Net improves the average accuracy by 5.87, 5.38, 25.71, and 5.01 percentage points on the four datasets, respectively. These results indicate that polarization information can effectively complement spectral representations and help suppress aliasing responses caused by spectral similarity in complex scenes. This work provides a promising approach for polarimetric hyperspectral image classification and camouflage target recognition.

Autor:innen und Institutionen

  • School of Physics, Xidian University, Xi'an, Shaanxi 710071, China.
  • School of Electronic Engineering, Xidian University, Xi'an, Shaanxi 710071, China.

ORCID-Profile: Yunhua Cao, Lu Bai

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • Postgraduate Innovation Fund of Xidian University

Zitieren

APA

Yan, L., Cao, Y., Bai, L., & Guo, X. (2026). PMDA-Net: a polarization-conditioned multi-scale dynamic attention network for polarimetric hyperspectral camouflage target classification. Applied Optics, 65(32), 11563. https://doi.org/10.1364/ao.610347

Vancouver

Yan L, Cao Y, Bai L, Guo X. PMDA-Net: a polarization-conditioned multi-scale dynamic attention network for polarimetric hyperspectral camouflage target classification. Applied Optics. 2026;65(32):11563. doi:10.1364/ao.610347

BibTeX
@article{Yan2026,
  author = {Yan, Lining and Cao, Yunhua and Bai, Lu and Guo, Xing},
  title = {PMDA-Net: a polarization-conditioned multi-scale dynamic attention network for polarimetric hyperspectral camouflage target classification},
  journal = {Applied Optics},
  year = {2026},
  volume = {65},
  number = {32},
  pages = {11563},
  doi = {10.1364/ao.610347}
}
Kostenlos starten →