EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Novel PolSAR Classification Method Based on Dynamic Weight Adjustment of Heterogeneous Feature Fusion

Yan Duan, Sonya Coleman, Li Yang, Haijun Wang, Guangwei Wang, Dermot Kerr

Remote Sensing · 12.04.2026 · 18 (8) · 1140

DOI: 10.3390/rs18081140 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 12.04.2026. Verfasst von Yan Duan und 5 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Project of Scientific Research Program of Hubei Provincial Department of Education, China Scholarship Council, University-level Research Start-up Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In response to the problems of insufficient fusion of amplitude and phase heterogeneity features, deficient direction sensitivity modeling, and a single fusion level in the polarimetric synthetic aperture radar classification task, this paper proposes a PolSAR classification method based on dynamic weight adjustment and heterogeneous feature fusion. This method utilizes a dual-branch parallel structure to extract polarization features and landcover amplitude-phase direction difference features separately and constructs a three-level progressive fusion strategy of sub-branch, cross-branch, and decision layer to achieve adaptive complementation of heterogeneous features. Experiments on three standard datasets show that the classification accuracy and visual consistency of this method are significantly superior to the classical methods, with the overall accuracy being improved by 1.5% to 2.4%.

Förderung

  • Project of Scientific Research Program of Hubei Provincial Department of Education
  • China Scholarship Council
  • University-level Research Start-up Fund

Zitieren

APA

Duan, Y., Coleman, S., Yang, L., Wang, H., Wang, G., & Kerr, D. (2026). A Novel PolSAR Classification Method Based on Dynamic Weight Adjustment of Heterogeneous Feature Fusion. Remote Sensing, 18(8), 1140. https://doi.org/10.3390/rs18081140

Vancouver

Duan Y, Coleman S, Yang L, Wang H, Wang G, Kerr D. A Novel PolSAR Classification Method Based on Dynamic Weight Adjustment of Heterogeneous Feature Fusion. Remote Sensing. 2026;18(8):1140. doi:10.3390/rs18081140

BibTeX
@article{Duan2026,
  author = {Duan, Yan and Coleman, Sonya and Yang, Li and Wang, Haijun and Wang, Guangwei and Kerr, Dermot},
  title = {A Novel PolSAR Classification Method Based on Dynamic Weight Adjustment of Heterogeneous Feature Fusion},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {8},
  pages = {1140},
  doi = {10.3390/rs18081140}
}
Kostenlos starten →