EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

High-Resolution Mapping Coastal Wetland Vegetation Using Frequency-Augmented Deep Learning Method

Ning Gao, Xinyuan Du, Peng Xu, Erding Gao, Yixin Yang

Remote Sensing · 13.01.2026 · 18 (2) · 247

DOI: 10.3390/rs18020247 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 13.01.2026. Verfasst von Ning Gao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Coastal wetland vegetation exhibits pronounced spectral mixing, complex mosaic spatial patterns, and small target sizes, posing considerable challenges for fine-grained classification in high-resolution UAV imagery. At present, remote sensing classification of ground objects based on deep learning mainly relies on spectral and structural features, while the frequency domain features of ground objects are not fully considered. To address these issues, this study proposes a vegetation classification model that integrates spatial-domain and frequency-domain features. The model enhances global contextual modeling through a large-kernel convolution branch, while a frequency-domain interaction branch separates and fuses low-frequency structural information with high-frequency details. In addition, a shallow auxiliary supervision module is introduced to improve local detail learning and stabilize training. With a compact parameter scale suitable for real-world deployment, the proposed framework effectively adapts to high-resolution remote sensing scenarios. Experiments on typical coastal wetland vegetation including Reeds, Spartina alterniflora, and Suaeda salsa demonstrate that the proposed method consistently outperforms representative segmentation models such as UNet, DeepLabV3, TransUNet, SegFormer, D-LinkNet, and MCCA across multiple metrics including Accuracy, Recall, F1 Score, and mIoU. Overall, the results show that the proposed model effectively addresses the challenges of subtle spectral differences, pervasive species mixture, and intricate structural details, offering a robust and efficient solution for UAV-based wetland vegetation mapping and ecological monitoring.

Zitieren

APA

Gao, N., Du, X., Xu, P., Gao, E., & Yang, Y. (2026). High-Resolution Mapping Coastal Wetland Vegetation Using Frequency-Augmented Deep Learning Method. Remote Sensing, 18(2), 247. https://doi.org/10.3390/rs18020247

Vancouver

Gao N, Du X, Xu P, Gao E, Yang Y. High-Resolution Mapping Coastal Wetland Vegetation Using Frequency-Augmented Deep Learning Method. Remote Sensing. 2026;18(2):247. doi:10.3390/rs18020247

BibTeX
@article{Gao2026,
  author = {Gao, Ning and Du, Xinyuan and Xu, Peng and Gao, Erding and Yang, Yixin},
  title = {High-Resolution Mapping Coastal Wetland Vegetation Using Frequency-Augmented Deep Learning Method},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {2},
  pages = {247},
  doi = {10.3390/rs18020247}
}
Kostenlos starten →