Semantic Segmentation of Multispectral Remote Sensing Imagery for Coastal Wetlands with SegFormer
Remote Sensing · 28.02.2026 · 18 (5) · 745
DOI: 10.3390/rs18050745 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 28.02.2026. Verfasst von Simin Peng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China.
Abstract (Originalsprache)
Pixel-level semantic segmentation plays an essential role in coastal wetland monitoring using multispectral remote sensing imagery. However, accurate mapping remains challenging due to spectral confusion among heterogeneous land-cover types, fragmented spatial structures, and pronounced class imbalance. Based on the situation, we used the original SegFormer as the basic framework and developed an improved framework to better suit the characteristics of coastal wetland scenes. Prior to the encoder, we introduced a Spectral-Aware Embedding (SAE) module to strengthen inter-band feature representation through spectral projection and adaptive channel weighting. In the decoder, we constructed a Wetland Boundary-Refined Decoder (WBRD), utilizing a dual-path refinement strategy to capture fine-scale textures and a multi-scale boundary attention mechanism to enhance the delineation of irregular boundaries. Additionally, we incorporated a Wetland Imbalance Loss (WIL) during training to moderate the influence of dominant classes. In this article, we evaluated our framework on the Yan14 dataset. The results showcased the framework’s effectiveness, improving segmentation accuracy and boundary fidelity, particularly for rare and narrow wetland categories, while maintaining reasonable computational efficiency.
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Program of China
Zitieren
APA
Peng, S., Xie, H., Liu, N., & Zeng, Y. (2026). Semantic Segmentation of Multispectral Remote Sensing Imagery for Coastal Wetlands with SegFormer. Remote Sensing, 18(5), 745. https://doi.org/10.3390/rs18050745
Vancouver
Peng S, Xie H, Liu N, Zeng Y. Semantic Segmentation of Multispectral Remote Sensing Imagery for Coastal Wetlands with SegFormer. Remote Sensing. 2026;18(5):745. doi:10.3390/rs18050745
BibTeX
@article{Peng2026,
author = {Peng, Simin and Xie, Huachen and Liu, Nian and Zeng, Yi},
title = {Semantic Segmentation of Multispectral Remote Sensing Imagery for Coastal Wetlands with SegFormer},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {5},
pages = {745},
doi = {10.3390/rs18050745}
}
EUVIMED