EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TAHRNet: An Improved HRNet-Based Semantic Segmentation Model for Mangrove Remote Sensing Imagery

Haonan Lin, Dongyang Fu, Chuhong Wang, Jinjun Huang, Hanrui Wu, Yu Huang, Litian Xiong

Forests · 25.04.2026 · 17 (5) · 525

DOI: 10.3390/f17050525 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Forests, online erschienen am 25.04.2026. Verfasst von Haonan Lin und 6 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Ocean University, Southern Marine Science and Engineering Guangdong Laboratory, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mangrove represent vital coastal ecosystems that contribute to shoreline stabilization, ecological balance, and environmental management. Nevertheless, the precise delineation of mangrove regions using remote sensing data is often impeded by spectral similarities with intertidal mudflats and aquatic features, alongside the irregular spatial patterns and intricate margins of mangrove stands. This research utilizes high-resolution Gaofen-6 (GF-6) satellite observations as the foundational data to develop Triplet Axial High-Resolution Network (TAHRNet), a semantic segmentation architecture derived from the High-Resolution Network with Object-Contextual Representations (HRNet-OCR) framework for mangrove identification. The model integrates a Triplet Attention module to facilitate cross-dimensional feature dependencies and an improved Multi-Head Sequential Axial Attention mechanism to capture long-range spatial context while maintaining structural consistency. Based on evaluations using the test dataset, TAHRNet yielded a Mean Intersection over Union (MIoU) of 92.01% and a Overall Accuracy of 96.38%. Relative to U-Net and SegFormer, the proposed approach showed MIoU improvements of 5.25% and 1.88%, with corresponding Accuracy gains of 2.68% and 0.94%. Further application to coastal mapping in Zhanjiang produced results that align with manual visual interpretation. These findings suggest that TAHRNet is a viable tool for mangrove extraction and can provide technical support for coastal monitoring and ecological analysis.

Förderung

  • Guangdong Ocean University
  • Southern Marine Science and Engineering Guangdong Laboratory
  • National Natural Science Foundation of China
  • Department of Education of Guangdong Province

Zitieren

APA

Lin, H., Fu, D., Wang, C., Huang, J., Wu, H., Huang, Y., & Xiong, L. (2026). TAHRNet: An Improved HRNet-Based Semantic Segmentation Model for Mangrove Remote Sensing Imagery. Forests, 17(5), 525. https://doi.org/10.3390/f17050525

Vancouver

Lin H, Fu D, Wang C, Huang J, Wu H, Huang Y, et al. TAHRNet: An Improved HRNet-Based Semantic Segmentation Model for Mangrove Remote Sensing Imagery. Forests. 2026;17(5):525. doi:10.3390/f17050525

BibTeX
@article{Lin2026,
  author = {Lin, Haonan and Fu, Dongyang and Wang, Chuhong and Huang, Jinjun and Wu, Hanrui and Huang, Yu and Xiong, Litian},
  title = {TAHRNet: An Improved HRNet-Based Semantic Segmentation Model for Mangrove Remote Sensing Imagery},
  journal = {Forests},
  year = {2026},
  volume = {17},
  number = {5},
  pages = {525},
  doi = {10.3390/f17050525}
}
Kostenlos starten →