EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Extraction of Photosynthetic and Non-Photosynthetic Vegetation Cover in Typical Grasslands Using UAV Imagery and an Improved SegFormer Model

Jie He, Xiaoping Zhang, Weibin Li, Du Lyu, Yi Ren, Wenlin Fu

Remote Sensing · 12.09.2025 · 17 (18) · 3162

DOI: 10.3390/rs17183162 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 12.09.2025. Verfasst von Jie He und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Proof of Concept Fund, Shaanxi Provincial Water Conservancy Fund Project, Shaanxi Coal Geology Group Co., Ltd..

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate monitoring of the coverage and distribution of photosynthetic (PV) and non-photosynthetic vegetation (NPV) in the grasslands of semi-arid regions is crucial for understanding the environment and addressing climate change. However, the extraction of PV and NPV information from Unmanned Aerial Vehicle (UAV) remote sensing imagery is often hindered by challenges such as low extraction accuracy and blurred boundaries. To overcome these limitations, this study proposed an improved semantic segmentation model, designated SegFormer-CPED. The model was developed based on the SegFormer architecture, incorporating several synergistic optimizations. Specifically, a Convolutional Block Attention Module (CBAM) was integrated into the encoder to enhance early-stage feature perception, while a Polarized Self-Attention (PSA) module was embedded to strengthen contextual understanding and mitigate semantic loss. An Edge Contour Extraction Module (ECEM) was introduced to refine boundary details. Concurrently, the Dice Loss function was employed to replace the Cross-Entropy Loss, thereby more effectively addressing the class imbalance issue and significantly improving both the segmentation accuracy and boundary clarity of PV and NPV. To support model development, a high-quality PV and NPV segmentation dataset for Hengshan grassland was also constructed. Comprehensive experimental results demonstrated that the proposed SegFormer-CPED model achieved state-of-the-art performance, with a mIoU of 93.26% and an F1-score of 96.44%. It significantly outperformed classic architectures and surpassed all leading frameworks benchmarked here. Its high-fidelity maps can bridge field surveys and satellite remote sensing. Ablation studies verified the effectiveness of each improved module and its synergistic interplay. Moreover, this study successfully utilized SegFormer-CPED to perform fine-grained monitoring of the spatiotemporal dynamics of PV and NPV in the Hengshan grassland, confirming that the model-estimated fPV and fNPV were highly correlated with ground survey data. The proposed SegFormer-CPED model provides a robust and effective solution for the precise, semi-automated extraction of PV and NPV from high-resolution UAV imagery.

Förderung

  • Proof of Concept Fund
  • Shaanxi Provincial Water Conservancy Fund Project
  • Shaanxi Coal Geology Group Co., Ltd.
  • Shaanxi Provincial Public Welfare Geological Survey Project

Zitieren

APA

He, J., Zhang, X., Li, W., Lyu, D., Ren, Y., & Fu, W. (2025). Extraction of Photosynthetic and Non-Photosynthetic Vegetation Cover in Typical Grasslands Using UAV Imagery and an Improved SegFormer Model. Remote Sensing, 17(18), 3162. https://doi.org/10.3390/rs17183162

Vancouver

He J, Zhang X, Li W, Lyu D, Ren Y, Fu W. Extraction of Photosynthetic and Non-Photosynthetic Vegetation Cover in Typical Grasslands Using UAV Imagery and an Improved SegFormer Model. Remote Sensing. 2025;17(18):3162. doi:10.3390/rs17183162

BibTeX
@article{He2025,
  author = {He, Jie and Zhang, Xiaoping and Li, Weibin and Lyu, Du and Ren, Yi and Fu, Wenlin},
  title = {Extraction of Photosynthetic and Non-Photosynthetic Vegetation Cover in Typical Grasslands Using UAV Imagery and an Improved SegFormer Model},
  journal = {Remote Sensing},
  year = {2025},
  volume = {17},
  number = {18},
  pages = {3162},
  doi = {10.3390/rs17183162}
}
Kostenlos starten →