EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semantic Segmentation of China’s Coastal Wetlands Based on Sentinel-2 and Segformer

Xufeng Lin, Youwei Cheng, Gong Chen, Wenjing Chen, Rong Chen, Demin Gao, Yinlong Zhang, Yongbo Wu

Remote Sensing · 25.07.2023 · 15 (15) · 3714

DOI: 10.3390/rs15153714 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 25.07.2023. Verfasst von Xufeng Lin und 7 weiteren Autor:innen. Die Arbeit wurde bisher 56-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Forestry Science & Technology Innovation and Extension Project, Provincial Student Innovation Training Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Concerning the ever-changing wetland environment, the efficient extraction of wetland information holds great significance for the research and management of wetland ecosystems. China’s vast coastal wetlands possess rich and diverse geographical features. This study employs the SegFormer model and Sentinel-2 data to conduct a wetland classification study for coastal wetlands in Yancheng, Jiangsu, China. After preprocessing the Sentinel data, nine classification objects (construction land, Spartina alterniflora (S. alterniflora), Suaeda salsa (S. salsa), Phragmites australis (P. australis), farmland, river system, aquaculture and tidal falt) were identified based on the previous literature and remote sensing images. Moreover, mAcc, mIoU, aAcc, Precision, Recall and F-1 score were chosen as evaluation indicators. This study explores the potential and effectiveness of multiple methods, including data image processing, machine learning and deep learning. The results indicate that SegFormer is the best model for wetland classification, efficiently and accurately extracting small-scale features. With mIoU (0.81), mAcc (0.87), aAcc (0.94), mPrecision (0.901), mRecall (0.876) and mFscore (0.887) higher than other models. In the face of unbalanced wetland categories, combining CrossEntropyLoss and FocalLoss in the loss function can improve several indicators of difficult cases to be segmented, enhancing the classification accuracy and generalization ability of the model. Finally, the category scale pie chart of Yancheng Binhai wetlands was plotted. In conclusion, this study achieves an effective segmentation of Yancheng coastal wetlands based on the semantic segmentation method of deep learning, providing technical support and reference value for subsequent research on wetland values.

Förderung

  • Jiangsu Forestry Science & Technology Innovation and Extension Project
  • Provincial Student Innovation Training Program

Zitieren

APA

Lin, X., Cheng, Y., Chen, G., Chen, W., Chen, R., Gao, D., Zhang, Y., & Wu, Y. (2023). Semantic Segmentation of China’s Coastal Wetlands Based on Sentinel-2 and Segformer. Remote Sensing, 15(15), 3714. https://doi.org/10.3390/rs15153714

Vancouver

Lin X, Cheng Y, Chen G, Chen W, Chen R, Gao D, et al. Semantic Segmentation of China’s Coastal Wetlands Based on Sentinel-2 and Segformer. Remote Sensing. 2023;15(15):3714. doi:10.3390/rs15153714

BibTeX
@article{Lin2023,
  author = {Lin, Xufeng and Cheng, Youwei and Chen, Gong and Chen, Wenjing and Chen, Rong and Gao, Demin and Zhang, Yinlong and Wu, Yongbo},
  title = {Semantic Segmentation of China’s Coastal Wetlands Based on Sentinel-2 and Segformer},
  journal = {Remote Sensing},
  year = {2023},
  volume = {15},
  number = {15},
  pages = {3714},
  doi = {10.3390/rs15153714}
}
Kostenlos starten →