EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Land-use classification based on high-resolution remote sensing imagery and deep learning models

Mengmeng Hao, Xiaohan Dong, Dong Jiang iD, Xianwen Yu, Fangyu Ding iD, Jun Zhuo

PLOS ONE · 18.04.2024 · 19 (4) · e0300473

DOI: 10.1371/journal.pone.0300473 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 18.04.2024. Verfasst von Mengmeng Hao und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, China. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Fund Project, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-resolution imagery and deep learning models have gained increasing importance in land-use mapping. In recent years, several new deep learning network modeling methods have surfaced. However, there has been a lack of a clear understanding of the performance of these models. In this study, we applied four well-established and robust deep learning models (FCN-8s, SegNet, U-Net, and Swin-UNet) to an open benchmark high-resolution remote sensing dataset to compare their performance in land-use mapping. The results indicate that FCN-8s, SegNet, U-Net, and Swin-UNet achieved overall accuracies of 80.73%, 89.86%, 91.90%, and 96.01%, respectively, on the test set. Furthermore, we assessed the generalization ability of these models using two measures: intersection of union and F1 score, which highlight Swin-UNet’s superior robustness compared to the other three models. In summary, our study provides a systematic analysis of the classification differences among these four deep learning models through experiments. It serves as a valuable reference for selecting models in future research, particularly in scenarios such as land-use mapping, urban functional area recognition, and natural resource management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningRemote Sensing TechnologyGeneralization, PsychologicalImagery, Psychotherapy

Autor:innen und Institutionen

  • Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, China.
  • College of Resources and Environment, University of Chinese Academy of Sciences, Beijing, China.
  • ByteDance Inc, Beijing, China.

ORCID-Profile: Dong Jiang, Fangyu Ding

Förderung

  • National Science Fund Project
  • National Natural Science Foundation of China

Zitieren

APA

Hao, M., Dong, X., Jiang, D., Yu, X., Ding, F., & Zhuo, J. (2024). Land-use classification based on high-resolution remote sensing imagery and deep learning models. PLOS ONE, 19(4), e0300473. https://doi.org/10.1371/journal.pone.0300473

Vancouver

Hao M, Dong X, Jiang D, Yu X, Ding F, Zhuo J. Land-use classification based on high-resolution remote sensing imagery and deep learning models. PLOS ONE. 2024;19(4):e0300473. doi:10.1371/journal.pone.0300473

BibTeX
@article{Hao2024,
  author = {Hao, Mengmeng and Dong, Xiaohan and Jiang, Dong and Yu, Xianwen and Ding, Fangyu and Zhuo, Jun},
  title = {Land-use classification based on high-resolution remote sensing imagery and deep learning models},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {4},
  pages = {e0300473},
  doi = {10.1371/journal.pone.0300473}
}
Kostenlos starten →