EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on Classification of Grassland Degeneration Indicator Objects Based on UAV Hyperspectral Remote Sensing and 3D_RNet-O Model

Eerdoumutu Jin, Jianmin Du, Yuge Bi, Shengli Wang, Xinchao Gao

Sensors · 08.02.2024 · 24 (4) · 1114

DOI: 10.3390/s24041114 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 08.02.2024. Verfasst von Eerdoumutu Jin und 4 weiteren Autor:innen. Beteiligte Einrichtung: Mechanical and Electrical Engineering College, Inner Mongolia Agricultural University, Hohhot 010018, China. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Inner Mongolia Autonomous Region Higher Education Science Research Project, Higher Education Key Research Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time and high-precision land cover classification is the foundation for efficient and quantitative research on grassland degradation using remote sensing techniques. In view of the shortcomings of manual surveying and satellite remote sensing, this study focuses on the identification and classification of grass species indicating grassland degradation. We constructed a UAV-based hyperspectral remote sensing system and collected field data in grassland areas. By applying artificial intelligence technology, we developed a 3D_RNet-O model based on convolutional neural networks, effectively addressing technical challenges in hyperspectral remote sensing identification and classification of grassland degradation indicators, such as low reflectance of vegetation, flat spectral curves, and sparse distribution. The results showed that the model achieved a classification accuracy of 99.05% by optimizing hyperparameter combinations based on improving residual block structures. The establishment of the UAV-based hyperspectral remote sensing system and the proposed 3D_RNet-O classification model provide possibilities for further research on low-altitude hyperspectral remote sensing in grassland ecology.

Schlagwörter

Stichwörter der Autor:innen

Unmanned Aerial Vehicleconvolutional neural networkdeep learningdesert grasslandlow-altitude remote sensing

Autor:innen und Institutionen

  • Mechanical and Electrical Engineering College, Inner Mongolia Agricultural University, Hohhot 010018, China.

Förderung

  • National Natural Science Foundation of China
  • Inner Mongolia Autonomous Region Higher Education Science Research Project
  • Higher Education Key Research Project
  • Natural Science Foundation Joint Fund Project
  • Research Key Project at Universities of Inner Mongolia Autonomous Region
  • Inner Mongolia Autonomous Region Natural Science Foundation Joint Fund

Zitieren

APA

Jin, E., Du, J., Bi, Y., Wang, S., & Gao, X. (2024). Research on Classification of Grassland Degeneration Indicator Objects Based on UAV Hyperspectral Remote Sensing and 3D_RNet-O Model. Sensors, 24(4), 1114. https://doi.org/10.3390/s24041114

Vancouver

Jin E, Du J, Bi Y, Wang S, Gao X. Research on Classification of Grassland Degeneration Indicator Objects Based on UAV Hyperspectral Remote Sensing and 3D_RNet-O Model. Sensors. 2024;24(4):1114. doi:10.3390/s24041114

BibTeX
@article{Jin2024,
  author = {Jin, Eerdoumutu and Du, Jianmin and Bi, Yuge and Wang, Shengli and Gao, Xinchao},
  title = {Research on Classification of Grassland Degeneration Indicator Objects Based on UAV Hyperspectral Remote Sensing and 3D_RNet-O Model},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {4},
  pages = {1114},
  doi = {10.3390/s24041114}
}
Kostenlos starten →