Intelligent agriculture: deep learning in UAV-based remote sensing imagery for crop diseases and pests detection

Controlling crop diseases and pests is essential for intelligent agriculture (IA) due to the significant reduction in crop yield and quality caused by these problems. In recent years, the remote sensing (RS) areas has been prevailed over by unmanned aerial vehicle (UAV)-based applications. Herein, b...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Frontiers in plant science Jg. 15; S. 1435016
Hauptverfasser: Zhu, Hongyan, Lin, Chengzhi, Liu, Gengqi, Wang, Dani, Qin, Shuai, Li, Anjie, Xu, Jun-Li, He, Yong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Switzerland Frontiers Media SA 24.10.2024
Frontiers Media S.A
Schlagworte:
Agricultural production
Agriculture
Algorithms
Artificial intelligence
Crop diseases
crop diseases and pests
Crop yield
Deep learning
deep learning (DL)
intelligent agriculture (IA)
Large language models
Machine learning
Pest control
Pests
Plant diseases
Plant Science
Remote sensing
remote sensing (RS)
Sensors
unmanned aerial vehicle (UAV)
Unmanned aerial vehicles
unmanned aerial vehicle (UAV)
crop diseases and pests
remote sensing (RS)
intelligent agriculture (IA)
deep learning (DL)
ISSN:1664-462X, 1664-462X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Controlling crop diseases and pests is essential for intelligent agriculture (IA) due to the significant reduction in crop yield and quality caused by these problems. In recent years, the remote sensing (RS) areas has been prevailed over by unmanned aerial vehicle (UAV)-based applications. Herein, by using methods such as keyword co-contribution analysis and author co-occurrence analysis in bibliometrics, we found out the hot-spots of this field. UAV platforms equipped with various types of cameras and other advanced sensors, combined with artificial intelligence (AI) algorithms, especially for deep learning (DL) were reviewed. Acknowledging the critical role of comprehending crop diseases and pests, along with their defining traits, we provided a concise overview as indispensable foundational knowledge. Additionally, some widely used traditional machine learning (ML) algorithms were presented and the performance results were tabulated to form a comparison. Furthermore, we summarized crop diseases and pests monitoring techniques using DL and introduced the application for prediction and classification. Take it a step further, the newest and the most concerned applications of large language model (LLM) and large vision model (LVM) in agriculture were also mentioned herein. At the end of this review, we comprehensively discussed some deficiencies in the existing research and some challenges to be solved, as well as some practical solutions and suggestions in the near future.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Review-3
content type line 23
Ke Xu, Anhui Polytechnic University, China
José Luis Hernández-Hernández, Chilpancingo Institute of Technology, Mexico
These authors have contributed equally to this work and share first authorship
Reviewed by: Lingxian Zhang, China Agricultural University, China
Edited by: Jun Ni, Nanjing Agricultural University, China
ISSN:1664-462X
1664-462X
DOI:10.3389/fpls.2024.1435016