YOLO deep learning algorithm for object detection in agriculture: a review

YOLO represents the one-stage object detection also called regression-based object detection. Object in the given input is directly classified and located instead of using the candidate region. The accuracy from two-stage detection is higher than one-stage detection where one-stage object detection...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of agricultural engineering (Pisa, Italy) Jg. 55; H. 4
Hauptverfasser: Kanna S, Kamalesh, Ramalingam, Kumaraperumal, P, Pazhanivelan, R, Jagadeeswaran, P.C., Prabu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Bologna PAGEPress Publications 01.01.2024
Schlagworte:
Accuracy
Agriculture
Algorithms
computer vision
Deep learning
Environmental monitoring
Land use
Machine learning
object detection
Object recognition
Pests
Plant diseases
real-time farming
Remote sensing
Urban planning
Wildlife
YOLO
ISSN:1974-7071, 2239-6268
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:YOLO represents the one-stage object detection also called regression-based object detection. Object in the given input is directly classified and located instead of using the candidate region. The accuracy from two-stage detection is higher than one-stage detection where one-stage object detection speed is higher than two-stage object detection. YOLO has become popular because of its Detection accuracy, good generalization, open-source, and speed. YOLO boasts exceptional speed due to its approach of using regression problems for frame detection, eliminating the need for a complex pipeline.  In agriculture, using remote sensing and drone technologies YOLO classifies and detects crops, diseases, and pests, and is also used for land use mapping, environmental monitoring, urban planning, and wildlife. Recent research highlights YOLO's impressive performance in various agricultural applications. For instance, YOLOv4 demonstrated high accuracy in counting and locating small objects in UAV-captured images of bean plants, achieving an AP of 84.8% and a recall of 89%. Similarly, YOLOv5 showed significant precision in identifying rice leaf diseases, with a precision rate of 90%. In this review, we discuss the basic principles behind YOLO, different versions of YOLO, limitations, and YOLO application in agriculture and farming.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1974-7071
2239-6268
DOI:10.4081/jae.2024.1641