Deep Learning for Weed Detection and Segmentation in Agricultural Crops Using Images Captured by an Unmanned Aerial Vehicle

Artificial Intelligence (AI) has changed how processes are developed, and decisions are made in the agricultural area replacing manual and repetitive processes with automated and more efficient ones. This study presents the application of deep learning techniques to detect and segment weeds in agric...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Vol. 16; no. 23; p. 4394
Main Authors: Silva, Josef Augusto Oberdan Souza, Siqueira, Vilson Soares de, Mesquita, Marcio, Vale, Luís Sérgio Rodrigues, Marques, Thiago do Nascimento Borges, Silva, Jhon Lennon Bezerra da, Silva, Marcos Vinícius da, Lacerda, Lorena Nunes, Oliveira-Júnior, José Francisco de, Lima, João Luís Mendes Pedroso de, Oliveira, Henrique Fonseca Elias de
Format: Journal Article
Language:English
Published: Basel MDPI AG 01.12.2024
Subjects:
agricultural crops
Agricultural industry
Algorithms
Artificial intelligence
Artificial neural networks
Computer vision
Crops
Datasets
Deep learning
Detectron2
Drone aircraft
Image processing
Image segmentation
Localization
Machine learning
Machine vision
Mask R-CNN
Neural networks
Performance evaluation
precision agriculture
Recall
remote sensing
Satellites
Segmentation
segmentation algorithms
Soybean
Soybeans
Training
Unmanned aerial vehicles
Weeds
Brazil
ISSN:2072-4292, 2072-4292
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Artificial Intelligence (AI) has changed how processes are developed, and decisions are made in the agricultural area replacing manual and repetitive processes with automated and more efficient ones. This study presents the application of deep learning techniques to detect and segment weeds in agricultural crops by applying models with different architectures in the analysis of images captured by an Unmanned Aerial Vehicle (UAV). This study contributes to the computer vision field by comparing the performance of the You Only Look Once (YOLOv8n, YOLOv8s, YOLOv8m, and YOLOv8l), Mask R-CNN (with framework Detectron2), and U-Net models, making public the dataset with aerial images of soybeans and beans. The models were trained using a dataset consisting of 3021 images, randomly divided into test, validation, and training sets, which were annotated, resized, and increased using the Roboflow application interface. Evaluation metrics were used, which included training efficiency (mAP50 and mAP50-90), precision, accuracy, and recall in the model’s evaluation and comparison. The YOLOv8s variant achieved higher performance with an mAP50 of 97%, precision of 99.7%, and recall of 99% when compared to the other models. The data from this manuscript show that deep learning models can generate efficient results for automatic weed detection when trained with a well-labeled and large set. Furthermore, this study demonstrated the great potential of using advanced object segmentation algorithms in detecting weeds in soybean and bean crops.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2072-4292
2072-4292
DOI:10.3390/rs16234394