Deep Learning for Weed Detection and Segmentation in Agricultural Crops Using Images Captured by an Unmanned Aerial Vehicle
Remote Sensing · 24.11.2024 · 16 (23) · 4394
DOI: 10.3390/rs16234394 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 24.11.2024. Verfasst von Josef Augusto Oberdan Souza Silva und 10 weiteren Autor:innen. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Council for Scientific and Technological Development (CNPq), Foundation for Research Support of the State of Goiás (FAPEG); Embrapa Rice and Beans, University of Georgia; ACIV—Associação para o Desenvolvimento da Engenharia Civil—Portugal; and internal funding from the Goiano Federal Institute—Campus Ceres.
Abstract (Originalsprache)
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.
Förderung
- National Council for Scientific and Technological Development (CNPq)
- Foundation for Research Support of the State of Goiás (FAPEG); Embrapa Rice and Beans
- University of Georgia; ACIV—Associação para o Desenvolvimento da Engenharia Civil—Portugal; and internal funding from the Goiano Federal Institute—Campus Ceres
Zitieren
APA
Silva, J. A. O. S., Siqueira, V. S. D., Mesquita, M., Vale, L. S. R., Marques, T. D. N. B., Silva, J. L. B. D., Silva, M. V. D., Lacerda, L. N., Oliveira-Júnior, J. F. D., Lima, J. L. M. P. D., & Oliveira, H. F. E. D. (2024). Deep Learning for Weed Detection and Segmentation in Agricultural Crops Using Images Captured by an Unmanned Aerial Vehicle. Remote Sensing, 16(23), 4394. https://doi.org/10.3390/rs16234394
Vancouver
Silva JAOS, Siqueira VSD, Mesquita M, Vale LSR, Marques TDNB, Silva JLBD, et al. Deep Learning for Weed Detection and Segmentation in Agricultural Crops Using Images Captured by an Unmanned Aerial Vehicle. Remote Sensing. 2024;16(23):4394. doi:10.3390/rs16234394
BibTeX
@article{Silva2024,
author = {Silva, Josef Augusto Oberdan Souza and Siqueira, Vilson Soares de and Mesquita, Marcio and Vale, Luís Sérgio Rodrigues and Marques, Thiago do Nascimento Borges and Silva, Jhon Lennon Bezerra da and Silva, Marcos Vinícius da and Lacerda, Lorena Nunes and Oliveira-Júnior, José Francisco de and Lima, João Luís Mendes Pedroso de and Oliveira, Henrique Fonseca Elias de},
title = {Deep Learning for Weed Detection and Segmentation in Agricultural Crops Using Images Captured by an Unmanned Aerial Vehicle},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {23},
pages = {4394},
doi = {10.3390/rs16234394}
}
EUVIMED