Publicação

A YOLO-Based Approach for Detection of Olive Knot Disease through UAV and Computer Vision Technologies

Detalhes bibliográficos
Resumo:	This work presents an approach for detecting olive knot disease in olive trees, utilizing Computer Vision (CV), Unmanned Aerial Vehicle (UAV) based imagery, and Machine Learning (ML) within the context of Precision Agriculture (PA). The study focuses on applying the You Only Look Once (YOLO) deep learning architecture to develop a model capable of identifying trees affected by the disease with accuracy and speed. By integrating UAV technology with object detection algorithms, this approach enables real-time monitoring of olive plantations, supporting early detection and targeted interventions. This study emphasizes the potential of combining drone imaging and ML to drive sustainable and practical solutions in PA. Results show that this method can potentially improve crop management by reducing human labor and contributing to the enhancement of disease control strategies.
Autores principais:	Morais, Maurício Herche Fófano de
Outros Autores:	Mendes, João; Santos, Murillo Ferreira dos; Fernandes, Fernanda Mara; Lima, José; Pereira, Ana I.
Assunto:	Unmanned aerial vehicle Disease detection Olive knot Computer vision Deep learning YOLO
Ano:	2025
País:	Portugal
Tipo de documento:	comunicação em conferência
Tipo de acesso:	acesso aberto
Instituição associada:	Instituto Politécnico de Bragança
Idioma:	inglês
Origem:	Biblioteca Digital do IPB

Descrição
Resumo:	This work presents an approach for detecting olive knot disease in olive trees, utilizing Computer Vision (CV), Unmanned Aerial Vehicle (UAV) based imagery, and Machine Learning (ML) within the context of Precision Agriculture (PA). The study focuses on applying the You Only Look Once (YOLO) deep learning architecture to develop a model capable of identifying trees affected by the disease with accuracy and speed. By integrating UAV technology with object detection algorithms, this approach enables real-time monitoring of olive plantations, supporting early detection and targeted interventions. This study emphasizes the potential of combining drone imaging and ML to drive sustainable and practical solutions in PA. Results show that this method can potentially improve crop management by reducing human labor and contributing to the enhancement of disease control strategies.

Carregando projetos financiados...