YOLO performance analysis for real-time detection of soybean pests

Autor(es)

Tetila, Everton Castelao ; da Silveira, Fabio Amaral Godoy ; Costa, Anderson Bessa da ; Amorim, Willian Paraguassu ; Astolfi, Gilberto ; Pistori, Hemerson ; Barbedo, Jayme Garcia Arnal

• Tipo de documento: Artigo Científico
• Fonte: SMART AGRICULTURAL TECHNOLOGY; v. 7, p. 10-pg., 2024-02-05.

Resumo

In this work, we evaluated the You Only Look Once (YOLO) architecture for real-time detection of soybean pests. We collected images of the soybean plantation in different days, locations and weather conditions, between the phenological stages R1 to R6, which have a high occurrence of insect pests in soybean fields. We employed a 5 -fold cross -validation paired with four metrics to evaluate the classification performance and three metrics to evaluate the detection performance. Experimental results showed that YOLOv3 architecture trained with a batch size of 32 leads to higher classification and detection rates compared to batch sizes of 4 and 16. The results indicate that the evaluated architecture can support specialists and farmers in monitoring the need for pest control action in soybean fields. (AU)

• Processo FAPESP: 23/03870-8 - Monitoramento de rebanhos usando imagens de drones.
• Beneficiário: Everton Castelão Tetila
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 22/09319-9 - Centro de Ciência para o Desenvolvimento em Agricultura Digital - CCD-AD/SemeAr
• Beneficiário: Silvia Maria Fonseca Silveira Massruhá
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Ciência para o Desenvolvimento