Performance Analysis of YOLOv3 for Real-Time Detection of Pests in Soybeans

  • Fábio Amaral Godoy da Silveira UFGD
  • Everton Castelão Tetila UFGD
  • Gilberto Astolfi IFMS / UFMS
  • Anderson Bessa da Costa UFGD
  • Willian Paraguassu Amorim UFGD


In this work, we evaluate the You Only Look Once (YOLOv3) architecture for real-time detection of insect pests in soybean. Soybean crop images were collected on different days, locations, and weather conditions between the phenological stages R1 to R6, considered the period of the high occurrence of soybean pests. For training and testing the neural network, we used 5-fold cross-validation analyzing four metrics to evaluate the classification results: precision, recall, F-score, and accuracy; and three metrics to evaluate the detection results: mean absolute error (MAE), root mean square error (RMSE) and coefficient of determination (R2). The experimental results showed that the YOLOv3 architecture trained with batch size 32 leads to higher classification and detection rates than batch sizes 4 and 16. The results indicate that the evaluated architecture can support experts and farmers in monitoring pest control action levels in soybean fields.

Palavras-chave: Deep learning, Object detection, Precision agriculture, Pests in soybeans
Como Citar

Selecione um Formato
SILVEIRA, Fábio Amaral Godoy da; TETILA, Everton Castelão; ASTOLFI, Gilberto; COSTA, Anderson Bessa da; AMORIM, Willian Paraguassu. Performance Analysis of YOLOv3 for Real-Time Detection of Pests in Soybeans. In: BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS), 10. , 2021, Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 . ISSN 2643-6264.