Análise de desempenho da YOLOv3 para detecção em tempo real de insetos-praga na soja

Abstract

In this work, we evaluated the You Only Look Once (YOLOv3) architecture for real-time detection of pests in soybeans. Plantation images were collected on different days, locations and climatic conditions, between the phenological stages R1 to R6, considered to have a high occurrence of pests in soybeans. For the training and testing of the neural network, we used a 5-fold cross-validation considering 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 compared to batch sizes 4 and 16. The results indicate that the evaluated architecture can support specialists and farmers in monitoring the levels of pest control action in soybean fields.