YOLO performance analysis for real-time detection of soybean pests

Author(s)

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

• Document type: Journal article
• Source: SMART AGRICULTURAL TECHNOLOGY; v. 7, p. 10-pg., 2024-02-05.

Abstract

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)

• FAPESP's process: 23/03870-8 - Cattle monitoring using drone images.
• Grantee: Everton Castelão Tetila
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• FAPESP's process: 22/09319-9 - Center of Science for Development in Digital Agriculture - CCD-AD/SemeAr
• Grantee: Silvia Maria Fonseca Silveira Massruhá
• Support Opportunities: Research Grants - Science Centers for Development