Answers are grounded in this paper and cite their sources.
Demonstrates efficient egg counting in Spodoptera frugiperda populations, supporting pest management efforts.
Spodoptera frugiperda is one of the most economically important agricultural pests affecting maize, cotton, and soybean production worldwide. Efficient monitoring of egg masses is essential for population assessment, pest management decision-making, and biological control programs. This study proposes an automated framework for the detection and counting of S. frugiperda egg masses using a deep learning approach based on the YOLOv11 architecture. Six models were trained and evaluated under different configurations to investigate the effects of synthetic data augmentation, image resolution, loss-function weighting, and augmentation intensity on detection and counting performance. Model evaluation was performed using standard object detection metrics, including Precision, Recall, mAP@50, and mAP@50–95, as well as direct comparisons between automated predictions and manually annotated egg-mass counts. The best-performing configuration achieved a Precision of 88.90%, Recall of 92.03%, mAP@50 of 91.18%, and mAP@50–95 of 50.66%. Furthermore, the model produced highly accurate counting estimates, achieving a Mean Absolute Percentage Error (MAPE) of only 4.08% across the test dataset. Comparative analyses demonstrated that the incorporation of biologically realistic synthetic samples significantly improved detection performance, particularly by reducing missed detections and enhancing model generalization. Qualitative assessment revealed that the main source of error occurred in images containing densely clustered egg masses, where object crowding and partial overlap increased detection difficulty. Despite these challenges, the proposed framework consistently generated reliable population estimates and demonstrated strong potential as a tool for automated pest monitoring. The results indicate that combining YOLOv11 with synthetic data augmentation provides an effective and scalable solution for egg-mass detection and counting, supporting the development of intelligent monitoring systems for integrated pest management programs.
No takes yet. Share an insight, caveat, or question.
Roveda et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: