Field-Oriented Rice Pest Detection: Dataset Construction and Performance Analysis

Rice is one of the world’s most important staple crops, and outbreaks of insect pests pose a persistent threat to yield stability and food security in major rice-growing regions. Reliable field-scale rice pest detection remains challenging due to limited datasets, heterogeneous imaging conditions, and inconsistent annotations. To address these limitations, we construct RicePest-30, a field-oriented dataset comprising 8848 images and 62,227 annotated instances covering 30 major rice pest species. Images were collected using standardized square-framing protocols to preserve spatial context and visual consistency under diverse illumination and background conditions. Based on RicePest-30, YOLOv11 was adopted as the primary detection framework and optimized through a systematic hyperparameter tuning process. The learning rate was selected via grid search within the range of 0.001–0.01, yielding an optimal value of 0.002. Training was conducted for up to 300 epochs with an early-stopping strategy to prevent overfitting. For fair comparison, YOLOv5s, YOLOv8s, Faster R-CNN, and RetinaNet were trained for the same number of epochs under unified settings, using the Adam optimizer with a learning rate of 0.001. Model performance was evaluated using Precision, Recall, AP@50, mAP@50:95, and counting error metrics. The experimental results indicate that YOLOv11 provides the most balanced performance across precision, localization accuracy, and counting stability. However, all models exhibit degraded performance in small-object scenarios, dense pest distributions, and visually similar categories. Error analyses further reveal that class imbalance and field-scene variability are the primary factors limiting detection robustness. Overall, this study contributes a high-quality, uniformly annotated rice pest dataset and a systematic benchmark of mainstream detection models under realistic field conditions. The findings highlight critical challenges in fine-grained pest recognition and provide a solid foundation for future research on small-object enhancement, adaptive data augmentation, and robust deployment of intelligent pest monitoring systems.