Objective To address issues including data scarcity, low accuracy, and poor real-time performance in rice pest detection, this study constructed a specialized dataset and proposed an efficient detection method.

Method The Pest5 dataset was built based on insect-attracting light traps. Within the ATSS framework, the improved model, PestDet, was proposed. Improvements included: A combined data augmentation strategy and anchor optimization were adopted to enhance sample diversity and target matching capability; GHM-C and DIoU were used as the classification and regression losses, respectively, to improve robustness and localization accuracy; Inflated convolutions was introduced to reconstruct the feature pyramid for enhanced multi-scale feature perception; The detection head architecture was simplified and the Coordinate Attention (CA) mechanism was embedded to accelerate inference and strengthen key information extraction.

Result PestDet achieved an mAP of 92.0% and FPS of 40.2 on the Pest5 dataset, surpassing the original ATSS by 7.0 percentage points and 8.0 respectively, and outperformed other mainstream models.

Conclusion PestDet demonstrates high accuracy with high efficiency, enabling effective identification of rice pests in complex backgrounds, and provides technical support for intelligent pest monitoring and precision control.