APEST-YOLO:AMULTI-SCALE AGRICULTURAL PEST DETECTION MODEL BASED ON DEEP LEARNING

Crop pests and diseases pose a significant threat to smart agriculture, making pest detection a critical component in agricultural applications. However, current detection methods often struggle to effectively identify multi-scale pest data. In response, we present a novel agricultural pest detection model (APest-YOLO) based on a lightweight approach. The APest-YOLO model enhances pest detection efficiency while reducing model size, which is different from the baseline models. Our model features an original grouping atrous spatial pyramid pooling fast module, comprising four convolution layers with varying rates to capture multi-scale and multi-level pest characteristics. Additionally, we incorporate a convolutional block attention module to extract smoother features from pest images with noisy and complex backgrounds. We evaluated the APest-YOLO model on a large-scale multi-pest dataset encompassing 37 pest species. Furthermore, the APestYOLO model achieved 99.3% mAP0.5 0.5 and found that it outperforms baseline models, demonstrating effective pest species detection capabilities.