Citrus Disease Detection Based on Dilated Reparam Feature Enhancement and Shared Parameter Head.

Abstract

Accurate citrus disease identification is essential for targeted orchard pesticide application. Current models struggle with accuracy and efficiency due to diverse leaf lesion patterns and complex orchard environments. This study presents YOLOv8n-DE, an improved lightweight YOLOv8-based model for enhanced citrus disease detection. It introduces the DR module structure for effective feature enhancement and the Detect_Shared architecture for parameter efficiency. Evaluated on public and orchard-collected datasets, YOLOv8n-DE achieves 97.6% classification accuracy, 91.8% recall, and 97.3% mAP, with a 90.4% mAP for challenging diseases. Compared to the original YOLOv8, it reduces parameters by 48.17%, computational load by 59.26%, and model size by 41.94%, while significantly decreasing classification and regression errors, and false positives/negatives. YOLOv8n-DE offers outstanding performance and lightweight advantages for citrus disease detection, supporting precision agriculture development in orchards.

Code and data availability

The supplied blocks describe a YOLOv8n-DE citrus disease detection model trained on a mix of field-collected images and four public datasets (PlantVillage, CCL'20, Citrus Plant Dataset, AI Challenger), but no block contains author code availability, a public deposit of the annotated 6050-image dataset, trained model/ck

No evidence-backed public reproduction asset is currently recorded.