您好,欢迎访问重庆市农业科学院 机构知识库!

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

文献类型: 外文期刊

作者: Guo, Xu 1 ; Wang, Xingmeng 2 ; Zhu, Wenhao 2 ; Yang, Simon X. 3 ; Song, Lepeng 2 ; Li, Ping 4 ; Li, Qinzheng 2 ;

作者机构: 1.Chongqing Chem Ind Vocat Coll, Sch Big Data & Automat, Chongqing 401228, Peoples R China

2.Chongqing Univ Sci & Technol, Sch Elect & Elect Engn, Chongqing 401331, Peoples R China

3.Univ Guelph, Sch Engn, Adv Robot & Intelligent Syst Lab, Guelph, ON N1G 2W1, Canada

4.Chongqing Acad Agr Sci, Chongqing 400039, Peoples R China

关键词: YOLOv8n-DE; dilated reparam feature enhancement; shared parameter head; citrus disease detection; real-time detection

期刊名称:SENSORS ( 影响因子:3.5; 五年影响因子:3.7 )

ISSN:

年卷期: 2025 年 25 卷 7 期

页码:

收录情况: SCI

摘要: 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.

  • 相关文献
作者其他论文 更多>>