华南农业大学学报2026，Vol.47Issue(4)：616-626,11.DOI:10.7671/j.issn.1001-411X.202511013
基于改进YOLOv8的叶面荧光雾滴沉积检测方法研究
A detection method for foliar fluorescent droplet deposition based on improved YOLOv8
摘要
Abstract
[Objective]To guide the rational application of pesticides,this study aims to develop a simple and reliable detection method to acquire real-time information on the deposition and distribution of pesticide droplet on crop leaves.[Method]This study proposed a method for detecting foliar fluorescent droplet deposition based on an improved YOLOv8.By screening fluorescent tracers and optimizing their mass concentrations,suitable experimental conditions for leaf droplet image acquisition were determined,and a corresponding dataset was constructed.Based on YOLOv8-seg,the AdamW optimizer was introduced,an efficient multi-scale attention(EMA)mechanism was embedded into the backbone network,and a semantics and detail infusion(SDI)module was incorporated into the neck structure to enhance detection performance.[Result]The fluorescence tracer screening results showed that the fluorescein(a yellow-green fluorescent tracer)solution with 1.0 g/L clearly revealed the spatial distribution of droplets on leaf surfaces.Field experiment results demonstrated that the improved model achieved mAP@0.50 and mAP@0.50-0.95 values of 95.4％and 73.1％respectively,in object detection tasks.For segmentation mask evaluation,the mAP@0.50 and mAP@0.50-0.95 reached 92.5％and 61.3％respectively,outperforming the baseline model in overall performance.[Conclusion]The improved YOLOv8-based method for fluorescent droplet deposition detection on leaf surface enables accurate droplet recognition and distribution analysis.It features simple operation and high stability,offering technical support for spray quality assessment and precision pesticide application.关键词
荧光雾滴图像/雾滴沉积检测/实例分割/YOLOv8Key words
Droplet fluorescence image/Droplet deposition detection/Instance segmentation/YOLOv8分类
农业科技引用本文复制引用
薛秀云,黄诚乐,朱佳妮,孙道宗,吕石磊,李震..基于改进YOLOv8的叶面荧光雾滴沉积检测方法研究[J].华南农业大学学报,2026,47(4):616-626,11.基金项目
国家自然科学基金(32271997) （32271997）
国家现代农业产业技术体系(CARS-26) （CARS-26）
广东省重点领域研发计划(2023B0202090001) （2023B0202090001）
广州市科技计划(2024B03J1309) （2024B03J1309）
广东省现代农业产业技术体系创新团队建设项目(2024CXTD10) （2024CXTD10）
广东省科技创新战略专项资金"大学生科技创新培育"(pdjh2024b076) （pdjh2024b076）
