基于改进YOLOv8n算法的水稻叶病害检测研究

打开文本图片集

中图分类号：S126：S511 文献标识号：A 文章编号：1001-4942（2025）09-0164-09

Research on Rice LeafDisease Detection Based on Improved YOLOv8n Algorithm

Liu Zhengfeng'，Yang Jiansheng¹， Zhang Mei' ，Chen Zhe²， Zhang Qunying 2 （1.Electrical Engineering College，Guizhou University，Guiyang 55Oo25，China ; 2. Guizhou Botanical Garden， Guiyang 550oo1， China）

AbstractRice leaf disease detection is one of the important ways to reduce disease risk and stabilize rice yield.In response to the problems of large parameter size，high computational complexity，and low accuracy in existing rice leaf disease detection models，this study proposed an improved YOLOv8n model. First，the backbone network of the original YOLOv8n was replaced with a lightweight HGNetv2 architecture，and the Conv module in the HG-Block was replaced with a Ghost module，improving detection accuracy while reducing model size.Next，the residual blocks in the C3 module were replaced with Ghost Botleneck to creating a new C3Ghost module，which was used to replace all C2f modules in the neck，further reducing model size while maintaining model performance.Finally，a dense prediction channel knowledge distilation technique was employed to enhance the model in a lossess manner.Experimental results indicated that compared with the baseline model ΥOLOv8n ，the proposed improved model reduced the parameter size，weights，and floating-point operations by 39.33% ， 37.00% ，and 28.40% ，respectively，while achieved precision and recall of 94.3% and （204号 95.6% ，and mAP of 96.7% ， significantly outperforming the baseline model. Overall， the proposed improved model could meet the demands for accuracy and lightweight design in rice leaf disease detection tasks in agricultural scenarios， demonstrating good development potential and application prospects.

KeywordsRice leaf disease detection; ΥOLOv8n ; Model lightweighting;HGNetv2; Knowledge distillation

水稻作为全球主要的粮食作物之一，产量水平直接关系到多数人口的温饱问题[1-2]，因此，及时监测预报和防治病害对维护粮食安全至关重要。（剩余9317字）