基于YOLOv8n的梨树叶片病害检测模型  

Detection model of pear leaf disease based on YOLOv8n

作　　者：黄政 张涛 孔万仔 赵丹枫[1] 魏泉苗 HUANG Zheng;ZHANG Tao;KONG Wanzai;ZHAO Danfeng;WEI Quanmiao(College of Information Technology,Shanghai Ocean University,Shanghai 201306,China;East China Sea Bureau,Ministry of Natural Resources,Shanghai 200137,China)

机构地区：[1]上海海洋大学信息学院,上海201306 [2]自然资源部东海局,上海200137

出　　处：《湖南农业大学学报(自然科学版)》2025年第2期113-121,共9页Journal of Hunan Agricultural University(Natural Sciences)

基　　金：国家自然科学基金青年项目(42106190)。

摘　　要：针对传统目标检测模型对自然场景下梨树叶片病害检测存在精度低、模型参数量大等问题,提出一种基于YOLOv8n的梨树叶片病害检测改进模型。首先,使用RepGhostNet改进主干网络,利用结构重参数化实现特征的隐式重用,在提升网络特征提取能力的同时使网络更加轻量化。其次,引入双层路由注意力机制,通过查询自适应的方式降低模型对不相关特征的关注,提高模型对关键信息的敏感性,增强网络的表征能力和特征融合能力。最后,使用Inner-SIoU损失函数优化边界框回归,加快模型收敛速度,提高识别精度。结果表明:改进后的模型能够有效对梨树叶片病害进行检测,在DiaMOSPlant数据集上对梨树叶片病害的检测平均精准度m AP@50达到0.901,相较于原模型提高了5.6%;而模型参数量仅为2.4×10^(6)个,计算量仅为7GFLOPs,相较于原模型分别降低了20.00%和13.58%。与SSD、Faster-RCNN、YOLOv5n、YOLOv8s等主流目标检测模型相比,改进的模型不仅平均精准度有所提高,而且参数量和计算量均减少。In response to the challenges of low accuracy and large model parameters number in traditional object detection models for detecting pear leaf diseases in natural scenes,an improved model for pear leaf disease detection based on YOLOv8n was proposed.Firstly,the RepGhostNet was employed to enhance the backbone network,which utilized structural reparameterization to achieve implicit feature reuse,thereby enhancing the network's feature extraction capabilities while maintaining lightweight characteristics.Secondly,the bi-level routing attention mechanism was utilized to dynamically filter out less relevant key-value pairs at a coarse region level,thereby lowering attention to irrelevant features and increasing sensitivity to essential information,and enhancing the network's representational and feature fusion capabilities.Finally,the Inner-SIoU loss function was employed to optimize bounding box regression,accelerate model convergence and improve recognition accuracy.The results showed that the improved model effectively detected pear leaf diseases,achieving an mAP@50 score of 0.901 on the DiaMOS Plant dataset.Compared to the original model,the improved model exhibited a notable 5.6%enhancement in performance,with reduced model parameter quantity(2.4×10^(6))and computations(7 GFLOPs),representing a 20.00%and 13.58%decrease,respectively.When compared to mainstream object detection models such as SSD,Faster-R CNN,YOLOv5n,and YOLOv8s,the enhanced model showed an increase in average precision,accompanied by reductions in both parameter and computation loads.

关 键 词：梨树叶片病害检测 YOLOv8n 模型轻量化 RepGhostNet 双层路由注意力机制 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] S432.9[自动化与计算机技术—计算机科学与技术]