基于改进YOLOv8模型的玉米叶斑病快速识别方法

打开文本图片集

关键词：玉米；叶斑病；改进；YOLOv8模型；快速识别

中图分类号：S126；TP391.41 文献标识码：A

文章编号：0439-8114（2025）05-0160-07

DOI：10.14088/j.cnki.issn0439-8114.2025.05.025 开放科学（资源服务）标识码（OSID）：□

A rapid identification method for maize leaf spot disease based on the improved YOLOv8 model

ZHANGLu，WUXue-lian （Economics and Management School，Yangtze University，Jingzhou ，Hubei，China）

Abstract：Toachieverapididentificationofmaizeleafspotdisease，thedetectionperformanceoftheimprovedYOLOv8modelwasoptimizedbyintegratingtheGlobalAtentionModule（GAM），Slim-Necklightweightmodule，andInner-CIoUlossfunction.Compared with the original YOLOv8 model，the improved YOLOv8 model（GAM + Slim-Neck+Inner-CIoU）showed increases of 4.15% in Precision， 5.51% in Recall， 3.91% in mAP @ 0.5，and 11.35% in mAP @[0.5： 0.95]，while the number of parameters and detection time decreased by10.39% and 3.42% ，respectively. The improved YOLOv8 model outperformed other models（YOLOv3，YOLO v5 ，YOLO v6 ，and Faster R-CNN） in Precision，Recall，mAP @ 0.5，and mAP ，while also demonstrating significant advantagesinparameterquantitynddetectiontime，combining higheficiencywithlightweightcharacteristics.TheimprovedYOLOv8model eficientlycaurediticaliforation，fullyitegatedultdimesioalatures，ndratioallloatedomputatioalrouces，thereby enhancing recognition accuracy.

Key words：maize;leaf spot disease;improvement；YOLOv8 model; rapid identification

随着农业生产规模的扩大和气候变化的影响，玉米叶斑病已成为全球玉米生产中的主要病害。（剩余9061字）