基于改进YOLOv8模型的黄花菜花蕾识别研究

打开文本图片集

静琦，，.基于改进YOLOv8模型的黄花菜花蕾识别研究［J].湖北农业科学，2025，64（7）：186-191.

关键词：改进YOLOv8模型;深度学习；黄花菜（HemerocalliscitrinaBaroni）;花蕾；识别

中图分类号：TP391 文献标识码：A

文章编号：0439-8114（2025）07-0186-06

DOI：10.14088/j.cnki.issn0439-8114.2025.07.032 开放科学（资源服务）标识码（OSID）：I

Research on daylily buds recognition based on an improved YOLOv8 model

HUOJing-qi，CUI Ting-ting，XUE Zhi-lu （School of Mechatronic Engineering，Xi'an Vocational and Technical College，Xi'an 71Oooo，China）

Abstract：A CSPDenseNetbackbone module wasconstructedbydeply integratingCSPNetand DenseNet.This module wasintegrated intotheYOLOv8model，replacingthelasttwostandardconvolutioalmodulesattheendoftebackbonenetwork，resultinginteimproved YOLOv8model（Dense-YOLOv8）.Theresults demonstrated thattheDense-YOLOv8modelsuccesfullyidentifiedall maturebudsunderscenarioswithasimplebackgroundandsparsedaylily（Hemerocaliscitrina）Baronibuds.Underscenarioswith asimple backgroudanddensedaylilybuds，theDense-YOLOv8 modelexhibitedexcellentrecognitionperformanceinthebuddetectiontask，altoughsosedetectiosstilouednprocessingtightlyacenttargetsUnderscenariosiholebackground and dense daylily buds，the Dense-YOLOv8 model successfully identified all mature buds.The mAP ， FI ，recognition speed， and model size of the Dense-YOLOv8 model were 90.75% ，89 % ， 53f/s ，and 217.68 MB，respectively. Compared with the YOLO Δv8 2 model，FasterR-CNNmodelandYOLOv7model，theDense-YOLOv8 modelsignificantly improvedboththeaccuracyandspeedof object detection while streamlining the network structure and reducing parameters.

Key Words： improved YOLOv8 model;deep learning；daylily（Hemerocalis citrina Baroni）；bud;recognition

黄花菜（HemerocalliscitrinaBaroni）作为经济作物，对种植环境要求较低，但对采摘条件要求严苛，成熟可食用的黄花菜通常呈淡黄色，花蕾端口处微微开裂时为最佳采摘时机。（剩余9075字）