|本期目录/Table of Contents|

[1]董雁凯,王玉超,李博梾,等.基于改进YOLO v5的黄瓜霜霉病分级方法[J].江苏农业科学,2023,51(22):213-220.
 Dong Yankai,et al.A cucumber downy mildew grading method based on improved YOLO v5[J].Jiangsu Agricultural Sciences,2023,51(22):213-220.
点击复制

基于改进YOLO v5的黄瓜霜霉病分级方法(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第51卷
期数:
2023年第22期
页码:
213-220
栏目:
农业工程与信息技术
出版日期:
2023-12-04

文章信息/Info

Title:
A cucumber downy mildew grading method based on improved YOLO v5
作者:
董雁凯12王玉超12李博梾12秦立峰13姚晓勉12周子奥12
1.西北农林科技大学机械与电子工程学院,陕西杨凌 712100; 2.农业农村部农业物联网重点实验室,陕西杨凌 712100;3.陕西省农业信息感知与智能服务重点实验室,陕西杨凌 712100
Author(s):
Dong Yankaiet al
关键词:
黄瓜霜霉病深度学习叶面积病害分级
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
针对温室黄瓜霜霉病病害程度检测分级困难的情况,提出一种基于改进YOLO v5的黄瓜霜霉病病害程度检测分级的方法。通过YOLO v5网络训练模型输出病害叶片最小外接矩形,利用矩形的长、宽建立适用的叶片面积测量方法;将原YOLO v5中Leaky ReLU激活函数改进为meta-ACON激活函数,并添加改进的ECANet注意力机制获取黄瓜霜霉病病斑面积。结果显示,改进后黄瓜叶片面积估算方法的模拟值与真实值拟合曲线的决定系数(r2)为9956%,均方根误差(RMSE)为0.10,在不同条件下黄瓜叶片面积最大估算误差为4.84%,最小值为0.34%,平均值为2.87%。改进后的YOLO v5模型检测准确率达到81.71%,较原始YOLO v5模型提高了2.73百分点;改进后的YOLO v5模型召回率为78.83%,较原始YOLO v5模型提高了0.99百分点;改进后的YOLO v5模型mAP为79.96%,较原始YOLO v5模型提高了1.24百分点。改进后的黄瓜霜霉病病害分级方法在1、3级的分级准确度分别为8043%、5294%;在5、7级的分级准确度分别为62.35%、88.37%;在9级的分级准确率为93.33%;平均分级准确率达到7538%,较改进前的模型分级准确率提高了18.07百分点。研究结果可为温室黄瓜霜霉病叶片面积与病害分级提供一种简便、准确的方法,从而为防治黄瓜霜霉病提供参考。
Abstract:
-

参考文献/References:

[1]徐世成,王鹤冰,冯俊杰,等. 黄瓜霜霉病及寄主抗性机制研究进展[J]. 生物工程学报,2022,38(5):1724-1737.
[2]徐静,苗腾,周云成,等. 基于高光谱成像技术的玉米弯孢叶斑病的早期检测[J]. 沈阳农业大学学报,2020,51(2):225-230.
[3]孙文斌,王荣,高荣华,等. 基于可见光谱和改进注意力的农作物病害识别[J]. 光谱学与光谱分析,2022,42(5):1572-1580.
[4]Lu J Z,Ehsani R,Shi Y Y,et al. Detection of multi-tomato leaf diseases (late blight,target and bacterial spots) in different stages by using a spectral-based sensor[J]. Scientific Reports,2018,8(1):2793.
[5]芦兵,孙俊,杨宁,等. 基于荧光透射谱和高光谱图像纹理的茶叶病害预测研究[J]. 光谱学与光谱分析,2019,39(8):2515-2521.
[6]张德荣,方慧,何勇. 可见/近红外光谱图像在作物病害检测中的应用[J]. 光谱学与光谱分析,2019,39(6):1748-1756.
[7]康丽,袁建清,高睿,等. 高光谱成像的水稻稻瘟病早期分级检测[J]. 光谱学与光谱分析,2021,41(3):898-902.
[8]张昭,王鹏,姚志凤,等. 基于多光谱荧光成像技术和SVM的葡萄霜霉病早期检测研究[J]. 光谱学与光谱分析,2021,41(3):828-834.
[9]曹银轩,黄卓,徐喜娟,等. 黄土高原植被日光诱导叶绿素荧光对气象干旱的响应[J]. 应用生态学报,2022,33(2):457-466.
[10]赵叶,竞霞,黄文江,等. 日光诱导叶绿素荧光与反射率光谱数据监测小麦条锈病严重度的对比分析[J]. 光谱学与光谱分析,2019,39(9):2739-2745.
[11]任守纲,陆海飞,袁培森,等. 基于显著性检测的黄瓜叶部病害图像分割算法[J]. 农业机械学报,2016,47(9):11-16.
[12]何自芬,黄俊璇,刘强,等. 基于非对称混洗卷积神经网络的苹果叶部病害分割[J]. 农业机械学报,2021,52(8):221-230.
[13]Narmadha R P,Sengottaiyan N,Kavitha R J. Deep transfer learning based rice plant disease detection model[J]. Intelligent Automation & Soft Computing,2022,31(2):1257-1271.
[14]Fuentes A,Yoon S,Kim T,et al. Open set self and across domain adaptation for tomato disease recognition with deep learning techniques[J]. Frontiers in Plant Science,2021,12:758027.
[15]Rashid J,Khan I,Ali G,et al. Multi-level deep learning model for potato leaf disease recognition[J]. Electronics,2021,10(17):2064.
[16]Elaraby A,Hamdy W,Alruwaili M. Optimization of deep learning model for plant disease detection using particle swarm optimizer[J]. Computers,Materials & Continua,2022,71(2):4019-4031.
[17]李萍,邵彧,齐国红,等. 基于跨深度学习模型的作物病害检测方法[J]. 江苏农业科学,2022,50(8):193-199.
[18]Qi J T,Liu X N,Liu K,et al. An improved YOLO v5 model based on visual attention mechanism:application to recognition of tomato virus disease[J]. Computers and Electronics in Agriculture,2022,194:106780.
[19]任守纲,贾馥玮,顾兴健,等. 反卷积引导的番茄叶部病害识别及病斑分割模型[J]. 农业工程学报,2020,36(12):186-195.
[20]李翠玲,李余康,谭昊然,等. 基于K-means聚类和RF算法的葡萄霜霉病检测分级方法[J]. 农业机械学报,2022,53(5):225-236,324.
[21]党满意,孟庆魁,谷芳,等. 基于机器视觉的马铃薯晚疫病快速识别[J]. 农业工程学报,2020,36(2):193-200.
[22]丁维龙,谢涛,徐利锋,等. 基于虚拟模型的水稻冠层叶面积计算方法[J]. 农业工程学报,2017,33(2):192-198.
[23]陈柱,杨君. 基于三维点云的植物叶片重建及其面积估算[J]. 传感技术学报,2022,35(3):349-354.
[24]张萌,张德安,鲁晓燕,等. 枣树叶面积估算模型构建[J]. 果树学报,2020,37(12):1964-1973.
[25]吴新辉,毛政元,翁谦,等. 利用基于残差多注意力和ACON激活函数的神经网络提取建筑物[J]. 地球信息科学学报,2022,24(4):792-801.
[26]Ma N N,Zhang X Y,Liu M,et al,Activate or not:learning customized activation[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition,2021:8028-8038.
[27]Xue H,Sun M H,Liang Y H. ECANet:explicit cyclic attention-based network for video saliency prediction[J]. Neurocomputing,2022,468:233-244.
[28]赵璐璐,王学营,张翼,等. 基于YOLO v5s融合SENet的车辆目标检测技术研究[J]. 图学学报,2022,43(5):776-782.
[29]Zhao X,Li K Y,Li Y X,et al. Identification method of vegetable diseases based on transfer learning and attention mechanism[J]. Computers and Electronics in Agriculture,2022,193:106703.
[30]张红斌,熊其鹏,蒋子良,等. 联合SENet异构层特征融合与集成学习的材质图像识别[J]. 控制与决策,2022,37(6):1632-1642.
[31]Xu B,Wang N Y,Chen T Q,et al. Empirical evaluation of rectified activations in convolutional network[J]. arXiv preprint arXiv:1505.00853,2015.
[32]苏宝峰,沈磊,陈山,等. 基于注意力机制的葡萄品种多特征分类方法[J]. 农业机械学报,2021,52(11):226-233,252.

相似文献/References:

[1]武玲,陆雅萍,丁泽华,等.草菇菌糠还田对大棚土壤肥力和黄瓜产量的影响[J].江苏农业科学,2013,41(05):372.
 Wu Ling,et al.Effects of mushroom substrate return to fields on soil fertility and cucumber yield in greenhouses[J].Jiangsu Agricultural Sciences,2013,41(22):372.
[2]徐强,耿友玲,齐晓花,等.不同栽培环境下黄瓜果实单宁含量主基因-多基因遗传分析[J].江苏农业科学,2014,42(12):194.
 Xu Qiang,et al.Genetic analysis of tannin content in cucumber by mixed model of major gene and polygene under different cultural environments[J].Jiangsu Agricultural Sciences,2014,42(22):194.
[3]董晓娅,邱白晶,管贤平.电化学分析方法检测黄瓜中残留的西维因[J].江苏农业科学,2014,42(11):337.
 Dong Xiaoya,et al(7).Detection of carbaryl residues in cucumber by electrochemical method[J].Jiangsu Agricultural Sciences,2014,42(22):337.
[4]王素平,孙艳军.H2O2预处理对低温下黄瓜幼苗抗氧化酶同工酶的影响[J].江苏农业科学,2013,41(06):123.
 Wang Suping,et al.Effect of H2O2 pretreatment on antioxidant isoenzyme in cucumber seedlings under chilling stress[J].Jiangsu Agricultural Sciences,2013,41(22):123.
[5]付瑞敏,韩鸿鹏,张丽琴,等.葡萄霜霉病和白粉病拮抗菌的分离、鉴定和He-Ne 激光诱变[J].江苏农业科学,2013,41(08):122.
 Fu Ruimin,et al.Isolation and identification of antagonistic bacteria against grape downy mildew and powdery mildew,and its mutation under He-Ne laser irradiation[J].Jiangsu Agricultural Sciences,2013,41(22):122.
[6]田福发,陈立昶,姜若勇,等.内置式秸秆反应堆对日光温室番茄和黄瓜生长的影响[J].江苏农业科学,2013,41(09):143.
 Tian Fufa,et al.Effect of built-in straw bio-reactor on growth of tomato and cucumber in greenhouse[J].Jiangsu Agricultural Sciences,2013,41(22):143.
[7]霍艳林,鲁顺保,关正君.盐胁迫对晋南部分主栽黄瓜品种种子萌发特性的影响[J].江苏农业科学,2016,44(03):165.
 Huo Yanlin,et al.Effect of salt stress on seed germination characteristics of cucumber cultivars in southern Shanxi[J].Jiangsu Agricultural Sciences,2016,44(22):165.
[8]王素平.钙和水杨酸对低温下黄瓜幼苗抗氧化酶同工酶的影响[J].江苏农业科学,2016,44(03):168.
 Wang Suping.Effects of Ca2+ and SA pretreatment on antioxidase isoforms in cucumber seedlings under chilling stress[J].Jiangsu Agricultural Sciences,2016,44(22):168.
[9]高攀,郭世荣,阳燕娟,等.Ca(NO3)2胁迫对白籽南瓜嫁接黄瓜幼苗生长及膜透性的影响[J].江苏农业科学,2013,41(11):157.
 Gao Pan,et al.Effects of Ca(NO3)2 stress on growth and cell membrane permeability of white seed pumpkin grafted cucumber seedlings[J].Jiangsu Agricultural Sciences,2013,41(22):157.
[10]王红君,张梦,赵辉,等.基于BP神经网络的温室黄瓜灌溉预测模型[J].江苏农业科学,2013,41(11):407.
 Wang Hongjun,et al.Irrigation forecast model of cucumber in greenhouse based on BP neural networks[J].Jiangsu Agricultural Sciences,2013,41(22):407.

备注/Memo

备注/Memo:
收稿日期:2023-02-06
基金项目:陕西省农业科技创新与攻关项目(编号:2020NY-101);国家重点研发计划子课题(编号:2020YFD1100602)。
作者简介:董雁凯(2001—),男,陕西富平人,主要从事农业信息化工程领域研究。E-mail:770938859@qq.com。
通信作者:秦立峰,博士,副教授,主要从事农业信息化技术领域的研究。E-mail:fuser@nwsuaf.edu.cn。
更新日期/Last Update: 2023-11-20