[1]梁岩,苏恒强.基于改进YOLO v8s的玉米病害程度检测模型[J].江苏农业科学,2025,53(20):296-307.
 Liang Yan,et al.A maize disease severity detection model based on improved YOLO v8s[J].Jiangsu Agricultural Sciences,2025,53(20):296-307.
点击复制

基于改进YOLO v8s的玉米病害程度检测模型()

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第53卷
期数:
2025年第20期
页码:
296-307
栏目:
病虫害智能检测
出版日期:
2025-10-20

文章信息/Info

Title:
A maize disease severity detection model based on improved YOLO v8s
作者:
梁岩苏恒强
吉林农业大学信息技术学院,吉林长春 130118
Author(s):
Liang Yanet al
关键词:
玉米病害检测YOLO v8深度学习模型轻量化
Keywords:
-
分类号:
S126;TP391.41
DOI:
-
文献标志码:
A
摘要:
针对现有玉米病害程度检测存在准确率低、模型参数量和计算量较大、难以在资源受限的农业设备和移动设备部署等问题,基于YOLO v8s提出了一种玉米病害程度检测模型CFMS-YOLO v8s。首先,在主干网络中,为同时提升模型的全局与局部细节信息提取能力,融合MHSA多头自注意力机制、CGLU卷积门控线性单元和DEconv细节增强卷积提出CSP-PTDB模块,替换第6、8层的C2f模块,为增强模型的多尺度特征与细颗粒度提取能力提出FPSC模块,使用膨胀率不同的共享卷积对多尺度特征进行提取,替换SPPF模块;其次,在特征融合网络中提出了MS-FPN特征融合网络,该网络先使用MLCA注意力机制对特征进行选择再以自顶向下的方式进行特征融合,增强了不同尺度特征的融合程度;最后,在检测头网络中引入ScConv轻量化卷积共享参数降低模型的参数量与计算量。试验结果表明,改进后的CFMS-YOLO v8s模型,在玉米病害程度测试集上的平均精确率为92.9%、召回率为92.9%、F1分数为92.8%,较原模型分别提升了1.3、1.2、1.2百分点,模型的参数量为5.0 M、计算量为14.5 G,较原模型分别降低了52.8%、49.1%。本研究提出的玉米病害程度检测模型不仅提高了检测的精度,而且降低了模型的参数量和计算量,使模型在检测精度与轻量化之间取得了更好的平衡。
Abstract:
-

参考文献/References:

[1]Malik M M,Fayyaz A M,Yasmin M,et al. A novel deep CNN model with entropy coded sine cosine for corn disease classification[J]. Journal of King Saud University(Computer and Information Sciences),2024,36(7):102126.
[2]樊湘鹏,周建平,许燕,等. 基于改进卷积神经网络的复杂背景下玉米病害识别[J]. 农业机械学报,2021,52(3):210-217.
[3]杨佳昊,左昊轩,黄祺成,等. 基于YOLO v5s的作物叶片病害检测模型轻量化方法[J]. 农业机械学报,2023,54(增刊1):222-229.
[4]Rashid R,Aslam W,Aziz R,et al. An early and smart detection of corn plant leaf diseases using IoT and deep learning multi-models[J]. IEEE Access,2024,12:23149-23162.
[5]杜英杰,宗哲英,王祯,等. 农作物病害诊断方法现状和展望[J]. 江苏农业科学,2023,51(6):16-23.
[6]Panigrahi K P,Sahoo A K,Das H. A CNN approach for corn leaves disease detection to support digital agricultural system[C]//2020 4th International Conference on Trends in Electronics and Informatics (ICOEI)(48184).Tirunelveli,India.IEEE,2020:678-683.
[7]Singh R,Sharma N,Gupta R. Classification and detection of corn leaf disease using ResNet 18 transfer learning model[C]//2023 8th International Conference on Communication and Electronics Systems (ICCES).Coimbatore,India.IEEE,2023:1655-1661.
[8]熊梦园,詹炜,桂连友,等. 基于ResNet模型的玉米叶片病害检测与识别[J]. 江苏农业科学,2023,51(8):164-170.
[9]马晓,邢雪,武青海.基于改进ConvNext的复杂背景下玉米叶片病害分类[J]. 江苏农业科学,2023,51(19):190-197.
[10]Chy M S R,Mahin M R H,Islam M F,et al. Classifying corn leaf diseases using ensemble learning with dropout and stochastic depth based convolutional networks[C]//Proceedings of the 2023 8th International Conference on Machine Learning Technologies.Stockholm Sweden.ACM,2023:185-189.
[11]李名博,任东悦,郭俊旺,等. 基于改进YOLOX-S的玉米病害识别[J]. 江苏农业科学,2024,52(3):237-246.
[12]张继成,黄向党. 基于改进YOLO v3的玉米病害识别方法[J]. 中国农机化学报,2024,45(7):269-275.
[13]马春悦,郭秀茹,王琛,等. 一种基于改进ResNet18神经网络的玉米叶片病害识别方法[J]. 山东农业大学学报(自然科学版),2024,55(3):356-366.
[14]陈广泉,侯梁宇,张建超,等. 河西走廊制种玉米锈病田间诊断与病原鉴定[J]. 农业科技通讯,2018(8):167-169.
[15]Chen Z X,He Z W,Lu Z M. DEA-Net:single image dehazing based on detail-enhanced convolution and content-guided attention[J]. IEEE Transactions on Image Processing,2024,33:1002-1015.
[16]Shi D.TransNeXt:robust foveal visual perception for vision transformers[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle,WA,USA.IEEE,2024:17773-17783.
[17]Prewitt J M S. Object enhancement and extraction[J]. Picture processing and Psychopictorics,1970,10(1):15-19.
[18]Wang A,Chen H,Liu L H,et al. YOLO v10:Real-time end-to-end object detection[EB/OL]. (2024-10-30)[2024-11-01]. https://arxiv.org/abs/2405.14458.
[19]陈梓延,王晓龙,何迪,等. 基于改进YOLO v8的轻量化车辆检测网络[J]. 计算机工程,2025,51(5):314-325.
[20]Wan D H,Lu R S,Shen S Y,et al. Mixed local channel attention for object detection[J]. Engineering Applications of Artificial Intelligence,2023,123:106442.
[21]Liu W Z,Lu H,Fu H T,et al. Learning to upsample by learning to sample[C]//2023 IEEE/CVF International Conference on Computer Vision (ICCV).Paris,France.IEEE,2023:6004-6014.
[22]Li J F,Wen Y,He L H. SCConv:spatial and channel reconstruction convolution for feature redundancy[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Vancouver,BC,Canada.IEEE,2023:6153-6162.
[23]Hou Q B,Zhou D Q,Feng J S.Coordinate attention for efficient mobile network design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Nashville,TN,USA.IEEE,2021:13708-13717.
[24]Ouyang D L,He S,Zhang G Z,et al. Efficient multi-scale attention module with cross-spatial learning[C]//ICASSP 2023-2023 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).Rhodes Island,Greece.IEEE,2023:1-5.
[25]Wang Q L,Wu B G,Zhu P F,et al. ECA-Net:efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle,WA,USA.IEEE,2020:11531-11539.
[26]Yang L,Zhang R Y,Li L,et al. Simam:a simple,parameter-free attention module for convolutional neural networks[C]//International Conference on Machine Learning.New York:PMLR,2021:11863-11874.
[27]Rahman M M,Munir M,Marculescu R. EMCAD:efficient multi-scale convolutional attention decoding for medical image segmentation[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle,WA,USA.IEEE,2024:11769-11779.
[28]Ding X H,Zhang X Y,Ma N N,et al. RepVGG:making VGG-style ConvNets great again[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Nashville,TN,USA.IEEE,2021:13733-13742.
[29]Han K,Wang Y H,Tian Q,et al. GhostNet:more features from cheap operations[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle,WA,USA.IEEE,2020:1577-1586.

相似文献/References:

[1]张永江,辛言言,李桂芬,等.实时荧光RT-PCR方法检测马铃薯V病毒[J].江苏农业科学,2013,41(06):36.
 Zhang Yongjiang,et al.Detection of potato virus V by real-time fluorescent RT-PCR[J].Jiangsu Agricultural Sciences,2013,41(20):36.
[2]杨怀君,阎洪山,卢勇涛,等.乌斯特智能在线检测控制系统试验分析[J].江苏农业科学,2014,42(09):287.
 Yang Huaijun,et al.Experimental analysis of Uster intelligent online detection and control system[J].Jiangsu Agricultural Sciences,2014,42(20):287.
[3]郭凤柳,熊蕊,刘晓慧,等.肉制品中驴源性成分PCR方法的建立及应用[J].江苏农业科学,2014,42(08):35.
 Guo Fengliu,et al.Establishment and application of PCR method for donkey derived ingredients in meat productsGuo Fengliu,et al[J].Jiangsu Agricultural Sciences,2014,42(20):35.
[4]冯才伟,冯月君,崔海峰,等.呋喃它酮代谢物化学发光试剂盒的建立[J].江苏农业科学,2013,41(09):277.
 Feng Caiwei,et al.Establishment of chemiluminescence assay kit of furaltadone metabolite[J].Jiangsu Agricultural Sciences,2013,41(20):277.
[5]刘健,张德咏,张松柏,等.湖南和福建辣椒上辣椒脉斑驳病毒的检测及系统发育分析[J].江苏农业科学,2016,44(05):184.
 Lu Jian,et al.Detection and phylogenetic analysis of chilli veinal mottle virus infected pepper in Hunan and Fujian provinces[J].Jiangsu Agricultural Sciences,2016,44(20):184.
[6]宋丰顺,倪大虎,倪金龙,等.杂交水稻种子纯度检测方法综述[J].江苏农业科学,2016,44(06):6.
 Song Fengshun,et al.Study on detection methods of seed purity of hybrid rice:a review[J].Jiangsu Agricultural Sciences,2016,44(20):6.
[7]赵永前,孙华伟,张敬峰,等.某进口原种猪场仔猪猪瘟首免日龄的确定与分析[J].江苏农业科学,2016,44(06):354.
 Zhao Yongqian,et al.Confirmation and analysis of date of initial immunization for piglet with swine fever virus vaccine in an import original breeding farm[J].Jiangsu Agricultural Sciences,2016,44(20):354.
[8]张文志,鲁绯,闫红.酱油中抗草甘膦大豆转基因多种成分的检测:实时荧光定量PCR和传统PCR的比较[J].江苏农业科学,2016,44(06):372.
 Zhang Wenzhi,et al.Detection of Roundup ready transgenic components in soy sauce:comparison of real-time fluorescence quantitative PCR and traditional PCR[J].Jiangsu Agricultural Sciences,2016,44(20):372.
[9]胡乐琴,吴春燕,杨秀文,等.微囊藻毒素ELISA检测方法的建立与评估[J].江苏农业科学,2015,43(09):340.
 Hu Leqin,et al.Establishment and evaluation of ELISA detection method of microcystic toxins[J].Jiangsu Agricultural Sciences,2015,43(20):340.
[10]钱正.农业质检机构的检测质量控制和开展新项目的方法确认[J].江苏农业科学,2015,43(06):271.
 Qian Zheng.Quality control of agricultural quality inspection institutions and methods for creating new projects[J].Jiangsu Agricultural Sciences,2015,43(20):271.

备注/Memo

备注/Memo:
收稿日期:2024-11-04
基金项目:国家自然科学基金(编号:U19A2061);吉林省发改委项目(编号:2021C044-8)。
作者简介:梁岩(1991—),男,黑龙江北安人,硕士,主要从事机器视觉、智慧农业研究。E-mail:20221127@mails.jlau.edu.cn。
通信作者:苏恒强,硕士,副教授,主要从事机器视觉、农业信息化研究。E-mail:suhengqiang@jlau.edu.cn。
更新日期/Last Update: 2025-10-20