|本期目录/Table of Contents|

[1]杨骞云,沈艳.基于改进YOLO v8s模型的玉米病虫害图像识别[J].江苏农业科学,2025,53(5):231-243.
 Yang Qianyun,et al.Recognition of maize pests and diseases images based on improved YOLO v8s model[J].Jiangsu Agricultural Sciences,2025,53(5):231-243.
点击复制

基于改进YOLO v8s模型的玉米病虫害图像识别(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第53卷
期数:
2025年第5期
页码:
231-243
栏目:
病虫害智能检测
出版日期:
2025-03-05

文章信息/Info

Title:
Recognition of maize pests and diseases images based on improved YOLO v8s model
作者:
杨骞云沈艳
成都信息工程大学计算机学院,四川成都 610200
Author(s):
Yang Qianyunet al
关键词:
玉米病虫害识别目标检测YOLO v8模型
Keywords:
-
分类号:
S126;TP391.41
DOI:
-
文献标志码:
A
摘要:
针对目标检测模型YOLO v8s在光照变化大和背景杂乱情况下,对玉米病虫害进行识别过程中存在检测漏检率高以及鲁棒性较差的问题,提出了一种基于改进YOLO v8s的玉米病虫害识别模型——DSCGAM-YOLO v8s。DSCGAM-YOLO v8s模型基于YOLO v8s模型,首先将GAM全局注意力机制加入C2f模块中的Bottleneck之前,构建全新设计的C2f-ATTENTION模块,在充分获取上下文信息的基础上降低复杂背景对病虫害图像识别的干扰;接着在Neck部分网络结构设计并添加DySnakeConv模块,DySnakeConv模块具有自适应调整卷积核的形状特性,更好地捕捉和感知图像中玉米病虫害的目标特征,避免光照和背景杂乱的影响;最后改进了Neck颈部网络结构,建立了160×160尺度的特征融合层以提升检验框对小目标检测的准确性,增强了浅层信息和深层信息的融合同时提高了识别精度,在Head网络中增加微小目标检测模块与160×160尺度的特征融合层进行连接。在使用自建的包含常见7种玉米病虫害数据集进行测试的情况下,DSCGAM-YOLO v8s模型的检测精确度、召回率分别达到了812%和71.3%,与YOLO v8s模型相比分别提高了9.9、8.9百分点。对比YOLO v3模型、YOLO v5s模型、YOLO v8s模型mAP分别提升了15.7、11.4、11.1百分点,对比其他研究中提出的玉米病虫害识别模型YOLO v3-Corn、Improved-YOLO v5s、YOLO v8-Extend模型mAP提升了12.8、8.4、6.8百分点。在保证提取相同特征参数,识别计算量提升不大的前提下,DSCGAM-YOLO v8s模型有效提高了识别精度。
Abstract:
-

参考文献/References:

[1] 代瑞熙,徐伟平. 中国玉米增产潜力预测[J]. 农业展望,2022,18(3):41-49.
[2]Spyrantis A,Woebbecke T,Rue D,et al. Accuracy of robotic and frame-based stereotactic neurosurgery in a phantom model[J]. Frontiers in Neurorobotics,2022,16:762317.
[3]何全令,杨静文,梁晋欣,等. 面向嵌入式除草机器人的玉米田间杂草识别方法[J]. 计算机工程与应用,2024,60(2):304-313.
[4]汪凤珠,赵博,刘阳春,等. 玉米青贮收获机多参数检测系统设计与试验[J]. 农业机械学报,2023,54(1):127-136.
[5]孟庆宽,何洁,仇瑞承,等. 基于机器视觉的自然环境下作物行识别与导航线提取[J]. 光学学报,2014,34(7):715002.
[6]Li M T,Lee S H. A study on small pest detection based on a CascadeR-CNN-swin model[J]. Computers,Materials & Continua,2022,72(3):6155-6165.
[7]徐会杰,黄仪龙,刘曼. 基于改进YOLO v3模型的玉米叶片病虫害检测与识别研究[J]. 南京农业大学学报,2022,45(6):1276-1285.
[8]凌慕菲,杨冬风. 基于改进YOLO v5s模型的玉米叶片病害识别[J]. 农业灾害研究,2023,13(8):126-128.
[9]张荣华,白雪,樊江川. 复杂场景下害虫目标检测算法:YOLO v8-Extend[J]. 智慧农业(中英文),2024,6(2):49-61.
[10] Wang C Y,Bochkovskiy A,Liao H M. YOLO v7:trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver,BC,Canada.IEEE,2023:7464-7475.
[11]Zhou Y J,Zhu W G,He Y H,et al. YOLO v8-based spatial target part recognition[C]//2023 IEEE 3rd International Conference on Information Technology,Big Data and Artificial Intelligence (ICIBA). Chongqing,China.IEEE,2023,3:1684-1687.
[12]Wu X P,Peng L,Yang H H,et al. Sparse fuse dense:towards high quality 3D detection with depth completion[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans,LA,USA.IEEE,2022:5408-5417.
[13]Wang C Y,Bochkovskiy A,Liao H M. YOLO v7:trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver,BC,Canada.IEEE,2023:7464-7475.
[14]王春梅,刘欢. YOLO v8-VSC:一种轻量级的带钢表面缺陷检测算法[J]. 计算机科学与探索,2024,3(1):151-160.
[15]Xu Y,Huang J N,Wang J X,et al. ESA-VLAD:a lightweight network based on second-order attention and NetVLAD for loop closure detection[J]. IEEE Robotics and Automation Letters,2021,6(4):6545-6552.
[16]Dian S Y,Yin Y J,Wu C,et al. Loop closure detection based on local-global similarity measurement strategies[J]. Journal of Electronic Imaging,2022,31(2):31-42.
[17]Dong G,Xie W,Huang X,et al. Review of small object detection algorithms based on deep learning[J]. Computer Engineering and Applications,2023,59(11):16-27.
[18]Yang G,Wang J,Nie Z,et al. A lightweight YOLO v8 tomato detection algorithm combining feature enhancement and attention[J]. Agronomy,2023,13(7):18-24.
[19]Wang C Y,Bochkovskiy A,Liao H M. YOLO v7:trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver,BC,Canada.IEEE,2023:7464-7475.
[20]安鹤男,管聪,邓武才,等. 基于YOLOX融合自注意力机制的FSA-FPN重构方法[J]. 电子技术应用,2023,49(3):61-66.
[21]黄骞瑶,陆安江. 基于YOLO v5对花生种子质量的识别研究[J]. 建模与仿真,2023,12(6):8.
[22]Xiao Q X,Huang J D,Huang Z Y,et al. Transparent component defect detection method based on improved YOLO v7 algorithm[J]. International Journal of Pattern Recognition and Artificial Intelligence,2023,37(14):2350030.
[23]Wang C Y,Mark Liao H Y,Wu Y H,et al. CSPNet:a new backbone that can enhance learning capability of CNN[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Seattle,WA,USA.IEEE,2020:1571-1580.
[24]Loureiro C,Filipe V,Gonalves L. Attention mechanism for classification of melanomas[M]//Optimization,Learning Algorithms and Applications.Cham:Springer International Publishing,2022:65-77.
[25]周兴华,陈西江,羊海东,等. 动态卷积YOLO v5的视频火焰检测算法[J]. 测绘科学,2023,48(4):106-118.
[26]耿磊,汪洋,傅洪亮,等. 一种基于动态卷积神经网络及脉冲神经网络的语音情感识别模型[J]. 计算机工程,2023,49(4):7.
[27]肖经纬,田军委,王沁,等. 基于改进残差网络的果实病害分类方法[J]. 计算机工程,2020,46(9):221-225.
[28]王凯,王伟,蒋志伟. 基于改进YOLO模型的遥感小目标检测[J]. 电光与控制,2023,30(6):60-64.
[29]Zhang Y K,Huang S J,Zhou G X,et al. Identification of tomato leaf diseases based on multi-channel automatic orientation recurrent attention network[J]. Computers and Electronics in Agriculture,2023,205:107605.
[30]Li Y. Scientific identification and control measures of several greenhouse cucumber diseases[J]. Primary Agricultural Technology Extension,2021,9(9):40-42.
[31]Chen P,Li W L,Yao S J,et al. Recognition and counting of wheat mites in wheat fields by a three-step deep learning method[J]. Neurocomputing,2021,437:21-30.

相似文献/References:

[1]孙建伟.水涝胁迫对玉米细胞保护酶同工酶的影响[J].江苏农业科学,2013,41(04):85.
[2]刘荣,张卫建,齐华,等.密植型玉米“中单909”高产群体结构特征[J].江苏农业科学,2013,41(05):56.
 Liu Rong,et al.Study on high yield population structure of close planting maize cultivar “Zhongdan 909”[J].Jiangsu Agricultural Sciences,2013,41(5):56.
[3]沈浜凯,肖龙云,冯乃杰,等.黄腐酸和AM真菌对玉米幼苗抗旱性的影响[J].江苏农业科学,2013,41(05):64.
 Shen Bangkai,et al.Effects of fulvic acid and AM fungi on drought resistance of maize seedlings[J].Jiangsu Agricultural Sciences,2013,41(5):64.
[4]张金然,缑艳霞,孙丽鹏.固氮螺菌157对玉米、向日葵的促生长作用[J].江苏农业科学,2014,42(12):116.
 Zhang Jinran,et al.Effects of Azospirillum 157 on growth of maize and sunflower[J].Jiangsu Agricultural Sciences,2014,42(5):116.
[5]白小军,吴燕,牛艳,等.玉米中乙草胺和莠去津残留量GC-MS/MS分析法的建立[J].江苏农业科学,2014,42(11):334.
 Bai Xiaojun,et al().Establishment of GC-MS/MS analysis method of acetochlor and atrazine residues in maize[J].Jiangsu Agricultural Sciences,2014,42(5):334.
[6]邹晓威,王娜,刘芬,等.玉米抗病相关基因在玉米与玉米丝黑穗病菌、玉米黑粉病菌互作过程中的表达差异分析[J].江苏农业科学,2014,42(11):150.
 Zou Xiaowei,et al(0).Different expression of resistance-related genes between Sporisorium reilianum and Ustilago maydis interact with corn[J].Jiangsu Agricultural Sciences,2014,42(5):150.
[7]杨洪兴,陈静,陈艳萍.江苏省玉米机械化生产的发展及育种对策思考[J].江苏农业科学,2014,42(11):116.
 Yang Hongxing,et al().Development and breeding strategy of mechanized production of maize in Jiangsu Province[J].Jiangsu Agricultural Sciences,2014,42(5):116.
[8]张丽妍,霍剑锋,孟繁盛,等.不同肥料、施肥水平及施用方法对玉米产量、性状及效益的影响[J].江苏农业科学,2014,42(11):119.
 Zhang Liyan,et al (9).Effects of different fertilizers,fertilizer levels and fertilizing methods on yield,characters and benefit of maize[J].Jiangsu Agricultural Sciences,2014,42(5):119.
[9]王雷,崔震海,张立军.玉米C4型PEPC全长基因的克隆与表达载体构建[J].江苏农业科学,2014,42(11):26.
 Wang Lei,et al().Cloning and expression vector construction of full-length C4 type PEPC gene in maize[J].Jiangsu Agricultural Sciences,2014,42(5):26.
[10]雷恩,赵光明,刘艳红.不同稀释浓度松土保水剂对玉米营养生长的影响[J].江苏农业科学,2013,41(06):77.
 Lei En,et al.Effect of different dilutions of super absorbent polymer on vegetative growth of maize[J].Jiangsu Agricultural Sciences,2013,41(5):77.
[11]冯峰,周鑫,陈诗瑶,等.一种基于改进神经网络算法ResNet50的玉米病虫害识别模型[J].江苏农业科学,2024,52(16):239.
 Feng Feng,et al.A maize pest and disease identification model based on improved neural network algorithm ResNet50[J].Jiangsu Agricultural Sciences,2024,52(5):239.

备注/Memo

备注/Memo:
收稿日期:2024-05-17
基金项目:国家自然科学基金(编号:62172061);四川省科技计划重点研发项目(编号:2023YFG0116)。
作者简介:杨骞云(2000—),男,江苏南京人,硕士研究生,主要研究方向为农业病虫害的识别与检测。E-mail:1592328161@qq.com。
通信作者:沈艳,博士,教授,主要研究方向为边缘计算、大数据、人工智能。E-mail:sheny@cuit.edu.cn。
更新日期/Last Update: 2025-03-05