[1]冯伟,赵霞.基于改进YOLO11模型的棉花叶片病害检测[J].江苏农业学报,2026,42(03):521-530.[doi:doi:10.3969/j.issn.1000-4440.2026.03.010]
　FENG Wei,ZHAO Xia.Cotton leaf disease detection based on an improved YOLO11 model[J].,2026,42(03):521-530.[doi:doi:10.3969/j.issn.1000-4440.2026.03.010]
点击复制

基于改进YOLO11模型的棉花叶片病害检测()

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
42
期数:
2026年03期
页码:
521-530
栏目:
植物保护
出版日期:
2026-03-31

文章信息/Info

Title:
Cotton leaf disease detection based on an improved YOLO11 model
作者:
冯伟; 赵霞
(甘肃农业大学信息科学技术学院,甘肃兰州730070)
Author(s):
FENG Wei; ZHAO Xia
(College of Information Science and Technology, Gansu Agricultural University, Lanzhou 730070, China)
关键词:
棉花; 叶片病害; YOLO11模型; 多尺度特征融合; 注意力机制; 动态特征融合
Keywords:
cotton; leaf disease; YOLO11 model; multi-scale feature fusion; attention mechanism; dynamic feature fusion
分类号:
TP391.41
DOI:
doi:10.3969/j.issn.1000-4440.2026.03.010
文献标志码:
A
摘要:
为提升YOLO11模型检测棉花叶片病害的性能,本研究以YOLO11模型为基准模型,引入多尺度边缘增强模块(Multi-scale edge enhancement module,MEEM)替代原模型中C3k2模块,在C2PSA模块中增加凝聚注意力机制(Condensed attention,CA),采用动态特征融合(Dynamic feature fusion,DFF)替代颈部网络中特征融合模块(Contat)构建改进YOLO11模型,增强模型对检测目标复杂细节和边缘特征提取以及小目标识别和多尺度特征融合能力,并用Kaggle平台、谷歌和百度搜索工具获得的棉花病害图像数据进行模型检测性能比较。结果表明,改进YOLO11模型对棉花叶片病害的检测准确率、召回率以及平均精度均值mAP50、mAP50∶95分别比基准模型（YOLO11模型）提高6.1个百分点、2.5个百分点、4.5个百分点、2.5个百分点,浮点运算量、参数量分别增加34.92%和26.74%。与YOLOv5、YOLOv8n、YOLOv10n等模型相比,改进YOLO11模型虽然参数量和浮点运算量较高,但其检测准确率、召回率、平均精度均值更高。改进YOLO11模型能显著提高棉花叶片卷叶病、灰霉病、叶斑病、萎蔫病的检测效果,且对枯萎病和健康叶片均保持较高的检测精度。本研究结果对棉花病害的自动化精准检测、预警防治以及棉花安全生产具有重要作用。
Abstract:
In order to improve the performance of the YOLO11 model in detecting cotton leaf diseases, this study used the YOLO11 model as the benchmark model, introduced a multi-scale edge enhancement module (MEEM) to replace the original C3k2 module, and added a condensed attention (CA) mechanism in the C2PSA module. The improved YOLO11 model was constructed by replacing the feature fusion module (Contat) with dynamic feature fusion (DFF), thereby enhancing its ability in extracting complex details and edge features of the target, recognizing small objects, and fusing multi-scale features. The cotton disease image data obtained by Kaggle platform, Google and Baidu search tools were used to compare the model detection performance. The results showed that the detection accuracy, recall rate, mean average precision (mAP50) and mAP50∶95 of the optimized model for cotton leaf diseases were 6.1 percentage points, 2.5 percentage points, 4.5 percentage points and 2.5 percentage points higher than those of the benchmark model, respectively. The floating point operations and parameter count increased by 34.92% and 26.74%, respectively. Compared with YOLOv5, YOLOv8n, YOLOv10n and other models, although the improved YOLO11 model had higher parameter count and floating point operations, its detection accuracy, recall rate and average accuracy were higher. The improved model significantly improved the detection performance of cotton leaf curl, gray mold, leaf spot and wilt diseases, and the detection accuracy of Fusarium wilt and healthy leaves remained high. The results of this study play an important role in the automatic and accurate detection, early warning and control of cotton diseases and the safe production of cotton.

参考文献/References:

[1]袁雄武. 机采棉除杂场中动力补偿的研究[D]. 阿拉尔:塔里木大学,2023.
[2]王晋伟,赵丽红,师勇强,等. 棉花病害全程防治技术研究初报[J]. 中国棉花,2020,47(5):20-22,46.
[3]毕君涛. 基于深度学习的棉叶主要病虫害检测方法研究[D]. 阿拉尔:塔里木大学,2023.
[4]陈沛沛,戴建国,张国顺,等. 基于模型剪枝的棉花氮素营养水平诊断[J]. 农业工程学报,2024,40(6):277-284.
[5]戴硕,白涛,李东亚,等. 基于知识蒸馏及改进ShuffleNet v2的棉花病虫害识别方法[J]. 江苏农业科学,2024,52(15):222-232.
[6]周淋芋,周卫,苏申申,等. 基于MobileNetV3的棉花病虫害图像分类算法改进[J]. 现代计算机,2024,30(22):55-60.
[7]GAO R C, DONG Z C, WANG Y Q, et al. Intelligent cotton pest and disease detection:edge computing solutions with transformer technology and knowledge graphs[J]. Agriculture,2024,14(2):247.
[8]SHAO Y, YANG W Z, WANG J J, et al. Cotton disease recognition method in natural environment based on convolutional neural network[J]. Agriculture,2024,14(9):1577.
[9]QIU K Y, ZHANG Y J, REN Z K, et al. SpemNet:a cotton disease and pest identification method based on efficient multi-scale attention and stacking patch embedding[J]. Insects,2024,15(9):667.
[10]王中璞,吴正香,张立杰,等. 基于ZC-YOLO的棉花杂质检测[J]. 毛纺科技,2024,52(12):95-101.
[11]郭文娟,冯全. 基于改进YOLO的棉花叶片病害检测[J]. 干旱地区农业研究,2024,42(6):195-205.
[12]朱莉. 基于改进Yolov5算法模型的棉籽分类筛选系统研究[D]. 阿拉尔:塔里木大学,2024.
[13]张楠楠,张晓,白铁成,等. 基于CBAM-YOLO v7的自然环境下棉叶病虫害识别方法[J]. 农业机械学报,2023,54(增刊1):239-244.
[14]MA Y K, WEI Y J, MA M S, et al. DCP-YOLOv7x:improved pest detection method for low-quality cotton image[J]. Frontiers in Plant Science,2024,15:1501043.
[15]FENG H R, CHEN X Q, DUAN Z Y. LCDDN-YOLO:lightweight cotton disease detection in natural environment,based on improved YOLOv8[J]. Agriculture,2025,15(4):421.
[16]LI J, LI J H, ZHAO X, et al. Lightweight detection networks for tea bud on complex agricultural environment via improved YOLO v4[J]. Computers and Electronics in Agriculture,2023,211:107955.
[17]LIU H, HOU Y S, ZHANG J C, et al. Research on weed reverse detection methods based on improved you only look once (YOLO) v8:preliminary results[J]. Agronomy,2024,14(8):1667.
[18]HE L H, ZHOU Y Z, LIU L, et al. Research on object detection and recognition in remote sensing images based on YOLOv11[J]. Scientific Reports,2025,15(1):14032.
[19]LI Y J, ZHOU Z F, PAN Y. YOLOv11-BSS:damaged region recognition based on spatial and channel synergistic attention and bi-deformable convolution in sanding scenarios[J]. Electronics,2025,14(7):1469.
[20]JI Y P, ZHANG D, HE Y L, et al. Improved YOLO11 algorithm for insulator defect detection in power distribution lines[J]. Electronics,2025,14(6):1201.
[21]TANG K, QIAN Y R, DONG H L, et al. SP-YOLO:a real-time and efficient multi-scale model for pest detection in sugar beet fields[J]. Insects,2025,16(1):102.
[22]XIONG X R, HE M T, LI T Y, et al. Adaptive feature fusion and improved attention mechanism-based small object detection for UAV target tracking[J]. IEEE Internet of Things Journal,2024,11(12):21239-21249.
[23]ALKHAMMASH E H. A comparative analysis of YOLOv9,YOLOv10,YOLOv11 for smoke and fire detection[J]. Fire,2025,8(1):26.
[24]SUN W Z, MENG N, CHEN L F, et al. CTL-YOLO:a surface defect detection algorithm for lightweight hot-rolled strip steel under complex backgrounds[J]. Machines,2025,13(4):301.
[25]熊干,陈慈发,张上. QMDF-YOLO11:复杂场景下水稻害虫检测算法[J]. 计算机工程与应用,2025,61(13):113-123.
[26]GAO S X, ZHANG P P, YAN T Y, et al. Multi-scale and detail-enhanced segment anything model for salient object detection[C/OL]//Association for Computing Machinery. Proceedings of the 32nd ACM international conference on multimedia. Melbourne:ACM,2024:9894-9903. https://doi.org/10.1145/3664647.3680650.
[27]ZHANG J H, KONG F T, WU J Z, et al. Automatic image segmentation method for cotton leaves with disease under natural environment[J]. Journal of Integrative Agriculture,2018,17(8):1800-1814.
[28]ZHAO H Y, GOU Y B, LI B Y, et al. Comprehensive and delicate:an efficient transformer for image restoration[C]//IEEE. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Vancouver,Canada:IEEE,2023:14122-14132.

相似文献/References:

[1]赵亮,狄佳春,陈旭升.棉花基因组数据库中ＣＰＳ＆ＫＳ 基因的查找与分析[J].江苏农业学报,2016,(01):27.[doi:10.3969/j.issn.1000-4440.2016.01.004 ]
　ZHAO Liang,DI Jia-chun,CEHN Xu-sheng.Analysis of ent-copalyl diphosphate aynthase and ent-kaurene synthase (CPS&KS) gene family in cotton genome databases[J].,2016,(03):27.[doi:10.3969/j.issn.1000-4440.2016.01.004 ]
[2]赵君,刘剑光,吴巧娟,等.棉花种质种仁含油量测定及其遗传多样性分析[J].江苏农业学报,2015,(05):975.[doi:doi:10.3969/j.issn.1000-4440.2015.05.006]
　ZHAO Jun,LIU Jian-guang,WU Qiao-juan,et al.Kernel oil content and genetic diversity of upland cotton germplasm[J].,2015,(03):975.[doi:doi:10.3969/j.issn.1000-4440.2015.05.006]
[3]杨长琴,刘瑞显,张国伟,等.花铃期干旱对棉纤维素累积及纤维比强度的影响[J].江苏农业学报,2015,(06):1218.[doi:doi:10.3969/j.issn.1000-4440.2015.06.005]
　YANG Chang-qin,LIU Rui-xian,ZHANG Guo-wei,et al.Cellulose accumulation and fiber strength affected by drought during flowering and bolling stage in cotton[J].,2015,(03):1218.[doi:doi:10.3969/j.issn.1000-4440.2015.06.005]
[4]杨长琴,刘瑞显,张国伟,等.花铃期渍水对棉铃对位叶光合速率、物质累积及产量的影响[J].江苏农业学报,2015,(04):732.[doi:10.3969/j.issn.1000-4440.2015.04.004]
　YANG Chang-qin,LIU Rui-xian,ZHANG Guo-wei,et al.Photosynthesis of subtending leaves of bolls, dry matter accumulation and cotton yield in response to waterlogging during flowering and boll-forming stage[J].,2015,(03):732.[doi:10.3969/j.issn.1000-4440.2015.04.004]
[5]刘雅辉,王秀萍,鲁雪林,等.棉花耐盐相关序列扩增多态性（SRAP）分子标记筛选[J].江苏农业学报,2015,(03):484.[doi:10.3969/j.issn.1000-4440.2015.03.003]
　LIU Ya-hui,WANG Xiu-ping,LU Xue-lin,et al.Selection of sequence-related amplified polymorphism molecular marker associated with salt tolerance of cotton[J].,2015,(03):484.[doi:10.3969/j.issn.1000-4440.2015.03.003]
[6]王为,叶泗洪,潘宗瑾,等.棉花分子标记冗余性检测与评价的方法[J].江苏农业学报,2015,(02):247.[doi:10.3969/j.issn.1000-4440.2015.02.004]
　WANG Wei,YE Si-hong,PAN Zong-jin,et al.An approach to detecting and evaluating molecular marker redundancy in cotton[J].,2015,(03):247.[doi:10.3969/j.issn.1000-4440.2015.02.004]
[7]郭琪,徐珍珍,黄芳,等.棉花HKT基因家族的全基因组分析[J].江苏农业学报,2017,(05):975.[doi:doi:10.3969/j.issn.1000-4440.2017.05.003]
　GUO Qi,XU Zhen-zhen,HUANG Fang,et al.Genome-wide analysis of high-affinity potassium transporter gene family in cotton[J].,2017,(03):975.[doi:doi:10.3969/j.issn.1000-4440.2017.05.003]
[8]黄芳,徐珍珍,孟珊,等.盐胁迫下棉花LTR-反转座子的转录激活及在耐盐相关基因发掘中的应用[J].江苏农业学报,2017,(06):1220.[doi:doi:10.3969/j.issn.1000-4440.2017.06.004]
　HUANG Fang,XU Zhen-zhen,MENG Shan,et al.The identification of long terminal repeat retrotransposons (LTR-RTs) with transcription activity under salt stress and its application in screening the candidate genes related to salt-tolerant in cotton[J].,2017,(03):1220.[doi:doi:10.3969/j.issn.1000-4440.2017.06.004]
[9]徐剑文,孔杰,赵君,等.盐胁迫下棉花萌发、成苗和产量相关性状的QTL定位[J].江苏农业学报,2018,(05):972.[doi:doi:10.3969/j.issn.1000-4440.2018.05.002]
　XU Jian-wen,KONG-Jie,ZHAO Jun,et al.Identification of QTLs conferring the traits related to germination, seedling survival and production of cotton under salt stress[J].,2018,(03):972.[doi:doi:10.3969/j.issn.1000-4440.2018.05.002]
[10]韦陈华,邓国强,颜超,等.高密度重化控技术对小麦后直播棉花成铃时空分布的调控[J].江苏农业学报,2018,(05):1022.[doi:doi:10.3969/j.issn.1000-4440.2018.05.008]
　WEI Chen-hua,DENG Guo-qiang,YAN Chao,et al.Impact of high planting density with heavy chemical regulation technique on boll spatio-temporal distribution of cotton under direct seeding modes after wheat harvested[J].,2018,(03):1022.[doi:doi:10.3969/j.issn.1000-4440.2018.05.008]

备注/Memo

备注/Memo:
收稿日期：2025-05-13基金项目：甘肃省自然科学基金项目(24JRRA656)作者简介：冯伟(1996-),男,河南信阳人,硕士研究生,主要从事深度学习和目标检测研究。(E-mail)1807208292@qq.com通讯作者：赵霞,(E-mail)58892778@qq.com
更新日期/Last Update: 2026-04-17