An improved YOLO11-based method of detecting tomato leaf diseases

QIN Haoxiang; ZHAO Xia; WANG Min; ZHOU Hui

doi:10.13300/j.cnki.hnlkxb.2026.03.010

您当前的位置：

首页 >

文章列表页 >

An improved YOLO11-based method of detecting tomato leaf diseases

Agricultural artificial intelligence | 更新时间：2026-11-05

- An improved YOLO11-based method of detecting tomato leaf diseases
- Journal of Huazhong Agricultural University Vol. 45, Issue 3, Pages: 115-126(2026)
- 作者机构：
  
  甘肃农业大学信息科学技术学院，兰州730070
- 作者简介：
- 基金信息：
- DOI：10.13300/j.cnki.hnlkxb.2026.03.010
  CLC： S641.2;TP391.41
- Received：29 May 2025，
  
  Published：25 May 2026
- 稿件说明：
移动端阅览
秦皓翔，赵霞，王敏，等.基于改进YOLO11的番茄叶片病害检测方法［J］.华中农业大学学报，2026，45（3）：115‐126.

QIN Haoxiang,ZHAO Xia,WANG Min,et al.An improved YOLO11-based method of detecting tomato leaf diseases[J].Journal of Huazhong Agricultural University,2026,45(03):115-126.
秦皓翔，赵霞，王敏，等.基于改进YOLO11的番茄叶片病害检测方法［J］.华中农业大学学报，2026，45（3）：115‐126. DOI： 10.13300/j.cnki.hnlkxb.2026.03.010.

QIN Haoxiang,ZHAO Xia,WANG Min,et al.An improved YOLO11-based method of detecting tomato leaf diseases[J].Journal of Huazhong Agricultural University,2026,45(03):115-126. DOI： 10.13300/j.cnki.hnlkxb.2026.03.010.

摘要

为解决番茄叶片病害检测中存在的类别分布不均、小目标特征提取困难及复杂环境检测精度不足等问题，提出了一种融合多模块的YOLO11改进算法。模型首先采用自适应阈值焦点损失函数（adaptive threshold focal loss，ATFL）替换传统的交叉熵损失，通过动态权重分配策略，针对病害样本不平衡问题优化训练过程，增强模型对低频病害类别的特征学习能力，提高整体检测精度；其次，引入混合池化注意力模块（hybrid pooling attention，HPA）替换C3k2模块中的普通卷积，设计并行池化分支，结合分组特征重校准技术，强化小目标病害的空间特征提取能力，提升复杂背景下的抗遮挡检测能力；最后，将Conv结构中的归一化替换为重参数批归一化（re-parameterized batch normalization，RepBN），引入可学习调节参数重构归一化过程，稳定训练阶段的特征分布，加速模型收敛并增强泛化性能。结果显示，改进后的YOLO11模型在番茄叶片病害数据集上有着很好的性能，其精确率、召回率、mAP@0.5和mAP@0.5：0.95评价指标相较于YOLO11基础模型分别提升了5.8、4.3、2.3和1.2百分点，特别是在小目标病害区域和密集遮挡场景下，具有很好的检测效果。结果表明，YOLO11改进算法有效提升模型对番茄叶片病害的检测性能，实现番茄叶片病害检测精度与鲁棒性的同步提升。

Abstract

An improved YOLO11 algorithm integrating multiple modules was proposed to solve the problems of uneven distribution of categories， difficulties in extracting features of small target， and insufficient accuracy in detecting tomato leaf diseases in complex environments.Firstly， the adaptive threshold focal loss （ATFL） was used to replace the loss of traditional cross-entropy.The process of training was optimized by implementing a dynamic weight allocation strategy to address the issue of imbalanced samples of diseases， enhance the ability of model to learn features for disease categories with low-frequency and improve the overall accuracy of detection.Secondly， the hybrid pooling attention module （HPA） was introduced to replace the ordinary convolution in the C3k2 module， and a parallel pooling branch was designed.The ability of extracting spatial feature of small target diseases was strengthened by combining with the group feature recalibration technique to enhance the ability of antiocclusion detection in complex environments.Finally， the normalization in the Conv structure was replaced with re-parameterized batch normalization （RepBN）， and a learnable adjustment parameter was introduced to reconstruct the process of normalization to stabilize the feature distribution at the stage of training， accelerate the convergence of model， and enhance the performance of generalization.The results showed that the improved YOLO11 model had excellent performance on the dataset of tomato leaf diseases， with increases of 5.8， 4.3， 2.3， and 1.2 percentage points in the precision， recall， mAP@0.5， and mAP@0.5：0.95 evaluation metrics compared with that of the YOLO11 base model， respectively.It had good performance on detecting areas of small target diseases and scenarios of dense occlusion in particular.It is indicated that the improved YOLO11 algorithm effectively improves the performance of the model in detecting tomato leaf diseases， achieving a synchronous improvement in the accuracy and robustness of detecting tomato leaf diseases.

关键词

Keywords

references

吴六爱，许雪珂.基于改进YOLOv10n的轻量化番茄叶片病虫害检测方法［J］.智慧农业（中英文），2025，7（1）：146-155. WU L A，XU X K.Lightweight tomato leaf disease and pest detection method based on improved YOLOv10n［J］.Smart agriculture，2025，7（1）：146-155 （in Chinese with English abstract） .

姚佳成，葛浩然，张特.基于改进DeepLab V3+模型的番茄叶片病害检测与识别研究［J］.农业技术与装备，2024（9）：6-9. YAO J C，GE H R，ZHANG T.Research on tomato leaf disease detection and recognition based on improved DeepLab V3+ model［J］.Agricultural technology and equipment，2024（9）：6-9 （in Chinese with English abstract） .

赵艳芹，王萌.改进YOLOv5模型的番茄叶部病害检测算法［J］.黑龙江科技大学学报，2023，33（1）：136-141.ZHAO Y Q，WANG M.Detection of tomato leaf diseases based on improved YOLOv5 model［J］.Journal of Heilongjiang University of Science and Technology，2023，33（1）：136-141 （in Chinese with English abstract） .

YANG Z C，SUN L X，LIU Z H，et al.FATDNet：a fusion adversarial network for tomato leaf disease segmentation under complex backgrounds［J/OL］.Computers and electronics in agriculture，2025，234：110270［2025-05-29］.https：//doi.org/10.1016/j.compag.2025.110270.

王娜，陈勇，崔艳荣，等.基于改进轻量化YOLOv5n的番茄叶片病害识别方法［J］.江苏农业科学，2024，52（8）：192-199.WANG N，CHEN Y，CUI Y R，et al.Tomato leaf disease identification method based on improved lightweight YOLOv5n［J］.Jiangsu agricultural sciences，2024，52（8）：192-199 （in Chinese with English abstract） .

储鑫，李祥，罗斌，等.基于改进YOLOv4算法的番茄叶部病害识别方法［J］.江苏农业学报，2023，39（5）：1199-1208.CHU X，LI X，LUO B，et al.Tomato leaf disease identification met-hod based on improved YOLOv4 algorithm［J］.Jiangsu journal of agricultural sciences，2023，39（5）：1199-1208 （in Chinese with English abstract） .

SARDOGAN M，TUNCER A，OZEN Y.Plant leaf disease detection and classification based on CNN with LVQ algorithm［C］//2018 3rd International Conference on Computer Science and Engineering （UBMK）. September 20-23，2018 ，Sarajevo，Bosnia and Herzegovina.Sarajevo：IEEE，2018：382-385.

方晨晨，石繁槐.基于改进深度残差网络的番茄病害图像识别［J］.计算机应用，2020，40（S1）：203-208.FANG C C，SHI F H.Image recognition of tomato diseases based on improved depth residual network［J］.Journal of computer applications，2020，40（S1）：203-208 （in Chinese with English abstract） .

LIU J，WANG X W.Tomato diseases and pests detection based on improved YOLOv3 convolutional neural network［J/OL］.Frontiers in plant science，2020，11：898［2025-05-29］.https：//doi.org/10.3389/fpls.2020.00898.

KARTHIK R，HARIHARAN M，ANAND S，et al.Attention embedded residual CNN for disease detection in tomato leaves［J/OL］.Applied soft computing，2020，86：105933［2025-05-29］.https：//doi.org/10.1016/j.asoc.2019.105933.

周巧黎，马丽，曹丽英，等.基于改进轻量级卷积神经网络MobileNetV3的番茄叶片病害识别［J］.智慧农业（中英文），2022，4（1）：47-56.ZHOU Q L，MA L，CAO L Y，et al.Identification of tomato leaf diseases based on improved lightweight convolutional neural networks MobileNetV3［J］.Smart agriculture，2022，4（1）：47-56 （in Chinese with English abstract） .

贾兆红，张袁源，王海涛，等.基于Res2Net和双线性注意力的番茄病害时期识别方法［J］.农业机械学报，2022，53（7）：259-266.JIA Z H，ZHANG Y Y，WANG H T，et al.Identification method of tomato disease period based on Res2Net and bilinear attention mechanism［J］.Transactions of the CSAM，2022，53（7）：259-266 （in Chinese with English abstract） .

袁婷婷，赖惠成，汤静雯，等.LMFI-YOLO：复杂场景下的轻量化行人检测算法［J］.计算机工程与应用，2025，61（15）：111-123.YUAN T T，LAI H C，TANG J W，et al.LMFI-YOLO：lightweight pedestrian detection algorithm in complex scenes［J］.Computer engineering and applications，2025，61（15）：111-123 （in Chinese with English abstract） .

林汉源，范子安.基于改进YOLO11的小麦籽粒病害识别方法［J］.乡村科技，2024，15（19）：147-152.LIN H Y，FAN Z A.Identification method of wheat grain diseases based on improved YOLO11［J］.Rural science and technology，2024，15（19）：147-152 （in Chinese） .

朱永军，蔡光琪，韩进，等.基于改进YOLOv11的露天矿复杂背景下小目标检测［J］.工矿自动化，2025，51（4）：93-99.ZHU Y J，CAI G Q，HAN J，et al.Small object detection in complex open-pit mine backgrounds based on improved YOLOv11［J］.Journal of mine automation，2025，51（4）：93-99 （in Chinese with English abstract） .

CHENG S，HAN Y，WANG Z Q，et al.An underwater object recognition system based on improved YOLOv11［J/OL］.Electronics，2025，14（1）：201［2025-05-29］.https：//doi.org/10.3390/electronics14010201.

WANG Y，JIANG Y，XU H Q，et al.Detection method of key ship parts based on YOLOv11［J/OL］.Processes，2025，13（1）：201［2025-05-29］.https：//doi.org/10.3390/pr13010201.

YANG B，ZHANG X Y， ZHANG J.EFLNet： enhancing feature learning for infrared small target detection［J］.IEEE transactions on geoscience and remote sensing，2024，62：1-11.

CHEN P，HE W X，QIAN F，et al.A synergistic CNN-transformer network with pooling attention fusion for hyperspectral image classification［J/OL］.Digital signal processing，2025，160：105070［2025-05-29］.https：//doi.org/10.1016/j.dsp.2025.105070.

GUO J L，CHEN X H，TANG Y H，et al.SLAB： Efficient transformers with simplified linear attention and progressive reparameterized batch normalization［PP/OL］.arXiv，2024：2405.11582［2025-05-29］.https：//doi.org/10.48550/arXiv.2405.11582.

IOFFE S，SZEGEDY C.Batch normalization：accelerating deep network training by reducing internal covariate shift［PP/OL］.arXiv，2015：1502.03167［2025-05-29］.https：//doi.org/10.48550/arXiv.1502.03167.

HENDRYCKS D，GIMPEL K.Gaussian error linear units（gelus）［PP/OL］.arXiv，2016：1606.08415［2025-05-29］.https：//doi.org/10.48550/arXiv.1606.08415.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Improved YOLOv8s-based model for detecting bud eye in tubers of seed potatoes

Detecting characteristics of abnormal body surface in Micropterus salmoides under recirculating aquaculture systems based on YOLOv8-DBCS

Cotton leaf disease detection based on EDW-YOLOv8

Detection of umami intensity in grass carp based on hyper-spectrum and multi-attention mechanisms

Passivation effect of compound microbial agents on heavy metals in pig slurry and uptake characteristics of oats in sandy land

Related Author

She Chaomin

Duan Hongbing

Zhou Ling

Wei Jia

Cai Xingkui

ZHU Ming

WANG Rong

WAN Peng

Related Institution

College of Engineering， Huazhong Agricultural University

Ministry of Agriculture and Rural Affairs Key Laboratory of Agricultural Equipment in the Mid-Lower Reaches of the Yangtze River

Ministry of Agriculture and Rural Affairs Key Laboratory of Potato Biology and Biotechnology

College of Engineering，Huazhong Agricultural University/ Ministry of Agriculture and Rural Affairs Key Laboratory of Aquaculture Facilities Engineering

Ministry of Agriculture and Rural Affairs Key Laboratory of Agricultural Equipment in Mid-Lower Yangtze River

AI问答

⁰