在YOLO11n算法中改进RGB图像识别以实现对茶树病害的精确检测

陶晋贤; 李晓丽; 张敬斐; Muhammad SHOAIB; Muhammad Adnan ISLAM; Ibrar AHMAD; 何勇; 叶思潭; 王玉洁; 廖彬惠; Mostafa GOUDA

doi:10.1631/jzus.B2500693

Your Location：

Home >

Browse articles >

在YOLO11n算法中改进RGB图像识别以实现对茶树病害的精确检测

Scan QR Code

文章被引用时，请邮件提醒。

Submit

Research Article | Updated：2026-05-15

在YOLO11n算法中改进RGB图像识别以实现对茶树病害的精确检测
Improving RGB image recognition in the YOLO11n algorithm for accurate detection of tea plant diseases
浙江大学学报（英文版）（B辑：生物医学和生物技术） 2026年27卷第5期页码：482-498
Affiliations：

1.College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China
2.Department of Nutrition and Food Science, National Research Centre, Dokki, Giza 12622, Egypt
3.Liandu Agriculture and Rural Bureau, Lishui 323000, China
Funds：

the Key R&D Projects in Zhejiang Province(2023C02009;2023C02043;2022C02044);the National Natural Science Foundation of China(32171889);the Earmarked Fund for China Agriculture Research System(CARS-19-02A)
DOI：10.1631/jzus.B2500693
中图分类号：
CSTR：
收稿：2025-10-30，

修回：2026-01-28，

纸质出版：2026-05-15
Accepted：

陶晋贤,李晓丽,张敬斐等.在YOLO11n算法中改进RGB图像识别以实现对茶树病害的精确检测[J].浙江大学学报（英文版）（B辑：生物医学和生物技术）,2026,27(05):482-498.

Jinxian TAO, Xiaoli LI, Jingfei ZHANG, et al. Improving RGB image recognition in the YOLO11n algorithm for accurate detection of tea plant diseases[J]. Journal of Zhejiang University-SCIENCE B, 2026, 27(5): 482-498.
陶晋贤,李晓丽,张敬斐等.在YOLO11n算法中改进RGB图像识别以实现对茶树病害的精确检测[J].浙江大学学报（英文版）（B辑：生物医学和生物技术）,2026,27(05):482-498. DOI： 10.1631/jzus.B2500693.

Jinxian TAO, Xiaoli LI, Jingfei ZHANG, et al. Improving RGB image recognition in the YOLO11n algorithm for accurate detection of tea plant diseases[J]. Journal of Zhejiang University-SCIENCE B, 2026, 27(5): 482-498. DOI： 10.1631/jzus.B2500693.

摘要

茶类病害（包括褐色疫病和灰色疫病）会显著降低茶叶的产量与品质，在龙井茶生产中尤为突出。传统检测方法易出现误检，而现有深度学习模型在自然田间条件下通常难以保证足够的鲁棒性。为了解决上述问题，本文提出并验证了一种改进的轻量级检测模型—融合非对称多级（AML）机制、动态蛇形卷积（DSC）与SIoU损失函数的YOLO模型（ADS-YOLO）。本研究在自然光照条件下，构建了包含5694张手机拍摄茶叶图像的数据集。以YOLO11n为基线模型，进行了以下主要改进：引入SIoU损失函数以提升边界框回归效果；采用DSC，基于动态空间上下文实现自适应特征提取；设计AML机制，通过自适应多尺度结构实现轻量化的特征融合。研究结果表明，ADS-YOLO的精确率为0.935，召回率为0.870，而基线模型YOLO11n的对应值分别为0.894和0.818。更重要的是，ADS-YOLO实现了137.1 FPS的实时检测性能，同时降低了计算复杂度。相较于YOLOv5n，ADS-YOLO的当交并比阈值为0.5时的平均精度均值（mAP@0.5）提升了6.4%；相较于YOLOv7t，精确率最高提升了44.6%。综上所述，ADS-YOLO实现了高精度检测，可为作物健康实时监测及茶叶生产的精准可持续发展提供可扩展性的解决方案。

Abstract

Tea diseases

including brown and gray blight

result in significant yield and quality losses

especially in Longjing tea production. Traditional detection methods are prone to errors

while existing deep learning models often struggle to be robust under natural field conditions. To address these challenges

an improved lightweight detection model

asymmetric multi-level (AML) mechanism

dynamic snake convolution (DSC)

and scalable intersection over union (SIoU) loss function-You Only Look Once (YOLO) (ADS-YOLO)

was developed and validated. In the method

a dataset comprising 5694 smartphone-captured images of tea leaves was established under natural lighting. Enhancements were implemented in the YOLO11n baseline algorithm through incorporation of the SIoU loss function for better bounding box regression

DSC

which realizes adaptive feature extraction based on the dynamic spatial context

and an AML mechanism

which achieves lightweight feature fusion via adaptive multi-scale design. The results showed that ADS-YOLO achieved a precision of 0.935 and a recall of 0.870

compared to 0.894 and 0.818

respectively

when the baseline YOLO11n was used. Importantly

ADS-YOLO demonstrated a real-time performance of 137.1 frames per second (FPS)

coupled with reduced computational costs. ADS-YOLO improved the mean average precision (mAP) at intersection over union threshold of 0.5 (mAP@0.5) by 6.4% compared with YOLOv5n and achieved up to 44.6% higher accuracy than YOLOv7t. In conclusion

ADS-YOLO achieved high accuracy

providing a scalable solution for real-time crop health monitoring and sustainable precision agriculture for tea production.

关键词

Keywords

references

Abulizi A , Ye JX , Abudukelimu H , et al. , 2025 . DM-YOLO: improved YOLOv9 model for tomato leaf disease detection . Front Plant Sci , 15 : 1473928 . https://doi.org/10.3389/fpls.2024.1473928 https://doi.org/10.3389/fpls.2024.1473928

An QL , Wang K , Li ZY , et al. , 2022 . Real-time monitoring method of strawberry fruit growth state based on YOLO improved model . IEEE Access , 10 : 124363 - 124372 . https://doi.org/10.1109/ACCESS.2022.3220234 https://doi.org/10.1109/ACCESS.2022.3220234

Ariyawansa HA , Tsai I , Wang JY , et al. , 2021 . Molecular phylogenetic diversity and biological characterization of Diaporthe species associated with leaf spots of Camellia sinensis in Taiwan . Plants , 10 ( 7 ): 1434 . https://doi.org/10.3390/plants10071434 https://doi.org/10.3390/plants10071434

Bao WX , Fan T , Hu GS , et al. , 2022 . Detection and identification of tea leaf diseases based on AX-RetinaNet . Sci Rep , 12 : 2183 . https://doi.org/10.1038/s41598-022-06181-z https://doi.org/10.1038/s41598-022-06181-z

Chen HB , Wang RJ , Du JM , et al. , 2023 . Feature refinement method based on the two-stage detection framework for similar pest detection in the field . Insects , 14 ( 10 ): 819 . https://doi.org/10.3390/insects14100819 https://doi.org/10.3390/insects14100819

Chutichaimaytar P , Zongqi Z , Kaewtrakulpong K , et al. , 2025 . An improved small object detection CTB-YOLO model for early detection of tip-burn and powdery mildew symptoms in coriander ( Coriandrum sativum ) for indoor envir onment using an edge device. Smart Agric Technol , 12 : 101142 . https://doi.org/10.1016/j.atech.2025.101142 https://doi.org/10.1016/j.atech.2025.101142

Dai M , Dorjoy MMH , Miao H , et al. , 2023 . A new pest detection method based on improved YOLOv5m . Insects , 14 : 54 . https://doi.org/10.3390/insects14010054 https://doi.org/10.3390/insects14010054

Dhanya VG , Subeesh A , Kushwaha NL , et al. , 2022 . Deep learning based computer vision approaches for smart agricultural applications . Artif Intell Agric , 6 : 211 - 229 . https://doi.org/10.1016/j.aiia.2022.09.007 https://doi.org/10.1016/j.aiia.2022.09.007

Dong C , Duoqian M , 2023 . Control distance IoU and control distance IoU loss for better bounding box regression . Pattern Recognit , 137 : 109256 . https://doi.org/10.1016/j.patcog.2022.109256 https://doi.org/10.1016/j.patcog.2022.109256

Elharrouss O , Akbari Y , Almadeed N , et al. , 2024 . Backbones-review: feature extractor networks for deep learning and deep reinforcement learning approaches in computer vision . Comput Sci Rev , 53 : 100645 . https://doi.org/10.1016/j.cosrev.2024.100645 https://doi.org/10.1016/j.cosrev.2024.100645

Feng HR , Chen XQ , Duan ZY , 2025 . LCDDN-YOLO: lightweight cotton disease detection in natural environment, based on improved YOLOv8 . Agriculture , 15 ( 4 ): 421 . https://doi.org/10.3390/agriculture15040421 https://doi.org/10.3390/agriculture15040421

Gu ZC , Zhu K , You ST , 2023 . YOLO-SSFS: a method combining SPD-Conv/STDL/IM-FPN/SIoU for outdoor small target vehicle detection . Electronics , 12 ( 18 ): 3744 . https://doi.org/10.3390/electronics12183744 https://doi.org/10.3390/electronics12183744

Huang ZX , Gouda M , Ye ST , et al. , 2024 . Advanced deep learning algorithm for instant discriminating of tea leave stress symptoms by smartphone-based detection . Plant Physiol Biochem , 212 : 108769 . https://doi.org/10.1016/j.plaphy.2024.108769 https://doi.org/10.1016/j.plaphy.2024.108769

Iqbal MS , El-Ashram S , Hussain S , et al. , 2019 . Efficient cell classification of mitochondrial images by using deep learning . J Opt , 48 : 113 - 122 . https://doi.org/10.1007/s12596-018-0508-4 https://doi.org/10.1007/s12596-018-0508-4

Lawal OM , Huamin Z , Fan Z , 2021 . Ablation studies on YOLOFruit detection algorithm for fruit harvesting robot using deep learning . IOP Conf Ser Earth Environ Sci , 922 : 012001 . https://doi.org/10.1088/1755-1315/922/1/012001 https://doi.org/10.1088/1755-1315/922/1/012001

Li XT , Zhang TH , Yu M , et al. , 2025 . A YOLOv8‐based method for detecting tea disease in natural environments . Agron J , 117 ( 2 ): e70043 . https://doi.org/10.1002/agj2.70043 https://doi.org/10.1002/agj2.70043

Lin YT , Xia YJ , Xia PC , et al. , 2025 . YOLO11-ARAF: an accurate and lightweight method for apple detection in real-world complex orchard environments . Agriculture , 15 ( 10 ): 1104 . https://doi.org/10.3390/agriculture15101104 https://doi.org/10.3390/agriculture15101104

Liu Y , Liu HM , Xu WH , et al. , 2024 . Advances and challenges of carbon storage estimation in tea plantation . Ecol Inf , 81 : 102616 . https://doi.org/10.1016/j.ecoinf.2024.102616 https://doi.org/10.1016/j.ecoinf.2024.102616

Lu JQ , Luo HX , Yu CR , et al. , 2024 . Tea bud DG: a lightweight tea bud detection model based on dynamic detection head and adaptive loss function . Comput Electron Agric , 227 : 109522 . https://doi.org/10.1016/j.compag.2024.109522 https://doi.org/10.1016/j.compag.2024.109522

Ma CR , Chi G , Ju XP , et al. , 2025 . YOLO-CWD: a novel model for crop and weed detection based on improved YOLOv8 . Crop Prot , 192 : 107169 . https://doi.org/10.1016/j.cropro.2025.107169 https://doi.org/10.1016/j.cropro.2025.107169

Meng JQ , Wang YX , Zhang JM , et al. , 2023 . Tea bud and picking point detection based on deep learning . Forests , 14 ( 6 ): 1188 . https://doi.org/10.3390/f14061188 https://doi.org/10.3390/f14061188

Parashar N , Johri P , Elbeltagi A , et al. , 2025 . Enhanced residual-attention deep neural network for disease classification in maize leaf images . Sci Rep , 15 : 29452 . https://doi.org/10.1038/s41598-025-14726-1 https://doi.org/10.1038/s41598-025-14726-1

Perez L , Wang J , 2017 . The effectiveness of data augmentation in image classification using deep learning . arXiv :1712. 04621 . https://doi.org/10.48550/arXiv.1712.04621 https://doi.org/10.48550/arXiv.1712.04621

Rahat IS , Ghosh H , Dara S , et al. , 2025 . Towards precision agriculture tea leaf disease detection using CNNs and image processing . Sci Rep , 15 : 17571 . https://doi.org/10.1038/s41598-025-02378-0 https://doi.org/10.1038/s41598-025-02378-0

Soeb JA , Jubayer F , Tarin TA , et al. , 2023 . Tea leaf disease detection and identification based on YOLOv7 (YOLO-T) . Sci Rep , 13 : 6078 . https://doi.org/10.1038/s41598-023-33270-4 https://doi.org/10.1038/s41598-023-33270-4

Sun YG , Li ZH , Guo HP , et al. , 2025 . TDDet: a novel lightweight and efficient tea disease detector . Comput Electron Agric , 237 : 110481 . https://doi.org/10.1016/j.compag.2025.110481 https://doi.org/10.1016/j.compag.2025.110481

Wang RJ , Chen YS , Zhang GH , et al. , 2025 . YOLO11-PGM: high-precision lightweight pomegranate growth monitoring model for smart agriculture . Agronomy , 15 ( 5 ): 1123 . https://doi.org/10.3390/agronomy15051123 https://doi.org/10.3390/agronomy15051123

Wang X , Wu Y , Cui LF , et al. , 2025 . Linear pattern detection of building groups by integrating dynamic snake convolution with YOLO11 . Geocarto Int , 40 ( 1 ): 2471914 . https://doi.org/10.1080/10106049.2025.2471914 https://doi.org/10.1080/10106049.2025.2471914

Wang ZH , Zhao ZX , Hong N , et al. , 2017 . Characterization of causal agents of a novel disease inducing brown-black spots on tender tea leaves in China . Plant Dis , 101 ( 10 ): 1802 - 1811 . https://doi.org/10.1094/PDIS-04-17-0495-RE https://doi.org/10.1094/PDIS-04-17-0495-RE

Wen CM , Cheng Y , Li SP , et al. , 2025 . Slim-YOLO: an improved sugarcane tail tip recognition algorithm based on YOLO11n for complex field environments . Appl Sci , 15 ( 8 ): 4286 . https://doi.org/10.3390/app15084286 https://doi.org/10.3390/app15084286

Wu X , Deng HY , Wang Q , et al. , 2023 . Meta‐learning shows great potential in plant disease recognition under few available samples . Plant J , 114 ( 4 ): 767 - 782 . https://doi.org/10.1111/tpj.16176 https://doi.org/10.1111/tpj.16176

Xie S , Sun HW , 2023 . Tea-YOLOv8s: a tea bud detection model based on deep learning and computer vision . Sensors , 23 ( 14 ): 6576 . https://doi.org/10.3390/s23146576 https://doi.org/10.3390/s23146576

Xu JL , Pan F , Han XH , et al. , 2024 . EdgeTrim-YOLO: improved trim YOLO framework tailored for deployment on edge devices . 2024 4th International Conference on Computer Communication and Artificial Intelligence (CCAI). Xi’an , China , p. 113 - 118 . https://doi.org/10.1109/ccai61966.2024.10602964 https://doi.org/10.1109/ccai61966.2024.10602964

Yang ZM , Ma W , Lu JZ , et al. , 2023 . The application status and trends of machine vision in tea production . Appl Sci , 13 ( 19 ): 10744 . https://doi.org/10.3390/app131910744 https://doi.org/10.3390/app131910744

Yuan ZH , Ning H , Tang XY , et al. , 2024 . GDCP-YOLO: enhancing steel surface defect detection using lightweight machine learning approach . Electronics , 13 ( 7 ): 1388 . https://doi.org/10.3390/electronics13071388 https://doi.org/10.3390/electronics13071388

Zhan BS , Xiong X , Li XL , et al. , 2024 . BHC-YOLOV8: improved YOLOv8-based BHC target detection model for tea leaf disease and defect in real-world scenarios . Front Plant Sci , 15 : 1492504 . https://doi.org/10.3389/fpls.2024.1492504 https://doi.org/10.3389/fpls.2024.1492504

Zheng ZH , Wang P , Liu W , et al. , 2020 . Distance-IoU loss: faster and better learning for bounding box regression . Proceedings of the AAAI Conference on Artificial Intelligence . AAAI Press , Washington , DC , USA , 34 ( 7 ): 12993 - 13000 . https://doi.org/10.1609/aaai.v34i07.6999 https://doi.org/10.1609/aaai.v34i07.6999

Zheng ZW , Yu WW , 2025 . RG-YOLO: multi-scale feature learning for underwater target detection . Multimedia Syst , 31 : 26 . https://doi.org/10.1007/s00530-024-01617-0 https://doi.org/10.1007/s00530-024-01617-0

Zhu JJ , Qiu JL , Chen SW , et al. , 2025 . An application of YOLOv8 integrated with attention mechanisms for detection of grape leaf black rot spots . PLoS One , 20 ( 4 ): e0321788 . https://doi.org/10.1371/journal.pone.0321788 https://doi.org/10.1371/journal.pone.0321788

Zhu XY , Chen FJ , Zheng YL , et al. , 2024 . Detection of Camellia oleifera fruit maturity in orchards based on modified lightweight YOLO . Comput Electron Agric , 226 : 109471 . https://doi.org/10.1016/j.compag.2024.109471 https://doi.org/10.1016/j.compag.2024.109471

Zong HT , Zhang YS , Liu XX , et al. , 2023 . Recent trends in smartphone‐based optical imaging biosensors for genetic testing: a review . View , 4 ( 4 ): 20220062 . https://doi.org/10.1002/VIW.20220062 https://doi.org/10.1002/VIW.20220062

浏览量

Downloads

CSCD

工具集

关联资源

水生态系统中内分泌干扰物对水生生物和人类的影响及检测修复技术进展

RNA甲基转移酶HENMT1在生物学和疾病中的作用

秦皮乙素可通过抑制降钙素基因相关肽（CGRP）和调节脑膜肥大细胞减轻大鼠偏头痛样疼痛

屈光手术患者TGFBI突变多重qPCR检测体系的建立

耐盐植物促生菌Enterobacter sp. Av16和Acinetobacter sp. Av23减轻盐胁迫对白麻（Apocynum pictum）种子萌发和幼苗光合作用的抑制