[1]马聪,陈学东,张学俭,等.基于改进YOLOv10s的酿酒葡萄叶片病虫害检测算法[J].江苏农业学报,2025,(12):2387-2402.[doi:doi:10.3969/j.issn.1000-4440.2025.11.011]
　MA Cong,CHEN Xuedong,ZHANG Xuejian,et al.Detection algorithms for wine grape leaf diseases and pests based on improved YOLOv10s[J].,2025,(12):2387-2402.[doi:doi:10.3969/j.issn.1000-4440.2025.11.011]
点击复制

基于改进YOLOv10s的酿酒葡萄叶片病虫害检测算法()

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2025年12期
页码:
2387-2402
栏目:
农业信息工程
出版日期:
2025-12-31

文章信息/Info

Title:
Detection algorithms for wine grape leaf diseases and pests based on improved YOLOv10s
作者:
马聪1; 2; 陈学东1; 2; 张学俭1; 2; 薛新宇3; 张宋超3; 杨淑婷1; 2
(1.宁夏农林科学院农业经济与信息技术研究所,宁夏银川750002;2.宁夏数智农业工程技术研究中心,宁夏银川750002;3.农业农村部南京农业机械化研究所,江苏南京210014)
Author(s):
MA Cong1; 2; CHEN Xuedong1; 2; ZHANG Xuejian1; 2; XUE Xinyu3; ZHANG Songchao3; YANG Shuting1; 2
(1.Institute of Agricultural Economy and Information Technology, Ningxia Academy of Agriculture and Forestry Sciences, Yinchuan 750002, China;2.Ningxia Digital Intelligence Agricultural Engineering Technology Research Center, Yinchuan 750002, China;3.Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China)
关键词:
酿酒葡萄; 深度学习; 目标检测; YOLOv10; 视觉变换器; 注意力机制
Keywords:
wine grape; deep learning; object detection; YOLOv10; vision transformer; attention mechanism
分类号:
S663.1;TP391.4
DOI:
doi:10.3969/j.issn.1000-4440.2025.11.011
文献标志码:
A
摘要:
葡萄叶片病虫害的精准识别是实现葡萄种植智能化管理的重要研究方向。针对现有方法在光照变化、叶片遮挡等复杂田间环境下存在准确性与实时性不足的问题,本研究基于YOLOv10s提出一种用于酿酒葡萄叶片病虫害检测的高精度方法RMT-YOLOv10s。首先,在主干网络中使用网络视觉变换器(RMT)提取图像特征,实现局部与全局信息的协同建模；其次,在颈部网络设计一种融合通道注意力与深度可分离卷积的改进的角点注意力(ICA)模块,增强模型对关键病虫害区域的关注能力；最后,在目标边框损失函数上,使用WIoU Loss v3替换CIoU Loss,在稳定模型训练的同时更精确地预测目标。结果表明,相较于YOLOv10s模型,RMT-YOLOv10s的精确率、召回率、mAP50[在目标边框的交并比(IoU)阈值为0.5的条件下计算所有类别的平均精度并取其均值]以及mAP50∶95(在IoU阈值从0.50 到0.95、步长为0.05的10个不同阈值下,分别计算各类别的平均精度,再对这些平均精度取平均值得到的评价指标)在MS COCO2017验证集上分别提高了4.2个百分点、2.7个百分点、3.0个百分点和1.9个百分点,同时在自建酿酒葡萄叶片病虫害检测数据集上RMT-YOLOv10s在这4个指标上分别达到98.3%、97.0%、97.9%和92.9%,较YOLOv10s分别提升了2.3个百分点、1.6个百分点、2.1个百分点和2.5个百分点。
Abstract:
Accurate identification of grape leaf diseases and pests is a crucial research focus for realizing intelligent vineyard management. Existing detection methods often fail to deliver sufficient accuracy and real-time performance under complex field conditions such as varying illumination and leaf occlusion. To address these challenges, a high-precision method named RMT-YOLOv10s was proposed for wine grape leaf diseases and pests detection, based on the YOLOv10s framework. First, Retentive Networks Meet Vision Transformers (RMT) was integrated into the backbone network to extract image features, enabling collaborative modeling of both local and global information. Second, the Improved Coordinate Attention (ICA) module was proposed in the neck network, which combined channel attention and depthwise separable convolution, to enhance the focus of model on key diseased or pest-affected regions. Finally, WIoU Loss v3 was adopted to replace CIoU Loss in the bounding box loss function, which improved prediction accuracy while ensuring stable model training. The results demonstrated that compared with YOLOv10s, RMT-YOLOv10s achieved improvements of 4.2 percentage points, 2.7 percentage points, 3.0 percentage points, and 1.9 percentage points in Precision, Recall, mean average precision at intersection over union (IoU)=0.5 (mAP50), and mean average precision averaged over IoU thresholds from 0.50 to 0.95 with step 0.05 (mAP50∶95) on the MS COCO2017 validation set, respectively. Moreover, on a self-constructed dataset for wine grape leaf disease and pest detection, RMT-YOLOv10s achieved 98.3% Precision, 97.0% Recall, 97.9% mAP50 and 92.9% mAP50∶95, representing 2.3 percentage points, 1.6 percentage points, 2.1 percentage points, and 2.5 percentage points over YOLOv10s, respectively.

参考文献/References:

[1]刘帅,张亚红,刘鑫,等. 不同光源补光对设施红地球葡萄果实品质的影响[J]. 江苏农业学报,2021,37(4):949-956.
[2]范咏梅,姜新丽,郝敬喆,等. 葡萄斑叶蝉为害与葡萄叶片有关物质之间的相关性分析[J]. 西北农业学报,2008,17(1):70-73.
[3]李承烨,张震,梁哲恒,等. 目标检测模型综述[J/OL]. 计算机研究与发展,2025,62:1-35
[2025-05-07]. https://link.cnki.net/urlid/11.1777.TP.20250506.1645.012.
[4]ZOU Z X, CHEN K Y, SHI Z W, et al. Object detection in 20 years:a survey[J]. Proceedings of the IEEE,2023,111(3):257-276.
[5]王宁,智敏. 深度学习下的单阶段通用目标检测算法研究综述[J]. 计算机科学与探索,2025,19(5):1115-1140.
[6]GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Confe-rence on Computer Vision. December 7-13,2015,Santiago,Chile:IEEE,2015:1440-1448.
[7]WU J Z, LIU B, ZHANG H, et al. Fault detection based on fully convolutional networks (FCN)[J]. Journal of Marine Science and Engineering,2021,9(3):259.
[8]REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified,real-time object detection[C]//2016 IEEE Confe-rence on Computer Vision and Pattern Recognition. June 27-30,2016,Las Vegas,NV,USA:IEEE,2016:779-788.
[9]DUAN K W, BAI S, XIE L X, et al. CenterNet:keypoint triplets for object detection[C]//2019 IEEE/CVF International Confe-rence on Computer Vision. October 27-November 2,2019. Seoul,Korea (South):IEEE,2019:6569-6578.
[10]CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[M]//Computer Vision-ECCV 2020,Cham:Springer International Publishing,2020:213-229.
[11]ZHU X, SU W, LU L, et al. Deformable detr:deformable transformers for end-to-end object detection[J]. arXiv preprint,arXiv:2010.04159, 2020.
[12]LI F, ZHANG H, LIU S L, et al. DN-DETR:accelerate DETR training by introducing query DeNoising[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 18-24,2022,New Orleans,LA,USA. IEEE,2022:13609-13617.
[13]ZHANG H, LI F, LIU S, et al. Dino: Detr with improved denoising anchor boxes for end-to-end object detection[J]. arXiv preprint,arXiv:2203.03605, 2022.
[14]雷建云,叶莎,夏梦,等. 基于改进YOLOv4的葡萄叶片病害检测[J]. 中南民族大学学报(自然科学版),2022,41(6):712-719.
[15]刘广,胡国玉,古丽巴哈尔·托乎提,等. 基于改进YOLOv3的葡萄叶部病虫害检测方法[J]. 微电子学与计算机,2023,40(2):110-119.
[16]蔺瑶,曾晏林,刘金涛,等. 基于EBP-YOLOv8的葡萄叶病害检测与识别方法研究[J]. 山东农业大学学报(自然科学版),2024,55(3):322-334.
[17]王俏,张彪,刘鑫. 基于改进行锚分类的快速葡萄叶片病害检测算法[J]. 江苏农业科学,2024,52(23):206-213.
[18]张立强,武玲梅,蒋林利,等. 基于改进YOLO v8s的葡萄叶片病害检测[J]. 江苏农业科学,2024,52(21):221-228.
[19]蔡易南,肖小玲. 基于改进YOLO v5n的葡萄叶病虫害检测模型轻量化方法[J]. 江苏农业科学,2024,52(7):198-205.
[20]姜红花,胡芳超,刘志鹏,等. 基于YOLO v5s-RCW的葡萄病害检测方法[J/OL]. 农业机械学报,2025(6):1-10
[2025-06-20]. https://link.cnki.net/urlid/11.1964.S.20250619.1512.005.
[21]冀常鹏,佐永吉,代巍. 基于CMS-YOLOv8n的葡萄叶片病害检测[J]. 沈阳农业大学学报,2025,56(3):95-105.
[22]范明超,张和群,踪姿艳,等. 基于YOLO v8n-Grape的葡萄叶片病害小目标检测[J]. 江苏农业科学,2025,53(9):199-207.
[23]ZHANG Y, GUO Z Y, WU J Q, et al. Real-time vehicle detection based on improved YOLOv5[J]. Sustainability,2022,14(19):12274.
[24]SOHAN M, SAI R T, RAMI R C V. A review on YOLOv8 and its advancements[M]//Data Intelligence and Cognitive Informatics. Singapore:Springer Nature Singapore,2024:529-545.
[25]CHEN H, CHEN K, DING G G, et al. YOLOv10:real-time end-to-end object detection[C]//Advances in Neural Information Processing Systems 37. December 10-15,2024. Vancouver,BC,Canada:Neural Information Processing Systems Foundation,Inc. (NeurIPS),2024:107984-108011.
[26]LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO:common objects in context[M]//Computer Vision-ECCV 2014. Cham:Springer International Publishing,2014:740-755.
[27]FAN Q H, HUANG H B, CHEN M R, et al. RMT:retentive networks meet vision transformers[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 16-22,2024,Seattle,WA,USA:IEEE,2024:5641-5651.
[28]ROY A, ABDULLAH R, AHMED F, et al. RetNet:retinal disease detection using convolutional neural network[C]//2023 International Conference on Electrical,Computer and Communication Engineering. February 23-25,2023,Chittagong,Bangladesh:IEEE,2023:1-6.
[29]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. June 20-25,2021. Nashville,TN,USA:IEEE,2021:13713-13722.
[30]HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Re-cognition. June 18-23,2018,Salt Lake City,UT,USA:IEEE,2018:7132-7141.
[31]ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss:faster and better learning for bounding box regression[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(7):12993-13000.
[32]REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union:a metric and a loss for bounding box regression[C]//2019 IEEE/CVF Conference on Computer Vision and Pa-ttern Recognition. June 15-20,2019,Long Beach,CA,USA:IEEE,2019:658-666.
[33]CHO Y J. Weighted intersection over union (wIoU) for evaluating image segmentation[J]. arXiv preprint,arXiv:2107.09858,2021.

相似文献/References:

[1]任胜男,孙钰,张海燕,等.基于one-shot学习的小样本植物病害识别[J].江苏农业学报,2019,(05):1061.[doi:doi:10.3969/j.issn.1000-4440.2019.05.009]
　REN Sheng-nan,SUN Yu,ZHANG Hai-yan,et al.Plant disease identification for small sample based on one-shot learning[J].,2019,(12):1061.[doi:doi:10.3969/j.issn.1000-4440.2019.05.009]
[2]金寿祥,周宏平,姜洪喆,等.采摘机器人视觉系统研究进展[J].江苏农业学报,2023,(02):582.[doi:doi:10.3969/j.issn.1000-4440.2023.02.033]
　JIN Shou-xiang,ZHOU Hong-ping,JIANG Hong-zhe,et al.Research progress on visual system of picking robot[J].,2023,(12):582.[doi:doi:10.3969/j.issn.1000-4440.2023.02.033]
[3]李颀,郭梦媛.基于深度学习的休眠期苹果树点云语义分割[J].江苏农业学报,2023,(05):1189.[doi:doi:10.3969/j.issn.1000-4440.2023.05.011]
　LI Qi,GUO Meng-yuan.Semantic segmentation of apple tree point cloud in dormant period based on deep learning[J].,2023,(12):1189.[doi:doi:10.3969/j.issn.1000-4440.2023.05.011]
[4]翟先一,魏鸿磊,韩美奇,等.基于改进YOLO卷积神经网络的水下海参检测[J].江苏农业学报,2023,(07):1543.[doi:doi:10.3969/j.issn.1000-4440.2023.07.011]
　ZHAI Xian-yi,WEI Hong-lei,HAN Mei-qi,et al.Underwater sea cucumber identification based on improved YOLO convolutional neural network[J].,2023,(12):1543.[doi:doi:10.3969/j.issn.1000-4440.2023.07.011]
[5]许鑫,耿庆,郑凯,等.基于纹理特征与深度学习的小麦图像中的穗粒分割与计数[J].江苏农业学报,2024,(04):661.[doi:doi:10.3969/j.issn.1000-4440.2024.04.010]
　XU Xin,GENG Qing,ZHENG Kai,et al.Segmentation and counting of wheat spikes and grains based on texture features and deep learning[J].,2024,(12):661.[doi:doi:10.3969/j.issn.1000-4440.2024.04.010]
[6]李仁杰,宋涛,高婕,等.基于改进YOLOv5的自然环境下番茄患病叶片检测模型[J].江苏农业学报,2024,(06):1028.[doi:doi:10.3969/j.issn.1000-4440.2024.06.009]
　LI Renjie,SONG Tao,GAO Jie,et al.Tomato diseased leaf detection model based on improved YOLOv5 in natural environment[J].,2024,(12):1028.[doi:doi:10.3969/j.issn.1000-4440.2024.06.009]
[7]林祖香,王英东,马荣,等.基于YOLO-L的自然环境中澳洲坚果果实的检测和识别[J].江苏农业学报,2024,(11):2102.[doi:doi:10.3969/j.issn.1000-4440.2024.11.014]
　LIN Zuxiang,WANG Yingdong,MA Rong,et al.Macadamia (Macadamia integrifolia Maiden & Betche) detection and recognition in natural environments based on YOLO-L[J].,2024,(12):2102.[doi:doi:10.3969/j.issn.1000-4440.2024.11.014]
[8]王德兴,何勇,袁红春.基于YOLOv8-BAN模型的水下生物目标检测方法[J].江苏农业学报,2025,(01):101.[doi:doi:10.3969/j.issn.1000-4440.2025.01.012]
　WANG Dexing,HE Yong,YUAN Hongchun.Underwater biological target detection method based on YOLOv8-BAN model[J].,2025,(12):101.[doi:doi:10.3969/j.issn.1000-4440.2025.01.012]
[9]靳新宇,于复兴,索依娜,等.基于改进YOLOv8的水稻病害检测算法[J].江苏农业学报,2025,(03):537.[doi:doi:10.3969/j.issn.1000-4440.2025.03.013]
　JIN Xinyu,YU Fuxing,SUO Yina,et al.Rice disease detection algorithm based on improved YOLOv8[J].,2025,(12):537.[doi:doi:10.3969/j.issn.1000-4440.2025.03.013]
[10]马亚星,张文斌,鲁权,等.近红外光谱结合深度学习的苹果糖心区域面积占比预测[J].江苏农业学报,2025,(04):715.[doi:doi:10.3969/j.issn.1000-4440.2025.04.010]
　MA Yaxing,ZHANG Wenbin,LU Quan,et al.Near-infrared spectroscopy combined with deep learning for prediction of proportion of apple watercore area[J].,2025,(12):715.[doi:doi:10.3969/j.issn.1000-4440.2025.04.010]
[11]宋晓倩,张学艺,张春梅,等.基于深度迁移学习的酿酒葡萄种植信息提取[J].江苏农业学报,2020,(03):689.[doi:doi:10.3969/j.issn.1000-4440.2020.03.022]
　SONG Xiao-qian,ZHANG Xue-yi,ZHANG Chun-mei,et al.Extraction of wine grape planting information based on deep transfer learning[J].,2020,(12):689.[doi:doi:10.3969/j.issn.1000-4440.2020.03.022]

备注/Memo

备注/Memo:
收稿日期：2025-07-14基金项目：宁夏回族自治区重点研发计划项目(2024BBF01013)；宁夏自然科学基金项目(2023AAC03408)；宁夏农林科学院科技创新引导项目(NKYG-23-02)作者简介：马聪(1987-),女,宁夏吴忠人,硕士,助理研究员,研究方向为农业信息化。(E-mail)congcongcn@163.com通讯作者：杨淑婷，(E-mail)nxnkyyst@163.com
更新日期/Last Update: 2026-01-20