新疆大学 机械工程学院(智能制造现代产业学院),新疆 乌鲁木齐 830017
Hu Guoyu (1977―), female, professor, doctoral supervisor, research fields: research on agricultural robots and intelligent agricultural machinery equipment, E-mail: xjhuguoyu@xju.edu.cn.
收稿:2025-07-21,
修回:2025-12-28,
录用:2025-12-30,
纸质出版:2026-03-25
移动端阅览
胡国玉,林哲,王海宁,江德轩.基于改进YOLOv8模型的轻量化葡萄花穗及幼果检测模型[J].新疆大学学报(自然科学版中英文),2026,43(2):129-143.
Hu Guoyu,Lin Zhe,Wang Haining,Jiang Dexuan. Lightweight detection of grape inflorescences and fruitlets using an improved YOLOv8 model[J]. Journal of Xinjiang University(Natural Science Edition in Chinese and English),2026,43(2):129-143.
胡国玉,林哲,王海宁,江德轩.基于改进YOLOv8模型的轻量化葡萄花穗及幼果检测模型[J].新疆大学学报(自然科学版中英文),2026,43(2):129-143. DOI: 10.13568/j.cnki.651094.651316.2025.07.21.0003.
Hu Guoyu,Lin Zhe,Wang Haining,Jiang Dexuan. Lightweight detection of grape inflorescences and fruitlets using an improved YOLOv8 model[J]. Journal of Xinjiang University(Natural Science Edition in Chinese and English),2026,43(2):129-143. DOI: 10.13568/j.cnki.651094.651316.2025.07.21.0003.
在全球范围内,葡萄种植面积广阔、产量丰富,葡萄及相关产业已成为许多国家重要的经济支柱.在葡萄生产中,如何在其关键生长阶段实现高效精准的管理,对提升果实产量和品质至关重要.针对葡萄花穗与幼果期目标尺寸小、易受枝叶遮挡、颜色与背景相似度高,致使现有检测方法在复杂自然环境下识别效果不佳,进而制约精准施药技术应用的问题,本文在新疆建立了葡萄花穗与幼果的专用数据集,并提出一种改进的轻量化检测模型YOLOv8-FCD.该模型引入基于PConv的C2f_Faster模块以降低参数量与计算复杂度,将原始上采样方法替换为CARAFE模块,增强特征提取能力,并设计Detect_SEAM检测头,提升模型在遮挡与小目标场景下的识别精度.实验结果表明,YOLOv8-FCD模型的检测精度(
P
)为93.7%,召回率(
R
)为87.3%,平均精度均值(
mAP
)达到94.6%.与原始YOLOv8n模型相比,
P
提升8.2%,
mAP
提高2.6%,模型体积缩减至原来的85.71%.该模型可为葡萄植保智能化喷雾中的花穗与幼果识别提供有效的技术支撑.
Globally
grape cultivation spans vast areas and achieves substantial yields
making grapes and related industries vital economic pillars for many nations. In grape production
efficient and precise management during key growth stages is essential for enhancing both yield and quality. In view of the problems that during the grape inflorescences and young fruits stage
the targets are small in size
easily obscured by branches and leaves
and highly similar in color to the background
resulting in poor recognition performance of existing detection methods in complex natural environments
which in turn restricts the application of precision spraying technology. This paper establishes a dedicated dataset for grape inflorescences and young fruits in Xinjiang and proposes an improved lightweight detection model
YOLOv8-FCD. The model incorporates a PConv-based C2f_Faster module to reduce parameter count and computation
al complexity
replaces the original up-sampling method with the CARAFE module to enhance feature extraction capability
and introduces the Detect_SEAM detection head to improve recognition accuracy under occlusion and small-target conditions. Experimental results show that the YOLOv8-FCD model achieves a detection precision (
P
) of 93.7% and a recall (
R
) of 87.3%
with a mean average precision (
mAP
) of 94.6%. Compared to the original YOLOv8n model
P
improved by 8.2%
mAP
increased by 2.6%
and the model size is reduced to 85.71% of the original. This model provides effective technical support for the identification of grape inflorescences and young fruits in intelligent spraying for plant protection.
Tian Y , Chen G M , Li J F , et al . Current status of global grape industry development [J]. Tropical Agricultural Science , 2018 , 38 ( 6 ): 96 - 101+105 .
Crupi P , Alba V , Masi G , et al . Effect of two exogenous plant growth regulators on the color and quality parameters of seedless table grape berries [J]. Food Research International , 2019 , 126 : 108667 .
Rademacher W . Plant growth regulators:Backgrounds and uses in plant production [J]. Journal of Plant Growth Regulation , 2015 , 34 ( 4 ): 845 - 872 .
Han X Y , Mi Y F , Wang H L , et al . Influence of GA3 and CPPU on the quality attributes and peelability of “Wuhe Cuibao” grape [J]. Agronomy , 2025 , 15 ( 8 ): 1986 .
Liu Q , Peng J Q , Cheng J H , et al . Research progress on the application of plant growth regulators in grape production [J]. Heilongjiang Agricultural Science , 2019 ( 8 ): 169 - 174 .
Wodzicki L M , Madden L V , Long E Y , et al . Evaluation of a laser-guided intelligent sprayer for disease and insect management on grapes [J]. American Journal of Enology and Viticulture , 2023 , 74 ( 2 ): 0740024 .
Bhalekar D G , Parray R A , Ingle P V , et al . Agrochemical spray technology adoption and safety awareness assessment in crop protection in vineyard cultivation [J]. Current Natural Sciences & Engineering Journal , 2024 , 1 ( 3 ): 188 - 196 .
Wang C L , Liu S C , Wang Y W , et al . Application of convolutional neural network-based detection methods in fresh fruit production:A comprehensive review [J]. Frontiers in Plant Science , 2022 , 13 : 868745 .
Sozzi M , Cantalamessa S , Cogato A , et al . Automatic bunch detection in white grape varieties using YOLOv3,YOLOv4,and YOLOv5 deep learning algorithms [J]. Agronomy , 2022 , 12 ( 2 ): 319 .
Girshick R , Donahue J , Darrell T , et al . Region based convolutional networks for accurate object detection and segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2016 , 38 ( 1 ): 142 - 158 .
Ren S Q , He K M , Girshick R , et al . Faster R-CNN:Towards real time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2016 , 39 ( 6 ): 1137 - 1149 .
Shahin S , Sadeghian R , Sareh S , et al . Faster R-CNN-based decision making in a novel adaptive dual-mode robotic anchoring system [C]// 2021 IEEE International Conference on Robotics and Automation(ICRA 2021 ), May 30-June 5,2021 , Xi’an,Shaanxi,China.New York : IEEE , 2021 : 11010 - 11016 .
Liu W , Anguelov D , Erhan D , et al . SSD:Single shot multiBox detector [C]// 14th European Conference on Computer Vision(ECCV) , October 8-16,2016 , Amsterdam,Netherlands.Cham : Springer , 2016 : 21 - 37 .
Redmon J , Divvala S , Girshick R , et al . You only look once:Unified,real-time object detection [C]// International Conference on Computer Vision and Pattern Recognition(CVPR) , June 26-July 1,2016 , Las Vegas,NV,USA.New York : IEEE , 2016 : 779 - 788 .
Redmon J , Farhadi A . Yolov3:An incremental improvement [PP/OL]. arXiv ( 2018-04-18 )[ 2025-01-01 ]. https://arxiv.org/abs/1804.02767 https://arxiv.org/abs/1804.02767 .
Zhu X , Lyu S , Wang X , et al . TPH-YOLOv5:Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios [C]// 2021 IEEE/CVF International Conference on Computer Vision(ICCV 2021 ), October 11-17,2021 , Montreal,QC,Canada.New York : IEEE , 2021 : 2778 - 2788 .
董文轩 , 梁宏涛 , 刘国柱 , 等 . 深度卷积应用于目标检测算法综述 [J]. 计算机科学与探讨 , 2022 , 16 ( 5 ): 1025 - 1042 .
Dong W X , Liang H T , Liu G Z , et al . Review of deep convolution applied to target detection algorithms [J]. Journal of Frontiers of Computer Science and Technology , 2022 , 16 ( 5 ): 1025 - 1042 . (in Chinese)
Gao G H , Shuai C Y , Wang S Y , et al . Using improved YOLOv5s to recognize tomatoes in a continuous working environment [J]. Signal,Image and Video Processing , 2024 , 18 ( 5 ): 4019 - 4028 .
杜文圣 , 王春颖 , 朱衍俊 , 等 . 采用改进Mask R-CNN算法定位鲜食葡萄疏花夹持点 [J]. 农业工程学院 , 2022 , 38 ( 1 ): 169 - 177 .
Du W S , Wang C Y , Zhu Y J , et al . Fruit stem clamping points location for table grape thinning using improved Mask R-CNN [J]. Transactions of the Chinese Society of Agricultural Engineering , 2022 , 38 ( 1 ): 169 - 177 . (in Chinese)
孙俊 , 吴兆祺 , 贾忆琳 , 等 . 基于改进YOLOv5s的果园环境葡萄检测 [J]. 农业工程学报 , 2023 , 39 ( 18 ): 192 - 200 .
Sun J , Wu Z Q , Jia Y L , et al . Detecting grape in an orchard using improved YOLOv5s [J]. Transactions of the Chinese Society of Agricultural Engineering , 2023 , 39 ( 18 ): 192 - 200 . (in Chinese)
王金鹏 , 何萌 , 甄乾广 , 等 . 基于COF-YOLOv 8n的油茶果静、动态检测计数 [J/OL]. 农业机械学报 , 2024-01-17 . https://link.cnki.net/urlid/11.1964.S.20240117.0910.002 https://link.cnki.net/urlid/11.1964.S.20240117.0910.002 .
Wang J P , He M , Zhen Q G , et al . Camellia oleifera fruit static and dynamic detection counting based on improved COF-YOLOv
8 n[J/OL]. Transactions of the Chinese Society for Agricultural Machinery , 2024-01-17 . https://link.cnki.net/urlid/11.1964.S.20240117.0910.002 https://link.cnki.net/urlid/11.1964.S.20240117.0910.002 . (in Chinese)
Chen J , Kao S H , He H , et al . Run,don't walk:Chasing higher FLOPS for faster neural networks [C]// 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR 2023 ), June 18-22,2023 , Vancouver,COL,Canada.New York : IEEE , 2023 : 12021 - 12031 .
Wang J Q , Chen K , Xu R , et al . CARAFE:Content-aware reassembly of features [C]// 2019 IEEE/CVF International Conference on Computer Vision(ICCV 2019 ), October 27-November 2,2019 , Seoul,South Korea.New York : IEEE , 2019 : 3007 - 3016 .
Yu Z , Huang H , Chen W , et al . Yolo-facev2:A scale and occlusion aware face detector [J]. Pattern Recognition , 2024 , 155 : 110714 .
Selvaraju R R , Cogswell M , Das A , et al . Grad-CAM:Visual explanations from deep networks via gradient-based localization [C]// 2017 IEEE/CVF International Conference on Computer Vision(ICCV 2017 ), October 22-29 , Venice,Italy.New York : IEEE , 2017 : 618 - 626 .
0
浏览量
7
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
