基于改进YOLOv5s的硬核期葡萄簇检测

doi:10.13733/j.jcam.issn.2095‑5553.2024.08.035

摘要/Abstract

摘要： 为实现自然环境下硬核期葡萄簇的快速精准检测，提出一种改进的YOLOv5s网络。首先，将YOLOv5s主干特征提取网络和加强特征提取网络中的卷积模块（Conv）替换为拥有更强特征提取能力的RepConv模块；然后，将YOLOv5s主干特征提取网络中C3结构的BottleNeck也替换为RepConv模块；接下来，将高效通道注意力模块（ECA）添加到YOLOv5s加强特征提取网络中的C3结构；最后，将YOLOv5s卷积模块中的激活函数SiLU改为ReLU6。试验结果表明，改进YOLOv5s网络对葡萄簇检测的精确率为96.5%、召回率为94.5%、平均精度均值为98.0%、检测速度为260 f/s。相比Faster R-CNN、SSD、RetinaNet、YOLOv3（Ultralytics）、YOLOXs和YOLOv5s，其平均精度均值分别高10.4、44.1、13.9、0.2、8.9和1.0个百分点。提出的改进网络能够较好地检测自然环境下模糊、遮挡、簇粘连、不完整、昏暗及逆光等各种状态的硬核期葡萄簇，且方便在移动设备上部署。

关键词: 葡萄簇, 目标检测, YOLOv5s算法, 重参数化, 注意力机制

Abstract: In order to realize the rapid and accurate detection of stone hardening stage grape clusters in the natural environment, an improved YOLOv5s network was proposed. Firstly, the convolutional module (Conv) in the backbone feature extraction network and the enhanced feature extraction network of YOLOv5s was replaced by the RepConv module with stronger feature extraction capabilities. Secondly, the BottleNeck in the C3 structure of the backbone feature extraction network of YOLOv5s was also replaced by the RepConv module. Thirdly, the Efficient Channel Attention (ECA) module was added to the C3 structure of the enhanced feature extraction network of YOLOv5s. Finally, the activation function SiLU in the convolutional module of YOLOv5s was changed to ReLU6. The experimental results showed that the precision of the improved YOLOv5s network for grape cluster detection was 96.5%, the recall rate was 94.5%, the mean average precision was 98.0%, and the detection speed was 260 f/s. Compared with Faster R-CNN, SSD, RetinaNet, YOLOv3 (Ultralytics), YOLOXs and YOLOv5s, the mean average precision of the improved YOLOv5s was 10.4, 44.1, 13.9, 0.2, 8.9 and 1.0 percentage points higher, respectively. The improved network proposed in this paper can effectively detect stone hardening stage grape clusters in various states, such as blur, occlusion, cluster adhesion, incompleteness, dimness, and backlight in the natural environment, and is easy to deploy on mobile devices.

Key words: grape cluster, object detection, YOLOv5s algorithm, re?parameterization, attention mechanism

中图分类号:

TP391.4

冯晓, 张辉, 刘运超, 张微, 李小红, 马中杰, . 基于改进YOLOv5s的硬核期葡萄簇检测[J]. 中国农机化学报, 2024, 45(8): 240-245.

Feng Xiao, , Zhang Hui, , Liu Yunchao, Zhang Wei, , Li Xiaohong, , Ma Zhongjie, . Detection of grape cluster in stone hardening stage based on improved YOLOv5s [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(8): 240-245.

参考文献

[ 1 ] 彭红星，徐慧明，刘华鼐. 融合双分支特征和注意力机制的葡萄病虫害识别模型[J]. 农业工程学报， 2022， 38（10）: 156-165.
Peng Hongxing， Xu Huiming， Liu Huanai. Model for identifying grape pests and diseases based on two‑branch feature fusion and attention mechanism [J]. Transactions of the Chinese Society of Agricultural Engineering， 2022， 38（10）: 156-165.
[ 2 ] 蔡文龙，周艳，贾首星，等. 基于AMESim葡萄修剪机液压系统设计与仿真分析[J]. 中国农机化学报， 2020， 41（10）: 41-47.
Cai Wenlong， Zhou Yan， Jia Shouxing， et al. Design and simulation analysis on hydraulic system of grape trimmer based on AMESim [J]. Journal of Chinese Agricultural Mechanization， 2020， 41（10）: 41-47.
[ 3 ] 张佳喜，黄涛，王茂博. 单马达往复式葡萄剪枝机设计与试验[J]. 农业机械学报， 2021， 52（8）: 106-116.
Zhang Jiaxi， Huang Tao， Wang Maobo. Design and experiment of single motor reciprocating grape pruning machine [J]. Transactions of the Chinese Society for Agricultural Machinery， 2021， 52（8）: 106-116.
[ 4 ] Wang L， Zhao Y， Liu S， et al. Precision detection of dense plums in orchards using the improved YOLOv4 model [J]. Frontiers in Plant Science， 2022， 13: 839269.
[ 5 ] 王卓，王健，王枭雄，等. 基于改进YOLOv4的自然环境苹果轻量级检测方法[J]. 农业机械学报， 2022， 53（8）: 294-302.
Wang Zhuo， Wang Jian， Wang Xiaoxiong， et al. Lightweight real‑time apple detection method based on improved YOLOv4 [J]. Transactions of the Chinese Society for Agricultural Machinery， 2022， 53（8）: 294-302.
[ 6 ] 张三林，张立萍，郑威强，等. 基于YOLOv5的核桃品种识别与定位[J]. 中国农机化学报， 2022， 43（7）: 167-172.
Zhang Sanlin， Zhang Liping， Zheng Weiqiang， et al. Identification and localization of walnut varieties based on YOLOv5 [J]. Journal of Chinese Agricultural Mechanization， 2022， 43（7）: 167-172.
[ 7 ] 黄彤镔，黄河清，李震，等. 基于YOLOv5改进模型的柑橘果实识别方法[J]. 华中农业大学学报， 2022， 41（4）: 170-177.
[ 8 ] Ding X， Zhang X， Ma N， et al. RepvVGG: Making VGG‑style convnets great again [C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2021: 13733-13742.
[ 9 ] Vasu P K A， Gabriel J， Zhu J， et al. MobileOne: An improved one millisecond mobile backbone [J]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2023: 7907-7917.

[1]	赵晓霞, 程曼, 袁洪波. 基于StrongSORT算法的羊只多目标跟踪方法[[J]. 中国农机化学报, 2024, 45(8): 180-188.
[2]	李洁, 高尚兵, 余骥远, 陈新, 李士丛, 袁星星. 基于PMMS-Net和叶绿素荧光成像的绿豆叶斑病抗性鉴定方法[J]. 中国农机化学报, 2024, 45(8): 210-216.
[3]	刘星, 顾寄南, 黄则栋, 张文浩, 张伟. 基于深度学习的苹果点云语义分割方法研究[J]. 中国农机化学报, 2024, 45(8): 223-227.
[4]	苏斐, 王光辉, 史艳霞, 贾然, 闫银发, 祖林禄, . 融合通道注意力机制的ResUnet作物病斑分割模型[J]. 中国农机化学报, 2024, 45(8): 228-233.
[5]	周思捷, 刘天奇, 陈天华. 基于改进YOLOv5算法的水稻病害识别研究[J]. 中国农机化学报, 2024, 45(8): 246-253.
[6]	王克涛, 陈世锋, 陈贵, 韦锦, 蒙丽雯, 陈泉成. 基于YOLOv5s的园林球形绿篱检测方法[J]. 中国农机化学报, 2024, 45(8): 262-269.
[7]	岳耀华, 张伟, 亓立强, . 基于改进YOLOv5的田间大豆花朵生长状态检测方法研究[J]. 中国农机化学报, 2024, 45(7): 188-193.
[8]	张延军, 赵建鑫, . 基于多路神经网络的黄花菜关节点检测算法研究[J]. 中国农机化学报, 2024, 45(7): 228-234.
[9]	吴利刚, 吕媛媛, 周倩, 陈乐, 张梁, 史建华. 基于改进YOLOv5的轻量级黄花成熟检测方法[J]. 中国农机化学报, 2024, 45(7): 235-242.
[10]	张晨一, 张晓乾, 任振辉. 基于改进YOLOv3的自然场景中未成熟青苹果识别研究[J]. 中国农机化学报, 2024, 45(7): 243-248.
[11]	雷浩, 苑迎春, 何振学. 基于多尺度卷积和注意力机制的枣品种识别[J]. 中国农机化学报, 2024, 45(6): 135-141.
[12]	黄尧, 何敬, 付饶, 刘刚, , 林远杨. YOLOv5s-CBAM算法在福寿螺虫卵识别中的应用分析[J]. 中国农机化学报, 2024, 45(6): 223-228.
[13]	周康乔, 刘向阳, 郑特驹. 改进YOLOv5的小目标多类别农田害虫检测算法研究[J]. 中国农机化学报, 2024, 45(6): 235-241.
[14]	薛霞, 刘鹏, 周文. 基于改进YOLOv8算法的实时细粒度植物病害检测[J]. 中国农机化学报, 2024, 45(5): 188-194.
[15]	罗鑫, 李加强, 何超. 基于改进YOLOv4的澳洲坚果视觉监测方法[J]. 中国农机化学报, 2024, 45(5): 217-222.