改进YOLOv5模型的草莓检测方法研究

doi:10.13733/j.jcam.issn.2095-5553.2025.01.032

摘要/Abstract

摘要： 草莓检测对草莓的自动化采摘具有重要的意义和价值，针对目前草莓模型检测精度较低、模型占用较大等问题，基于深度学习技术，提出一种改进YOLOv5的目标检测方法。首先，使用Ghost模块对YOLOv5主干网络进行优化，降低模型参数量和复杂度；其次，使用坐标注意力模块CA，提升模型对草莓关键特征的关注；然后将YOLOv5中的定位损失替换为SIoU，考虑边界框回归之间的向量角度。结果表明，该模型的平均精度均值为94.8%，相较于目前经典的目标检测模型，检测能力提升显著，一张图片的预测时间为25.2ms，模型大小仅为10.4MB，具有较快的推理速度且模型尺寸较小。为草莓检测提供更加准确快捷的检测方法，更为容易地应用到移动式和嵌入式设备中。

关键词: 草莓, 深度学习, YOLOv5, 损失函数, 目标检测

Abstract: Strawberry detection is of great significance and value for automated strawberry picking. In order to address the problems of low detection accuracy and large model occupation of the current strawberry model, this study proposes an improved YOLOv5 object detection method based on deep learning technology. Firstly, the YOLOv5 backbone network is optimized by using Ghost model to reduce the number of model parameters and complexity. Secondly, the coordinate attention module CA is used to improve the models focus on key strawberry features. Then the localization loss in YOLOv5 is replaced with SIoU, and the vector angle between the bounding box regressions is considered. The test experimental results show that the average accuracy of the model is 94.8%, compared with the current classical object detection algorithm, the detection ability is improved while the prediction time for a picture is 25.2ms and the model size is only 10.4MB, with faster inference speed and lower model size, the research results can provide a more accurate and faster detection method for strawberry detection, which can be applied to mobile and embedded devices more easily.

Key words: strawberry, deep learning, YOLOv5, loss function, object detection

中图分类号:

彭勇, 乔印虎, 张春燕, 姚杰, 包殿令. 改进YOLOv5模型的草莓检测方法研究[J]. 中国农机化学报, 2025, 46(1): 213-219.

Peng Yong, Qiao Yinhu, Zhang Chunyan, Yao Jie, Bao Dianling. Research of strawberry detection method with improved YOLOv5 model[J]. Journal of Chinese Agricultural Mechanization, 2025, 46(1): 213-219.

参考文献

［1］　张更, 颜志明, 王全智, 等. 我国设施草莓无土栽培技术的研究进展与发展建议［J］. 江苏农业科学, 2019, 47（18）: 58-61.
［2］　翟长远, 付豪, 郑康, 等. 基于深度学习的大田甘蓝在线识别模型建立与试验［J］. 农业机械学报, 2022, 53（4）: 293-303.
Zhai Changyuan, Fu Hao, Zheng Kang, et al. Establishment and experimental verification of deep learning model for online recognition of field cabbage ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53（4）: 293-303.
［3］　苗中华, 沈一筹, 王小华, 等. 自然环境下重叠果实图像识别算法与试验［J］. 农业机械学报, 2016, 47（6）: 21-26.
Miao Zhonghua, Shen Yichou, Wang Xiaohua, et al. Image recognition algorithm and experiment of overlapped fruits in natural environment ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2016, 47（6）: 21-26.
［4］　王粮局, 张立博, 段运红, 等. 基于视觉伺服的草莓采摘机器人果实定位方法［J］. 农业工程学报, 2015, 31（22）: 25-31.
Wang Liangju, Zhang Libo, Duan Yunhong,et al. Fruit localization for strawberry harvesting robot based on visual servoing ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31（22）: 25-31.
［5］　张凯良, 杨丽, 张铁中. 草莓采摘位置机器视觉与激光辅助定位方法［J］. 农业机械学报, 2010, 41（4）: 151-156.
Zhang Kailiang, Yang Li, Zhang Tiezhong. Object locating method of laserassisted machine vision for strawberryharvesting ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2010, 41（4）: 151-156.
［6］　李震, 洪添胜, 倪慧娜, 等. 用高光谱成像技术检测柑橘红蜘蛛为害叶片的色素含量［J］. 农业工程学报, 2014, 30（6）: 124-130.
Li Zhen, Hong Tiansheng, Ni Huina, et al. Pigment content measurement for citrus red mite infected leaf using hyperspectral imaging technology ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30（6）: 124-130.
［7］　Schmidhuber J. Deep learning in neural networks: An overview ［J］. Neural Networks, 2015, 61: 85-117.
［8］　Ren S, He K, Girshick R, et al. Faster R-CNN: Towards realtime object detection with region proposal networks ［J］. Advances in Neural Information Processing Systems, 2015, 28.
［9］　He K, Gkioxari G, Dollár P, et al. Mask R-CNN ［C］.Proceedings of the IEEE International Conference on Computer Vision, 2017: 2961-2969.
［10］　Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector ［C］. European Conference on Computer Vision, Springer, Cham, 2016: 21-37.
［11］　Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection ［C］. Proceedings of the IEEE International Conference on Computer Vision, 2017: 2980-2988.
［12］　Redmon J, Farhadi A. YOLO9000: better, faster, stronger ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263-7271.
［13］　闫建伟, 赵源, 张乐伟, 等. 改进Faster-RCNN自然环境下识别刺梨果实［J］. 农业工程学报, 2019, 35（18）: 143-150.
Yan Jianwei, Zhao Yuan, Zhang Lewei,et al. Recognition of Rosa roxbunghii in natural environment based on improved Faster-RCNN ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35（18）: 143-150.
［14］　Chu P, Li Z, Lammers K, et al. Deep learningbased apple detection using a suppression Mask R-CNN ［J］. Pattern Recognition Letters, 2021, 147: 206-211.
［15］　赵德安, 吴任迪, 刘晓洋, 等. 基于YOLO深度卷积神经网络的复杂背景下机器人采摘苹果定位［J］. 农业工程学报, 2019, 35（3）: 164-173.
Zhao Dean, Wu Rendi, Liu Xiaoyang,et al. Apple positioning based on YOLO deep convolutional neural network for picking robot in complex background ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35（3）: 164-173.
［16］　Yu Y, Zhang K, Yang L, et al. Fruit detection for strawberry harvesting robot in nonstructural environment based on Mask R-CNN ［J］. Computers and Electronics in Agriculture, 2019, 163: 104846.
［17］　Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal speed and accuracy of object detection ［J］. arXiv preprint arXiv, 2004.10934, 2020.
［18］　Wang C Y, Liao H Y M, Wu Y H, et al. CSPNet: A new backbone that can enhance learning capability of CNN ［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020: 390-391.
［19］　Gevorgyan Z. SIoU Loss: More powerful learning for bounding box regression ［J］. arXiv preprint arXiv, 2205.12740, 2022.
［20］　Han K, Wang Y, Tian Q, et al. GhostNet: More features from cheap operations ［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 1580-1589.
［21］　Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design ［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 13713-13722.

[1]	夏子林, 张新洲, 王文波, 夏先飞, 陈兰, 顾寄南. 基于机器视觉的蚕豆荚高精度检测方法研究[J]. 中国农机化学报, 2025, 46(1): 157-163.
[2]	李春雨, 郭肖琴, 杨晶晶, 李忠华. 基于深度学习的水果图像识别[J]. 中国农机化学报, 2025, 46(1): 198-203.
[3]	牛潘婷, 张宝林, 潘丽杰, 郭建鹏(. 基于改进GoogLeNet的玉米叶片病害识别及其可解释性研究[J]. 中国农机化学报, 2025, 46(1): 204-212.
[4]	韩鹏飞, 宋其江, 贾梦实. 基于改进轻量化 EfficientNet-V2模型的小麦种子分类[J]. 中国农机化学报, 2024, 45(9): 111-117.
[5]	李志臣, 凌秀军, 李鸿秋. 基于声音深度学习的发动机失火故障诊断[J]. 中国农机化学报, 2024, 45(9): 134-140.
[6]	桑一男 , 徐增莱 , 汪琼 , 葛海涛 , 王殿广 . 一种轮式采花机器人设计——以黄蜀葵为例[J]. 中国农机化学报, 2024, 45(9): 202-208.
[7]	张传栋, 亓璐, 丁华立. 基于改进 YOLOv8n模型的多品种葡萄簇检测方法[J]. 中国农机化学报, 2024, 45(9): 220-226.
[8]	李邦国, 王辉, 宋杨, 任志伟, 刘跃华, 徐乐程. 基于无人驾驶小麦收割机立体视觉感知系统[J]. 中国农机化学报, 2024, 45(9): 244-249.
[9]	宋立航, 张屹, 时寅豪. 基于改进 YOLOv5s的自然环境下油桃成熟度检测方法[J]. 中国农机化学报, 2024, 45(9): 250-257.
[10]	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.
[11]	许贞辉, 李晓娟. 果园树干检测与导航线拟合算法研究[J]. 中国农机化学报, 2024, 45(8): 217-222.
[12]	胡国玉, 刘广, 周星光, 董娅兰, 周建平, . 基于Swin-TDL算法的果园环境下葡萄病害检测方法[J]. 中国农机化学报, 2024, 45(8): 234-239.
[13]	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.
[14]	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.
[15]	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.