基于改进YOLOv7-tiny的草莓生长阶段检测研究

doi:10.19640/j.cnki.jtau.2026.01.012

天津农学院学报 ›› 2026, Vol. 33 ›› Issue (1): 65-70.doi: 10.19640/j.cnki.jtau.2026.01.012

基于改进YOLOv7-tiny的草莓生长阶段检测研究

徐新¹, 景韩愈², 张天健¹, 王丽¹, 刘建波^{1,通信作者}

1.天津农学院工程技术学院,天津 300392;
2.中北大学软件学院,太原 030051

收稿日期:2024-07-11 出版日期:2026-02-28 发布日期:2026-02-05
通讯作者: 刘建波（1988—）,男,讲师,博士,主要研究方向为机器视觉与智能控制、机械装备智能设计与集成应用。E-mail：qingzhoujianbo@126.com。
作者简介:徐新（1998—）,男,硕士在读,研究方向为食品机械设计与装备。E-mail：xuxin2141@163.com。
基金资助:
天津市技术创新引导专项基金（23YDTPJC00620）; 天津市教委科研计划重点项目（2023ZD002）; 天津农学院青年科技人才发展基金项目（2025QNKJ13）

Strawberry growth stage detection based on improved YOLOv7-tiny

Xu Xin¹, Jing Hanyu², Zhang Tianjian¹, Wang Li¹, Liu Jianbo^{1,Corresponding Author}

1. College of Engineering and Technology, Tianjin Agricultural University, Tianjin 300392, China;
2. School of Software, North University of China, Taiyuan 030051, China

Received:2024-07-11 Online:2026-02-28 Published:2026-02-05

摘要/Abstract

摘要： 为解决草莓采摘过程中机器人对草莓识别精准度低、模型运行速度慢的问题,同时为了减小模型的尺寸,便于模型的搭载,本研究提出了一种基于改进YOLOv7-tiny模型的草莓生长阶段检测算法。首先,为提高模型的鲁棒性,采用数据增强技术,将原有数据进行扩张;其次,使用K-Means++算法对模型的真值盒进行重新聚类,以获得更适合检测草莓生长阶段的视野;为提高模型精度,在原有的网络框架下,增加了6个SimAM轻量级注意力机制模块。相较原有模型精度提高了5%,运行速度提高22.1帧/s,而模型尺寸并未明显提升,符合SimAM轻量级设计的要求。

关键词: 草莓, 生长阶段, YOLOv7-tiny, 目标检测

Abstract: In order to solve the problems of low accuracy of strawberry recognition and slow running speed of the model by the robot in the process of strawberry picking,and to reduce the size of the model to facilitate the mounting of the model, this study proposes a strawberry growth stage detection algorithm based on the improved YOLOv7-tiny model. Firstly, in order to improve the robustness of the model, data enhancement techniques are used to expand the original data; secondly, the K-Means++ algorithm is used to re-cluster the model’s anchors to obtain a more suitable field of view for strawberry growth stage detection; in order to improve the model accuracy, six SimAM lightweight attention mechanism modules are added under the original network framework; compared to the original model the accuracy was improved by 5 percentage points, and the running speed FPS was increased by 22.1, while the model size was not significantly improved, which is in line with the SimAM lightweight design.

Key words: strawberry, growth stage, YOLOv7-tiny, target detection

中图分类号:

S126
TP18

徐新, 景韩愈, 张天健, 王丽, 刘建波. 基于改进YOLOv7-tiny的草莓生长阶段检测研究[J]. 天津农学院学报, 2026, 33(1): 65-70.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://xuebao.tjau.edu.cn/CN/10.19640/j.cnki.jtau.2026.01.012

http://xuebao.tjau.edu.cn/CN/Y2026/V33/I1/65

参考文献

[1] 李鹏,王志强,刘凤之,等. 6个草莓品种果实香气组分分类及育种方向分析[J]. 中国果树,2023(6):38-45,53,142.
[2] 国家统计局. 中华人民共和国2022年国民经济和社会发展统计公报[J]. 中国统计,2023(3):12-29.
[3] PANG X L,SUN Y Q,KONG F Y,et al.Advances and perspectives in research of volatile flavor quality of agricultural products[J]. Scientia Agricultura Sinica,2019,52(18):3192-3198.
[4] WANG H,SARKAR A,RAHMAN A,et al.Research on the industrial upgrade of vegetable growers in Shaanxi:A cross-regional comparative analysis of experience reference[J]. Agronomy,2022,12(1):38.
[5] 赵春江. 智慧农业的发展现状与未来展望[J]. 华南农业大学学报,2021,42(6):1-7.
[6] 黄家才,赵雪迪,高芳征,等. 基于改进YOLOv5s的草莓多阶段识别检测轻量化算法[J]. 农业工程学报,2023,39(21):181-187.
[7] 苏文芝. 基于视觉交互技术的采摘机器人系统设计[J]. 农机化研究,2023,45(8):228-230,234.
[8] XIONG Y,GE Y,FROM P J.An improved obstacle separation method using deep learning for object detection and tracking in a hybrid visual control loop for fruit picking in clusters[J]. Computers and Electronics in Agriculture,2021,191:106508.
[9] FAN Y,ZHANG S,FENG K,et al.Strawberry maturity recognition algorithm combining dark channel enhancement and YOLOv5[J]. Sensors,2022,22(2):419.
[10] XU X,LIU J,XU Q, et al. Recent developments on detection technology for the drying processes of agricultural products[J]. Technology in Agronomy,2025,5(1):e013.[A1]
[11] WANG R,HAN F,JIN Y,et al.Correlation between moisture content and machine vision image characteristics of corn kernels[J]. International Journal of Food Properties,2020,23(1):319-328.
[12] WANG Y,WU H,HUA X,et al.Biological characters identification for hard clam larva based on the improved YOLOX-s[J]. Computers and Electronics in Agriculture,2023,212:108103.
[13] YU K,TANG G,CHEN W,et al.MobilNet-YOLOv5s:An improved lightweight method for real-time detection of sugarcane stem nodes in complex natural environments[J]. IEEE Access,2023,11:104070-104083.
[14] CHEN J,MA A,HUANG L,et al.GA-YOLO:A lightweight YOLO model for dense and occluded grape target detection[J]. Horticulturae,2023,9(4):443.
[15] GAI R,CHEN N,YUAN H.A detection algorithm for cherry fruits based on the improved YOLO-v4 model[J]. Neural Computing and Applications,2023,35(19):13895-13906.
[16] YUE X,WANG Q,HE L,et al.Research on tiny target detection technology of fabric defects based on improved YOLO[J]. Applied Sciences,2022,12(13):6823.
[17] WANG C Y,BOCHKOVSKIY A,LIAO H M.YOLOv7:Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Vancouver,BC,Canada. IEEE,2023:7464-7475.
[18] YANG L X,ZHANG R Y,LI L D,et al.SimAM:A simple,parameter-Free Attention Module for convolutional neural networks[C]//International Conference on Machine Learning,2021.
[19] XU X,LIU J,ZHANG T,et al.Online detection of potato drying stages based on improved YOLOv7-tiny model[J]. Drying Technology,2025,43(4):679-689.

基于改进YOLOv7-tiny的草莓生长阶段检测研究

Strawberry growth stage detection based on improved YOLOv7-tiny

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

本文评价

[1]	郭春艳, 杨洁, 李扬, 王丽娟. 戊唑醇对草莓育苗质量影响的研究[J]. 天津农学院学报, 2024, 31(6): 15-20.
[2]	王奎, 单慧勇, 董钟灿, 孙鹏阳, 李国军. 草莓采摘机器人行走控制系统的设计与实现[J]. 天津农学院学报, 2024, 31(2): 78-86.
[3]	周晓睿, 杨磊, 娄莉娟, 宋欣, 陈江涛. 基于改进ORB-SLAM2算法的动态特征点剔除[J]. 天津农学院学报, 2024, 31(1): 88-94.
[4]	侯佳聪, 邱安然, 常琳, 于玮玮, 王丽娟, 龙鸿. 遮阴对森林草莓分株生理特性的影响[J]. 天津农学院学报, 2023, 30(4): 1-7.
[5]	靳智翔, 吕鑫磊, 段雨杉, 王尧, 余茜颖, 龙鸿. 人工栽培条件下森林草莓花粉活力和萌发状况观测[J]. 天津农学院学报, 2023, 30(1): 42-45.
[6]	周家旭, 王丽娟. 不同草莓品种品质特性综合评价[J]. 天津农学院学报, 2021, 28(2): 1-5.
[7]	连朋, 杜梦卿, 王丽娟. 草莓茎尖组培消毒方法及激素配比的优选[J]. 天津农学院学报, 2019, 26(3): 21-25.
[8]	陈佳. 基于AHP的“长丰草莓”物流风险评估与防范策略[J]. 天津农学院学报, 2018, 25(2): 80-84.
[9]	马盼, 姜慧玲, 冯俊喜, 门洪文, 郭守鹏, 邹永洲, 刘帅, 杨苗苗. 济南市设施草莓生产状况调查与发展建议[J]. 天津农学院学报, 2018, 25(2): 85-88.