[1]尹书宇,阮宁君.基于YOLO11n的轻量级草莓成熟度检测方法[J].江苏农业学报,2025,(10):1997-2008.[doi:doi:10.3969/j.issn.1000-4440.2025.10.013]
　YIN Shuyu,RUAN Ningjun.A lightweight strawberry ripeness detection method based on YOLO11n[J].,2025,(10):1997-2008.[doi:doi:10.3969/j.issn.1000-4440.2025.10.013]
点击复制

基于YOLO11n的轻量级草莓成熟度检测方法()

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2025年10期
页码:
1997-2008
栏目:
农业信息工程
出版日期:
2025-10-31

文章信息/Info

Title:
A lightweight strawberry ripeness detection method based on YOLO11n
作者:
尹书宇; 阮宁君
(长江大学电子信息与电气工程学院,湖北荆州434020)
Author(s):
YIN Shuyu; RUAN Ningjun
(School of Electronic Information and Electrical Engineering, Yangtze University, Jingzhou 434020, China)
关键词:
目标检测; YOLO11n; 轻量化; 特征融合; 注意力机制; 草莓
Keywords:
object detection; YOLO11n; lightweight design; feature fusion; attention mechanism; strawberry
分类号:
S126;S668.4
DOI:
doi:10.3969/j.issn.1000-4440.2025.10.013
文献标志码:
A
摘要:
在田间环境下,为解决草莓采摘机器人设备计算资源受限、草莓果实目标小以及叶片遮挡和草莓果实重叠导致难以精确检测的问题,提出了一种基于YOLO11n的改进模型,对未成熟期、转变期、成熟期的草莓进行检测。首先,利用MobileNetV4替换原模型的主干网络来降低参数量和计算量。其次,提出了一种新的特征融合方法Bi-Freq,替代原模型中颈部网络的特征融合方法,提升了特征表示能力和鲁棒性。最后,在目标检测的输出层添加SEAM注意力机制来提高模型对空间维度和通道的处理能力。改进后的模型(YOLO11n-MFBS)参数量为1.713 M,浮点计算量为4.7 G,相比于原始模型YOLO11n参数量和浮点计算量分别减少33.9%和26.6%。与其他主流检测模型相比,YOLO11n-MFBS模型在轻量化和检测精度上的综合表现更好。
Abstract:
In field environments, to address the challenges of limited computing resources in strawberry-picking robots, small target size, as well as occlusions and overlaps caused by leaves and fruits that hinder accurate detection, an improved model based on YOLO11n was proposed to detect strawberries in the immature, turning, and mature stages. Firstly, MobileNetV4 was used to replace the original backbone network to reduce the number of parameters and computational cost. Secondly, a new feature fusion method, Bi-Freq, was proposed to replace the neck network’s original feature fusion strategy, enhancing feature representation and robustness. Finally, the SEAM attention mechanism was added to the detection head to improve the model’s capability in processing spatial and channel information. The improved model (YOLO11n-MFBS) achieved 1.713 M parameters and 4.7 G FLOPs, reducing parameters and floating-point computation by 33.9% and 26.6% respectively compared to the original YOLO11n. Compared with other mainstream detection models, YOLO11n-MFBS demonstrates superior performance in both lightweight design and detection accuracy.

参考文献/References:

[1]张丽勍,邹小花,邓波,等. 草莓产业标准化现状及对推进上海草莓全产业链标准化的思考[J]. 上海农业学报,2024,40(5):80-88.
[2]ZHANG C, GUO C T, LIU F, et al. Hyperspectral imaging analysis for ripeness evaluation of strawberry with support vector machine[J]. Journal of Food Engineering,2016,179:11-18.
[3]SHAO Y Y, WANG Y X, XUAN G T, et al. Assessment of strawberry ripeness using hyperspectral imaging[J]. Analytical Letters,2021,54(10):1547-1560.
[4]化春键,黄宇峰,蒋毅,等. 基于改进YOLOv7的田间环境下食用玫瑰检测方法[J]. 南京农业大学学报,2025，48（3)：714-723.
[5]化春键,黄宇峰,蒋毅,等. 基于改进YOLOv5s模型的田间食用玫瑰花检测方法[J]. 江苏农业学报,2024,40(8):1464-1472.
[6]ZHANG J, YAN L F, HOU J Y. Recognition of rice leaf diseases based on salient characteristics[C]//2018 13th World Congress on Intelligent Control and Automation (WCICA). July 4-8,2018,Changsha,China：IEEE,2018:801-806.
[7]OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems,Man,and Cybernetics,1979,9(1):62-66.
[8]CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning,1995,20(3):273-297.
[9]JING J P, ZHANG S J, SUN H X, et al. Detection of maturity of “Okubo” peach fruits based on inverted residual mobile block and asymptotic feature pyramid network[J]. Journal of Food Measurement and Characterization,2025,19(1):682-695.
[10]YASEEN M. What is YOLOv8:an in-depth exploration of the internal features of the next-generation object detector[J]. arXiv e-prints,2024,arXiv:2408.15857.
[11]YANG G Y, LEI J, ZHU Z K, et al. AFPN:asymptotic feature pyramid network for object detection[C]//2023 IEEE International Conference on Systems,Man,and Cybernetics (SMC). October 1-4,2023,Honolulu,Oahu,HI,USA:IEEE,2023:2184-2189.
[12]VASCONEZ J P, DELPIANO J, VOUGIOUKAS S, et al. Comparison of convolutional neural networks in fruit detection and counting:a comprehensive evaluation[J]. Computers and Electronics in Agriculture,2020,173:105348.
[13]HOWARD A G, ZHU M L, CHEN B, et al. MobileNets:efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint,2017,arXiv:1704.04861.
[14]LIU W, ANGUELOV D, ERHAN D, et al. SSD:single shot MultiBox detector[M]. Cham:Springer International Publishing,2016:21-37.
[15]方国文,何超,王鑫泽. 基于YOLOv8n的轻量级巴旦木果实识别方法[J]. 江苏农业学报,2024,40(9):1662-1670.
[16]TAN M X, PANG R M, LE Q V. EfficientDet:scalable and efficient object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 13-19,2020. Seattle,WA,USA. IEEE,2020:10778-10787.
[17]KHANAM R, HUSSAIN M. YOLOv11:an overview of the key architectural enhancements[J]. arXiv preprint,2024,arXiv:2410.17725.
[18]QIN D F, LEICHNER C, DELAKIS M, et al. MobileNetV4:universal models fortheMobile ecosystem[C]//Computer Vision-ECCV 2024. Cham:Springer Nature Switzerland,2025:78-96.
[19]CHEN L W, FU Y, GU L, et al. Frequency-aware feature fusion for dense image prediction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2024,46(12):10763-10780.
[20]WANG Y D, ZHANG J, KAN M N, et al. Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 13-19,2020,Seattle,WA,USA:IEEE,2020:12272-12281.
[21]陈仁凡,谢知,林晨. 基于YOLO-ODM的温室草莓成熟度的快速检测[J]. 华中农业大学学报,2023,42(4):262-269.
[22]赵佰亭,程瑞丰,贾晓芬. 融合多尺度特征的YOLOv8裂缝缺陷检测算法[J]. 计算机工程与应用,2024,60(22):261-270.
[23]杨信廷,胡焕,陈晓,等. 多源场景下粘虫板小目标害虫轻量化检测识别模型[J]. 智慧农业(中英文),2025,7(1):111-123.
[24]郑红娜,周理想,王强. 基于YOLO-PS的马铃薯幼苗检测方法研究[J]. 中国农机化学报,2024,45(12):245-250.
[25]黎祖胜,唐吉深,匡迎春. 基于改进YOLOv10n的轻量化荔枝虫害小目标检测模型[J]. 智慧农业(中英文),2025,7(2):146-159.
[26]奚小波,丁杰源,翁小祥,等. 基于轻量化YOLOv5s-MCA的番茄成熟度检测方法[J]. 农业机械学报,2025,56(3):383-391,436.
[27]曾孟佳,徐欢,黄旭. 一种基于改进YOLOv5n的黄桃虫害检测方法[J]. 安徽农业科学,2025,53(3):236-242.
[28]LIN T Y, DOLLR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). July 21-26,2017,Honolulu,HI,USA:IEEE,2017:936-944.
[29]LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 18-23,2018,Salt Lake City,UT,USA:IEEE,2018:8759-8768.
[30]韩科立,王振坤,余永峰,等. 基于改进YOLO 11n模型的棉花田间复杂环境障碍物检测方法[J]. 农业机械学报,2025,56(5):111-120.
[31]李凯璇,刘晓锋,陈强,等. YOLOv8-GAIS:一种改进的无人机航拍目标检测算法[J]. 光电工程,2025,52(4):77-90.
[32]陈仁凡,孔彦琪,钟雅露,等. 基于改进YOLO的轻量级草莓成熟度检测方法研究[J]. 江苏农业科学,2024,52(20):138-147.
[33]姜业帆,江朝晖,朱瑞,等. 基于PCIA-YOLO的复杂环境下草莓成熟度轻量化检测方法[J]. 南京农业大学学报, 2025,48(4):1-15.

相似文献/References:

[1]李恒,南新元,高丙朋,等.一种基于GhostNet的绿色类圆果实识别方法[J].江苏农业学报,2023,(03):724.[doi:doi:10.3969/j.issn.1000-4440.2023.03.013]
　LI Heng,NAN Xin-yuan,GAO Bing-peng,et al.A green round-like fruits identification method based on GhostNet[J].,2023,(10):724.[doi:doi:10.3969/j.issn.1000-4440.2023.03.013]
[2]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,(10):1543.[doi:doi:10.3969/j.issn.1000-4440.2023.07.011]
[3]化春键,黄宇峰,蒋毅,等.基于改进YOLOv5s模型的田间食用玫瑰花检测方法[J].江苏农业学报,2024,(08):1464.[doi:doi:10.3969/j.issn.1000-4440.2024.08.011]
　HUA Chunjian,HUANG Yufeng,JIANG Yi,et al.Detection method of edible roses in field based on improved YOLOv5s model[J].,2024,(10):1464.[doi:doi:10.3969/j.issn.1000-4440.2024.08.011]
[4]承达瑜,赵伟,何伟德,等. 基于改进YOLOv5n模型的农作物病虫害识别方法[J].江苏农业学报,2024,(11):2021.[doi:doi:10.3969/j.issn.1000-4440.2024.11.005]
　CHENG DayuZHAO WeiHE WeideWU ZepengWANG Jiandong. Identification method of crop diseases and insect pests based on improved YOLOv5n model[J].,2024,(10):2021.[doi:doi:10.3969/j.issn.1000-4440.2024.11.005]
[5]李芳,危疆树,王玉超,等.基于改进YOLOv8n模型的辣椒病害检测方法[J].江苏农业学报,2025,(02):323.[doi:doi:10.3969/j.issn.1000-4440.2025.02.013]
　LI Fang,WEI Jiangshu,WANG Yuchao,et al.A chili disease detection method based on an improved YOLOv8n model[J].,2025,(10):323.[doi:doi:10.3969/j.issn.1000-4440.2025.02.013]
[6]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,(10):537.[doi:doi:10.3969/j.issn.1000-4440.2025.03.013]
[7]夏顺兴,倪铭,罗友璐,等.基于改进YOLOv8n的草莓叶片病害检测方法[J].江苏农业学报,2025,(04):664.[doi:doi:10.3969/j.issn.1000-4440.2025.04.005]
　XIA Shunxing,NI Ming,LUO Youlu,et al.Strawberry leaf disease detection method based on improved YOLOv8n[J].,2025,(10):664.[doi:doi:10.3969/j.issn.1000-4440.2025.04.005]
[8]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.[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,(10):2387.[doi:doi:10.3969/j.issn.1000-4440.2025.11.011]
[9]唐义声,姜新华,于晓芳,等.基于WPM-YOLO11的玉米叶片病害检测方法[J].江苏农业学报,2026,42(02):264.[doi:doi:10.3969/j.issn.1000-4440.2026.02.005]
　TANG Yisheng,JIANG Xinhua,YU Xiaofang,et al.A maize leaf disease detection method based on WPM-YOLO11[J].,2026,42(10):264.[doi:doi:10.3969/j.issn.1000-4440.2026.02.005]

备注/Memo

备注/Memo:
收稿日期:2025-04-25基金项目:国家自然科学基金青年项目(52205587)；湖北省自然科学基金青年项目(2022CFB734)作者简介:尹书宇(2001-),男,湖北襄阳人,硕士研究生,研究方向为深度学习、图像处理、人工智能等。(E-mail)ysy04292001@163.com通讯作者:阮宁君,(Tel)18607219955；(E-mail)ruannj@yangtzeu.edu.cn
更新日期/Last Update: 2025-11-17