[1]范哲超,魏泽,张俊楠.基于改进YOLO v10n的番茄成熟度识别算法[J].江苏农业科学,2026,54(12):30-38.
 Fan Zhechao,et al.A recognition algorithm for tomato maturity based on improved YOLO v10[J].Jiangsu Agricultural Sciences,2026,54(12):30-38.
点击复制

基于改进YOLO v10n的番茄成熟度识别算法()

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第54卷
期数:
2026年第12期
页码:
30-38
栏目:
机器视觉与农业智能感知
出版日期:
2026-06-20

文章信息/Info

Title:
A recognition algorithm for tomato maturity based on improved YOLO v10
作者:
范哲超魏泽张俊楠
内蒙古机电职业技术学院电气工程系,内蒙古呼和浩特 010070
Author(s):
Fan Zhechaoet al
关键词:
YOLO v10n注意力机制番茄成熟度目标检测
Keywords:
-
分类号:
S126;TP391.41
DOI:
-
文献标志码:
A
摘要:
番茄成熟度识别是番茄自动采摘的核心技术,当前该领域面临检测精度较低与模型参数量过大的双重瓶颈,严重影响技术实用效率。为解决此问题,以YOLO v10n为基准模型,提出一种兼顾检测精度与轻量化需求的改进算法。借鉴Ghostnet网络的特征压缩思想,将G3Ghost与GhostConv模块融入模型主干网络及颈部网络,在保证特征提取有效性的同时降低模型冗余参数量;引入D-LKA注意力机制,强化模型对关键特征的聚焦能力,重点提升小目标番茄的检测性能,减少漏检现象;采用EIoU损失函数替代YOLO v10n原有的CIoU损失函数,进一步加快模型训练收敛速度并提升检测精度。在相同参数设置的对比试验中,所提出的改进模型能够准确识别出未成熟、半成熟、成熟3个阶段的番茄,并且在精确度、召回率及平均精度均值(mAP)上均优于其他对比模型,分别达到90.7%、87.8%、952%。改进模型参数量为3.04 M,小于大部分对比模型。
Abstract:
-

参考文献/References:

[1]孙永珍,贺靖,魏芳,等. “十三五”我国番茄产业发展及其国际竞争力评价[J]. 中国瓜菜,2023,36(1):112-116.
[2]Wu S X,Su H,Gao F Y,et al. An insight into the prevention and control methods for bacterial wilt disease in tomato plants[J]. Agronomy,2023,13(12):3025-3035.
[3]刘胤池,程旭,芦天罡,等. 农业机器人技术发展现状及趋势[J]. 农业工程,2025,15(6):14-18.
[4]柳军,周成钢,皮杰,等. 农业机器人感知关键技术研究现状与发展趋势[J]. 农机化研究,2025,47(5):1-8.
[5]孙宇朝,李守豪,夏秀波,等. 利用改进YOLO v5s模型检测番茄果实成熟度及外观品质[J]. 园艺学报,2024,51(2):396-410.
[6]张润池,周云成,侯玉涵,等. 基于超深掩蔽与改进YOLO v8的不同成熟度番茄计数方法[J]. 农业工程学报,2024,40(24):146-15.
[7]杨坚,钱振,张燕军,等. 采用改进YOLO v4-tiny的复杂环境下番茄实时识别[J]. 农业工程学报,2022,38(9):215-221.
[8]Shabani M,Abdel-mawgood A,Shimada A,et al. Tomato quality classification based on transfer learning feature extraction and machine learning algorithm classifiers[J]. IEEE Access,2024,12:12345-12356.
[9]梁敖,代东南,牛思琪,等. 基于改进YOLO v5s的草莓成熟度实时检测算法[J]. 山东农业科学,2024,56(11):156-163.
[10]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,2017,39(6):1137-1149.
[11]Xu X Y,Zhao M,Shi P X,et al. Crack detection and comparison study based on faster R-CNN and mask R-CNN[J]. Sensors,2022,22(3):1215.
[12]Khan A,Hassan T,Shafay M,et al. Tomato maturity recognition with convolutional transformers[J]. Scientific Reports,2023,13:22885.
[13]刘凯越,吴建军,李智慧,等. YOLO-Vega:一种面向复杂环境的轻量级番茄检测模型[J]. 计算机工程与应用,2025,1(2):1-15.
[14]廖新芝,孔国希,林桂潮,等. 基于CBAM-YOLO v8的温室番茄果实识别[J]. 中国瓜菜,2025,38(9):48-56.
[15]顾文娟,刘浩状,魏金,等. 基于FPBW-YOLO v8的复杂场景下番茄果实识别方法[J]. 农业机械学报,2025,56(8):467-478.
[16]陈翠琴,孟清. 基于图像处理技术的棚室番茄果实识别[J]. 农机化研究,2025,47(1):189-193.
[17]张俊宁,闫英,胡欢,等. 基于Sim-YOLO的复杂背景下樱桃番茄多目标检测[J]. 中国农机化学报,2025,46(3):238-245.
[18]吴秀君,丁琼. 基于改进YOLO v5的番茄品质识别技术[J]. 农业工程,2025,15(3):34-40.
[19]刘坤,吉宏亚,黄程菲,等. 基于改进YOLO v5s的番茄成熟度识别技术研究[J]. 中国农机化学报,2025,46(5):79-85.
[20]Wang A,Chen H,Liu L H,et al. YOLO v10:real-time end-to-end object detection[C]//Advances in Neural Information Processing Systems. Vancouver:Neural Information Processing Systems Foundation,2024,37:107984-108011.
[21]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.Seattle,WA,USA:IEEE,2020:1580-1589.
[22]He K M,Zhang X Y,Ren S Q,et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,NV,USA:IEEE,2016:770-778.
[23]Olorunshola O E,Irhebhude M E,Evwiekpaefe A E. A comparative study of YOLO v5 and YOLO v7 object detection algorithms[J]. Journal of Computing and Social Informatics,2023,2(1):1-12.
[24]Azad R,Niggemeier L,Hüttemann M,et al. Beyond self-attention:deformable large kernel attention for medical image segmentation[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.Seattle,WA,USA:IEEE,2024:1287-1297.
[25]Zhang Y F,Ren W Q,Zhang Z,et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing,2022,506:146-157.

相似文献/References:

[1]张会敏,谢泽奇,张善文.基于注意力胶囊网络的作物病害识别方法[J].江苏农业科学,2022,50(6):101.
 Zhang Huimin,et al.Study on crop disease recognition method based on attention capsule network[J].Jiangsu Agricultural Sciences,2022,50(12):101.
[2]李萍,邵彧,齐国红,等.基于跨深度学习模型的作物病害检测方法[J].江苏农业科学,2022,50(8):193.
 Li Ping,et al.Crop disease detection method based on cross deep learning model[J].Jiangsu Agricultural Sciences,2022,50(12):193.
[3]荣民希,班彬,王智峥,等.基于Macbm-RCNN的叶片周长和面积测量方法[J].江苏农业科学,2022,50(13):199.
 Rong Minxi,et al.Measurement method of leaf circumference and area based on Macbm-RCNN[J].Jiangsu Agricultural Sciences,2022,50(12):199.
[4]崔艳荣,卞珍怡,高英宁.基于生成对抗网络的花卉识别方法[J].江苏农业科学,2022,50(22):200.
 Cui Yanrong,et al.Flower recognition method based on generative adversarial networks[J].Jiangsu Agricultural Sciences,2022,50(12):200.
[5]温艳兰,陈友鹏,王克强,等.基于迁移学习和改进残差网络的复杂背景下害虫图像识别[J].江苏农业科学,2023,51(8):171.
 Wen Yanlan,et al.Recognition of pest images under complex background based on transfer learning and improved residual network[J].Jiangsu Agricultural Sciences,2023,51(12):171.
[6]马驰,吴华瑞,于会山.基于YOLOX的穴盘甘蓝病害检测方法[J].江苏农业科学,2023,51(8):193.
 Ma Chi,et al.Detection method of cabbage disease based on YOLOX[J].Jiangsu Agricultural Sciences,2023,51(12):193.
[7]赵嘉威,田光兆,邱畅,等.基于改进YOLOv4算法的苹果叶片病害检测方法[J].江苏农业科学,2023,51(9):193.
 Zhao Jiawei,et al.Detection method of apple leaf diseases based on improved YOLOv4 algorithm[J].Jiangsu Agricultural Sciences,2023,51(12):193.
[8]温钊发,蒲智,程曦,等.基于轻量级MIE_Net的田间农作物病害识别[J].江苏农业科学,2023,51(10):176.
 Wen Zhaofa,et al.Field crop disease identification based on lightweight MIE_Net[J].Jiangsu Agricultural Sciences,2023,51(12):176.
[9]沈志豪,刘金江,张建洋.基于改进YOLOX-s的田间麦穗检测及计数[J].江苏农业科学,2023,51(12):164.
 Shen Zhihao,et al.Detection and counting of wheat ears in field based on improved YOLOX-s[J].Jiangsu Agricultural Sciences,2023,51(12):164.
[10]曾晏林,贺壹婷,蔺瑶,等.基于BCE-YOLOv5的苹果叶部病害检测方法[J].江苏农业科学,2023,51(15):155.
 Zeng Yanlin,et al.An apple leaf disease detection method based on BCE-YOLOv5[J].Jiangsu Agricultural Sciences,2023,51(12):155.

备注/Memo

备注/Memo:
收稿日期:2025-09-23
基金项目:内蒙古自治区自然科学基金(编号:2025MS05032);内蒙古机电职业技术学院院级科研项目(编号:NJDZR2506)。
作者简介:范哲超(1983—),男,内蒙古乌兰察布人,硕士,教授,研究方向为农业自动化。E-mail:4168365@qq.com。
更新日期/Last Update: 2026-06-20