Method for the estimation of the cutting points in tomato seedling grafting based on improved YOLO11n

Authors

  • Rongtao Li 1. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China
  • Fahui Yuan 1. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China
  • Sajad Ali 1. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China
  • Xiang Yin 2. School of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, Shandong, China
  • Yong He 1. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China 3. Key Laboratory of Spectroscopy Sensing, Ministry of Agriculture and Rural Affairs, Hangzhou 310058, China
  • Yufei Liu 1. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China 3. Key Laboratory of Spectroscopy Sensing, Ministry of Agriculture and Rural Affairs, Hangzhou 310058, China

Keywords:

seedling grafting, stem detection, instance segmentation, key point detection, YOLO algorithm

Abstract

A grafting robot needs to obtain the position information for the plant seedlings to perform automatic grafting operations. Accurately measuring the cutting points required during grafting plays a pivotal role in completing high-quality grafting tasks. Traditional visual detection models exhibit suboptimal performance on edge devices due to their large model size and suffer from limited detection efficiency. To achieve rapid and precise cutting point localization, this study proposes an all-new module termed the Stimulative Upsample Block (SUB). Additionally, the Spatial and Channel Reconstruction Convolution (SCConv) and a Local Importance-based Attention (LIA) mechanism are incorporated into the YOLO11n architecture, culminating in an enhanced model named YOLO11n-LSS. Our model achieved mean average precision (mAP) values of 93.2% for the instance segmentation task and 98.9% for the key point detection task. Compared to YOLOv8n and YOLO11n, our model reduces the number of parameters and computational cost by 4.6% and 3.8%, respectively, making it a high-performance and lightweight solution. The successful application of the new algorithm will significantly improve the production efficiency of automated tomato grafting and contribute to the advancement of the tomato cultivation industry.      

Key words: seedling grafting, stem detection, instance segmentation, key point detection, YOLO algorithm

DOI: 10.25165/j.ijabe.20261901.10095

Li R T, Yuan F H, Ali S, Yin X, He Y, Liu Y F. Method for the estimation of the cutting points in tomato seedling grafting based on improved YOLO11n. Int J Agric & Biol Eng, 2026; 19(1): 179–186.

References

[1] Valderas-Martinez P, Chiva-Blanch G, Casas R, Arranz S, Martínez-Huélamo M, Urpi-Sarda M, et al. Tomato sauce enriched with olive oil exerts greater effects on cardiovascular disease risk factors than raw tomato and tomato sauce: A randomized trial. Nutrients, 2016; 8（3）: 170.

[2] Song Y J, Teakle G, Lillywhite R. Unravelling effects of red/far-red light on nutritional quality and the role and mechanism in regulating lycopene synthesis in postharvest cherry tomatoes. Food Chemistry, 2023; 414: 135690.

[3] Geng W C, Ma Y, Zhang Y X, Zhu F. Research progress in soil health regulation technology for protected agriculture. Chinese Journal of Eco-Agriculture, 2022; 30（12）: 1973–1984.

[4] Lu W H, Zhang N M, Bao L, Zhang L, Qin T F. Study advances on characteristics, causes and control measures of continuous cropping obstacles of facility cultivation in China. Soils, 2020; 52（4）: 651–658.

[5] Weng P Y, Zheng H Y. Causes and mechanism on crop continuous monoculture problems and its control strategy. Subtropical Plant Science, 2020; 49（2）: 157–162.

[6] Warschefsky E J, Klein L L, Frank M H, Chitwood D H, Londo J P, von Wettberg E J, et al. Rootstocks: Diversity, domestication, and impacts on shoot phenotypes. Trends in Plant Science, 2016; 21（5）: 418–437.

[7] Riga P, Benedicto L, García-Flores L, Villaño D, Medina S, Gil-Izquierdo Á. Rootstock effect on serotonin and nutritional quality of tomatoes produced under low temperature and light conditions. Journal of Food Composition and Analysis, 2016; 46: 50–59.

[8] Ma Q, Niu C X, Wang C, Chen C H, Li Y, Wei M. Effects of differentially expressed microRNAs induced by rootstocks and silicon on improving chilling tolerance of cucumber seedlings （Cucumis sativus L.）. BMC Genomics, 2023; 24（1）: 250.

[9] Fu S J, Chen J Q, Wu X L, Gao H B, Lü G Y. Comprehensive evaluation of low temperature and salt tolerance in grafted and rootstock seedlings combined with yield and quality of grafted tomato. Horticulturae, 2022; 8（7）: 595.

[10] Coşkun O F. The effect of grafting on morphological, physiological and molecular changes induced by drought stress in cucumber. Sustainability, 2023; 15（1）: 875.

[11] Tian H M, Cai K, Tao Z, Yang J S, Zhang J, Wang C, et al. Design of automatic grafting machine for vegetables. Journal of Anhui Agricultural Sciences, 2024; 52（23）: 197–200, 236.

[12] Zhang K L, Chu J, Zhang T Z, Yin Q, Kong Y S, Liu Z. Development status and analysis of automatic grafting technology for vegetables. Transactions of the Chinese Society for Agricultural Machinery, 2017; 48（3）: 1–13.

[13] Belmonte-Ureña L J, Garrido-Cardenas J A, Camacho-Ferre F. Analysis of world research on grafting in horticultural plants. HortScience, 2020; 55（1）: 112–120.

[14] Yan G P, Feng M S, Lin W G, Huang Y, Tong R Z, Cheng Y. Review and prospect for vegetable grafting robot and relevant key technologies. Agriculture, 2022; 12（10）: 1578.

[15] Gulzar Y. Fruit image classification model based on MobileNetV2 with deep transfer learning technique. Sustainability, 2023; 15（3）: 1906.

[16] Gao F F, Fang W T, Sun X M, Wu Z C, Zhao G N, Li G, et al. A novel apple fruit detection and counting methodology based on deep learning and trunk tracking in modern orchard. Computers and Electronics in Agriculture, 2022; 197: 107000.

[17] Yuan T, Lyu L, Zhang F, Fu J, Gao J, Zhang J X, et al. Robust cherry tomatoes detection algorithm in greenhouse scene based on SSD. Agriculture, 2020; 10（5）: 160.

[18] Ning Z T, Luo L F, Liao J X, Wen H J, Wei H L, Lu Q H. Recognition and the optimal picking point location of grape stems based on deep learning. Transactions of the Chinese Society of Agricultural Engineering （Transactions of the CSAE）, 2021; 37（9）: 222–229.

[19] Ko K, Jang I, Choi J H, Lim J H, Lee D U. Stochastic decision fusion of convolutional neural networks for tomato ripeness detection in agricultural sorting systems. Sensors, 2021; 21（3）: 917.

[20] Redmon J, Divvala S, Girshick R, Farhadi A. You Only Look Once: Unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）, Las Vegas: IEEE, 2016; pp.779–788. doi: 10.1109/CVPR.2016.91.

[21] Li T H, Sun M, He Q H, Zhang G S, Shi G Y, Ding X M, et al. Tomato recognition and location algorithm based on improved YOLOv5. Computers and Electronics in Agriculture, 2023; 208: 107759.

[22] Zhang G M, Cao H, Jin Y W, Zhong Y, Zhao A B, Zou X J, et al. YOLOv8n-DDA-SAM: Accurate cutting-point estimation for robotic cherry-tomato harvesting. Agriculture, 2024; 14（7）: 1011.

[23] Yu Q C, Xu Z H, Zhu Y. Watermelon rootstock seedling detection based on improved YOLOv8 image segmentation. International Journal of Advanced Computer Science and Applications, 2025; 16（2）: 160247.

[24] Yu Y T, Li Y J, Xie F X, Song J, Bai Y, Fan Y. Design and experiment of key components of a insertion vegetable grafting machine with six plants synchronous. Scientific Reports, 2025; 15（1）: 16650.

[25] Khanam R, Hussain M. YOLOv11: An overview of the key architectural enhancements. 2024; arXiv: 2410.17725. doi: 10.48550/arXiv.2410.17725.

[26] Wang Y, Li Y S, Wang G, Liu X G. PlainUSR: Chasing faster ConvNet for efficient super-resolution. Computer Vision - ACCV2024, 2024; 15475: 246–264.

[27] Li J F, Wen Y, He L H. SCConv: Spatial and channel reconstruction convolution for feature redundancy. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）, 2023; pp.6153–6162. doi: 10.1109/CVPR52729.2023.00596.

[28] Kleinhenz M D, Waiganjo M, Erbaugh J M, Miller S A. Preparing grafted tomato plants using the cleft graft method. Available: https://horticulture.ucdavis.edu/information/tomato-grafting-guide. Accessed on [2025-03-21].

[29] Wu M N, Lin H R, Shi X R, Zhu S J, Zheng B. MTS-YOLO: A multi-task lightweight and efficient model for tomato fruit bunch maturity and stem detection. Horticulturae, 2024; 10（9）: 1006.

[30] Sapkota R, Flores-Calero M, Qureshi R, Badgujar C, Nepal U, Poulose A, et al. YOLO advances to its genesis: a decadal and comprehensive review of the You Only Look Once （YOLO） series. Artificial Intelligence Review, 2025; 58（9）: 274.

Downloads

Published

2026-03-16

How to Cite

(1)
Li, R.; Yuan, F.; Ali, S.; Yin, X.; He, Y.; Liu, Y. Method for the Estimation of the Cutting Points in Tomato Seedling Grafting Based on Improved YOLO11n. Int J Agric & Biol Eng 2026, 19.

Issue

Vol. 19 No. 1 (2026): IJABE

Section

Information Technology, Sensors and Control Systems

License

Copyright (c) 2026 International Journal of Agricultural and Biological Engineering

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

IJABE is an international peer reviewed, open access journal, adopting Creative Commons Copyright Notices as follows.

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).