Comparative Performance Assessment of a Transplanting Robot Equipped with Machine Vision under Different YOLO Algorithms

Articles in Press

Document Type : Research Article- En

Authors

S. Khodatars

V. Rasooli Sharabiani

Department of Biosystems Engineering, Faculty of Agriculture and Natural Resources, University of Mohaghegh Ardabili, Ardabil, Iran

10.22067/jam.2026.99265.1496

Abstract

In this research, the performance of a greenhouse transplanting robot with a machine vision system based on the YOLO algorithms (YOLOv8s, YOLOv8n, YOLOv8m, YOLOv9c, YOLOv11s, YOLOv11m, and YOLOv11n) in handling pepper, lettuce, and tomato seedlings was evaluated in terms of detection accuracy, processing speed, and transplanting efficiency in a greenhouse environment. A robot was designed with a three-degree-of-freedom robotic arm, a dual-pin gripper, and a 1280×720 resolution camera, which was able to detect and transplant seedlings automatically. After comparing the different YOLO algorithms, the results showed that YOLOv8s had the best balance between accuracy (86.52%) and processing time (1’605.67 milliseconds), and the transplanting success rate was highest for tomato seedlings (92.38%) and lowest for pepper seedlings (81.11%). Statistical analysis confirmed that significant differences existed between the species. This system demonstrated a strong potential for precision agriculture by reducing labour costs and enhancing productivity. With future optimisations, it could deliver improved performance across diverse environmental conditions.

Keywords

Greenhouse

Machine vision

Robotic Transplanting

YOLO algorithm

Subjects

• Digital, Smart, and Precision Agriculture

---

Authors retain the copyright. This is an open access article distributed under Creative Commons Attribution 4.0 International License (CC BY 4.0)

References

1.      Abulizi, A., Ye, J., Abudukelimu, H., & Guo, W. (2025). DM-YOLO: Improved YOLOv9 model for tomato leaf disease detection. Frontiers in Plant Science, 15, 1473928. https://doi.org/10.3389/fpls.2024.1473928

2.      Bac, C. W., Van Henten, E. J., Hemming, J., & Edan, Y. (2014). Harvesting robots for high-value crops: State-of-the-art review and challenges ahead. Journal of Field Robotics, 31(6), 888–911. https://doi.org/10.1002/rob.21525

3.      Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint. https://doi.org/10.48550/arXiv.2004.10934

4.      Feng, P., Nie, Z., & Li, G. (2025). Field-deployable lightweight YOLOv8n for real-time detection and counting of   maize seedlings using UAV RGB imagery. Frontiers in Plant Science, 16, 1639533. https://doi.org/10.3389/fpls.2025.1639533

5.      Garzón, M., & de León, J. (2018). Robots in agriculture: State of art and practical experiences. Service Robots, 67. https://doi.org/10.5772/intechopen.69874

6.      Han, L., Xiang, D., Xu, Q., Du, X., Ma, G., & Mao, H. (2023). Development of simplified seedling transplanting device for supporting efficient production of vegetable raw materials. Applied Sciences, 13(18), 10022. https://doi.org/10.3390/app131810022

7.      Hayashi, S., Ota, T., Kubota, K., Ganno, K., & Kondo, N. (2005). Robotic harvesting technology for fruit vegetables in protected horticultural production. In Information and technology for sustainable fruit and vegetable production (pp. 227–236). Montpellier, France.

8.      Jocher, G. (2020). YOLOv5 by Ultralytics (Version 1.0) [Computer software]. https://github.com/ultralytics/yolov5

9.      Jocher, G., Chaurasia, A., & Qiu, J. (2023). YOLO by Ultralytics (Version 8.0.0) [Computer software]. https://github.com/ultralytics/ultralytics

10.  Jocher, G., & Qiu, J. (2024). Ultralytics YOLO11 (Version 11.0.0) [Computer software]. https://github.com/ultralytics/ultralytics

11.  Khadatkar, A., Magar, A., Sawant, C., & Modi, R. (2024). Development and testing of automatic seedling extractor in robotic transplanter using mechatronics for nursery seedlings. Discover Applied Sciences, 6(2), 51. https://doi.org/10.1007/s42452-024-05670-2

12.  Kondo, N., Monta, M., & Noguchi, N. (Eds.). (2011). Agricultural robots: Mechanisms and practice. Kyoto, Japan: Kyoto University Press.

13.  Li, D., Xu, L., Tan, C., Goodman, E. D., Fu, D., & Xin, L. (2015). Digitization and visualization of greenhouse tomato plants in indoor environments. Sensors, 15(2), 4019–4051. https://doi.org/10.3390/s150204019

14.  Li, M., Zhang, Z., Lei, L., Wang, X., & Guo, X. (2020). Agricultural greenhouse detection in high-resolution satellite images based on convolutional neural networks: Comparison of Faster R-CNN, YOLOv3 and SSD. Sensors, 20(17), 4938. https://doi.org/10.3390/s20174938

15.  Liakos, K. G., Busato, P., Moshou, D., Pearson, S., & Bochtis, D. (2018). Machine learning in agriculture: A review. Sensors, 18(8), 2674. https://doi.org/10.3390/s18082674

16.  Patrício, D. I., & Rieder, R. (2018). Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review. Computers and Electronics in Agriculture, 153, 69–81. https://doi.org/10.1016/j.compag.2018.08.001

17.  Shamshiri, R., Kalantari, F., Ting, K., Thorp, K. R., Hameed, I. A., Weltzien, C., Ahmad, D., & Shad, Z. M. (2018). Advances in greenhouse automation and controlled environment agriculture: A transition to plant factories and urban agriculture. International Journal of Agricultural and Biological Engineering, 11(1), 1–22. https://doi.org/10.25165/j.ijabe.20181101.3210

18.  Sharma, A., Kumar, V., & Longchamps, L. (2024). Comparative performance of YOLOv8, YOLOv9, YOLOv10, YOLOv11 and Faster R-CNN models for detection of multiple weed species. Smart Agricultural Technology, 9, 100648. https://doi.org/10.1016/j.atech.2024.100648

19.  Song, Y., Yang, L., Li, S., Yang, X., Ma, C., Huang, Y., & Hussain, A. (2024). Improved YOLOv8 model for phenotype detection of horticultural seedling growth based on digital cousin. Agriculture, 15(1), 28. https://doi.org/10.3390/agriculture15010028

20.  World Bank. (n.d.). Farming and agribusiness. World Bank Group. https://www.worldbank.org/ext/en/topic/farming-and-agribusiness

21.  Syed, T. N., Jizhan, L., Xin, Z., Shengyi, Z., Yan, Y., Mohamed, S. H. A., & Lakhiar, I. A. (2019). Seedling-lump integrated non-destructive monitoring for automatic transplanting with Intel RealSense depth camera. Artificial Intelligence in Agriculture, 3, 18–32. https://doi.org/10.1016/j.aiia.2019.09.001

22.  Tong, J., Jiang, H., & Zhou, W. (2012). Development of automatic system for the seedling transplanter based on machine vision technology. In Proceedings of the 2012 IEEE International Conference on Computer Science and Automation Engineering (CSAE) (Vol. 2, pp. 742–746). Zhangjiajie, China: IEEE. https://doi.org/10.1109/CSAE.2012.6272873

23.  Tong, J., Shi, H., Wu, C., Jiang, H., & Yang, T. (2018). Skewness correction and quality evaluation of plug seedling images based on Canny operator and Hough transform. Computers and Electronics in Agriculture, 155, 461–472. https://doi.org/10.1016/j.compag.2018.10.035

24.  Tripathi, A., Gohokar, V., & Kute, R. (2024). Comparative analysis of YOLOv8 and YOLOv9 models for real-time plant disease detection in hydroponics. Engineering, Technology & Applied Science Research, 14(5), 17269–17275. https://doi.org/10.48084/etasr.8301

25.  Vougioukas, S. (2019). Agricultural robotics. Annual Review of Control, Robotics, and Autonomous Systems, 2(1), 365–392. https://doi.org/10.1146/annurev-control-053018-023617

26.  Wang, A., Peng, T., Cao, H., Xu, Y., Wei, X., & Cui, B. (2022). TIA-YOLOv5: An improved YOLOv5 network for real-time detection of crop and weed in the field. Frontiers in Plant Science, 13, 1091655. https://doi.org/10.3389/fpls.2022.1091655

27.  Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7464–7475). Vancouver, BC, Canada: IEEE. https://doi.org/10.1109/CVPR52729.2023.00721

28.  Wang, Q., Hua, Y., Lou, Q., & Kan, X. (2025). SWMD-YOLO: A lightweight model for tomato detection in greenhouse environments. Agronomy, 15(7), 1593. https://doi.org/10.3390/agronomy15071593

29.  Wu, X., Dong, Z., Wang, C., Zhu, Z., Guo, Y., & Zheng, S. (2025). ESG-YOLO: An efficient object detection algorithm for transplant quality assessment of field-grown tomato seedlings based on YOLOv8n. Agronomy, 15(9), 2088. https://doi.org/10.3390/agronomy15092088