Logo PTI Logo FedCSIS

Position Papers of the 20th Conference on Computer Science and Intelligence Systems

Annals of Computer Science and Information Systems, Volume 44

Detection and Classification of Rumex Weeds in Grasslands Using YOLOv11

,

DOI: http://dx.doi.org/10.15439/2025F9629

Citation: Position Papers of the 20th Conference on Computer Science and Intelligence Systems, M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 44, pages 119–129 ()

Full text

Abstract. This paper explores the use of YOLOv11 and BoTSORT for detecting and tracking Rumex obtusifolius and Rumex crispus in grasslands. Two models were developed: Model A trained on the RumexWeeds dataset, and Model B, trained using transfer learning with additional datasets. While Model A performed well on its training data, it struggled in unseen environments. Model B showed improved generalisation, achieving higher performance across diverse conditions and successfully detecting Rumex longifolius in Norwegian grasslands. Both models were integrated with BoT-SORT and achieved high tracking metrics, supporting GPS-based mapping. Real-time field testing confirmed feasibility, although detection was affected by shadows, terrain, and camera placement. The results highlight the importance of diverse training data for robust weed detection. Future work should focus on expanding datasets, tuning hyperparameters, and improving hardware for reliable real-world deployment.

References

  1. A. Van Bruggen, M. He, K. Shin, V. Mai, K. Jeong, M. Finckh, and J. Morris, “Environmental and health effects of the herbicide glyphosate,” Science of The Total Environment, vol. 616-617, pp. 255–268, 2018. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0048969717330279
  2. A. Klik and J. Rosner, “Long-term experience with conservation tillage practices in austria: Impacts on soil erosion processes,” Soil and Tillage Research, vol. 203, p. 104669, 2020. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0167198720304517
  3. J. Wesseler, “The eu’s farm-to-fork strategy: An assessment from the perspective of agricultural economics,” Applied Economic Perspectives and Policy, vol. 44, no. 4, pp. 1826–1843, 2022. [Online]. Available: https://onlinelibrary.wiley.com/doi/abs/10.1002/aepp.13239
  4. S. Hejduk and P. Dolezal, “Nutritive value of broad-leaved dock (rumex obtusifolius l.) and its effect on the quality of grass silages,” Czech Journal of Animal Science, vol. 49, no. 4, pp. 144–150, 2004. [Online]. Available: https://cjas.agriculturejournals.cz/artkey/cjs-200404-0003.php
  5. P. E. Hatcher, L. O. Brandsaeter, G. Davies, A. Lüscher, H. L. Hinz, R. Eschen, and U. Schaffner, “Biological control of rumex species in europe: opportunities and constraints.” CABI, p. 470–475, 2008. [Online]. Available: https://doi.org/10.1079/9781845935061.0470
  6. J. Zhang, F. Yu, Q. Zhang, M. Wang, J. Yu, and Y. Tan, “Advancements of uav and deep learning technologies for weed management in farmland,” Agronomy, vol. 14, no. 3, 2024. [Online]. Available: https://www.mdpi.com/2073-4395/14/3/494
  7. J. Zhao, T. W. Berge, and J. Geipel, “Transformer in uav image-based weed mapping,” Remote Sensing, vol. 15, no. 21, 2023. [Online]. Available: https://www.mdpi.com/2072-4292/15/21/5165
  8. E. C. Tetila, B. L. Moro, G. Astolfi, A. B. da Costa, W. P. Amorim, N. A. de Souza Belete, H. Pistori, and J. G. A. Barbedo, “Real-time detection of weeds by species in soybean using uav images,” Crop Protection, vol. 184, p. 106846, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0261219424002746
  9. P. Wang, Y. Tang, F. Luo, L. Wang, C. Li, Q. Niu, and H. Li, “Weed25: A deep learning dataset for weed identification,” Frontiers in Plant Science, vol. Volume 13 - 2022, 2022. [Online]. Available: https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.1053329
  10. Y. Mu, R. Feng, R. Ni, J. Li, T. Luo, T. Liu, X. Li, H. Gong, Y. Guo, Y. Sun, Y. Bao, S. Li, Y. Wang, and T. Hu, “A faster r-cnn-based model for the identification of weed seedling,” Agronomy, vol. 12, no. 11, 2022. [Online]. Available: https://www.mdpi.com/2073-4395/12/11/2867
  11. T. W. Berge, T. Torp, F. Urdal, and M. Vallestad, “Sensor technology for precision weeding in cereals: Evaluation of a novel convolutional neural network to estimate weed cover, crop cover and soil cover in near-ground red-green-blue images,” Norwegian Institute of Bioeconomy Research (NIBIO), Ås, Norway, NIBIO Report 8(134), 2022. [Online]. Available: https://nibio.brage.unit.no/nibio-xmlui/handle/11250/3031834
  12. T. Jin, K. Liang, M. Lu, Y. Zhao, and Y. Xu, “Weedssort: A weed tracking-by-detection framework for laser weeding applications within precision agriculture,” Smart Agricultural Technology, vol. 11, p. 100883, 2025. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2772375525001169
  13. T. Utstumo, F. Urdal, A. Brevik, J. Dørum, J. Netland, Overskeid, T. Berge, and J. Gravdahl, “Robotic in-row weed control in vegetables,” Computers and Electronics in Agriculture, vol. 154, pp. 36–45, 11 2018.
  14. Kilter Systems, “Kilter systems – ai-powered agricultural robotics,” 2024, accessed: 14 April 2025. [Online]. Available: https://www.kiltersystems.com
  15. T. Anken and A. Latsch, “Characteristics of a spot sprayer for the treatment of rumex obtusifolius in meadows,” agricultural engineering.eu, vol. 78, no. 3, 2023. [Online]. Available: https://www.agricultural-engineering.eu/landtechnik/article/view/3295
  16. J. Valente, S. Hiremath, M. Ariza-Sentís, M. Doldersum, and L. Kooistra, “Mapping of rumex obtusifolius in nature conservation areas using very high resolution uav imagery and deep learning,” International Journal of Applied Earth Observation and Geoinformation, vol. 112, p. 102864, 2022. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1569843222000668
  17. R. Güldenring, F. K. van Evert, and L. Nalpantidis, “Rumexweeds: A grassland dataset for agricultural robotics,” Journal of Field Robotics, vol. 40, no. 6, pp. 1639–1656, 2023.
  18. “Susdock: Sustainable control and mapping of dock plants,” https://www.ri.se/en/susdock, accessed: 2025-04-22.
  19. Python Software Foundation, Python Language Reference, version 3.9.21, 2023. [Online]. Available: https://docs.python.org/3.9/
  20. S. L. Madsen, S. K. Mathiassen, M. Dyrmann, M. S. Laursen, L.-C. Paz, and R. N. Jørgensen, “Open Plant Phenotype Database of Common Weeds in Denmark,” Remote Sensing, vol. 12, no. 8, p. 1246, Apr. 2020. [Online]. Available: https://www.mdpi.com/691100
  21. A. Milan, L. Leal-Taixe, I. Reid, S. Roth, and K. Schindler, “Mot16: A benchmark for multi-object tracking,” 2016. [Online]. Available: https://arxiv.org/abs/1603.00831
  22. R. Khanam and M. Hussain, “Yolov11: An overview of the key architectural enhancements,” 2024. [Online]. Available: https://arxiv.org/abs/2410.17725
  23. C. Heindl, Toka, and J. Valmadre, “py-motmetrics: Python implementation of metrics for multiple object tracking,” https://github.com/cheind/py-motmetrics, 2024, accessed: 2025-03-21.