(50-4) 09 * << * >> * Russian * English * Content * All Issues

Development of a machine-learning algorithm for the automatic determination of the number of missing potato plants from UAV imagery
D.A. Poleshchenko1, I.S. Mikhailov1

1Stary Oskol Technological Institute n.a. A.A. Ugarov (branch) National University of Science and Technology MISIS, 309516, Stary Oskol, Russia, Makarenko Microdistrict 42

  Full text (PDF)

DOI: 10.18287/COJ1875

Article ID: 1875

Language: Russian

Abstract:
This paper presents a method for automatic identification of potato rows and detection of missing plants from UAV aerial imagery. The approach combines plant segmentation using YOLOv11 models, adaptive morphological filtering that accounts for spatial resolution, and automatic correction of row orientation. Experimental evaluation on field data demonstrated high row extraction accuracy (97.4 %) and effective gap detection (F1-score 0.91). The obtained results confirm the correct identification of crop structure, justifying the applicability of the approach for decision support in digital agriculture.

Keywords:
crop monitoring, potato, plant segmentation, orthomosaic, YOLOv11, Ground Sample Distance, remote sensing, UAV.

Citation:
Poleshchenko DA, Mikhailov IS. Development of a machine-learning algorithm for the automatic determination of the number of missing potato plants from UAV imagery. Computer Optics 2026; 50(4): 1875. doi: 10.18287/COJ1875.

References:

  1. Zualkernan I, Abuhani DA, Hussain MH, Khan J, ElMohandes M. Machine learning for precision agriculture using imagery from unmanned aerial vehicles (UAVs): a survey. Drones 2023; 7(6): 382. doi:10.3390/drones7060382.
  2. Li G, Le F, Si S, Cui L, Xue X. Image segmentation-based oilseed rape row detection for infield navigation of agri-robot. Agronomy 2024; 14(9): 1886. doi:10.3390/agronomy14091886.
  3. Ronchetti G, Mayer A, Facchi A, Ortuani B, Sona G. Crop row detection through UAV surveys to optimize on-farm irrigation management. Remote Sens 2020; 12(12): 1967. doi:10.3390/rs12121967.
  4. Deng G, Zhou F, Dong H, Xu Z, Li Y. Accurate sugarcane detection and row fitting using SugarRow-YOLO and clustering-based spline methods for autonomous agricultural operations. Appl Sci 2025; 15(14): 7789. doi:10.3390/app15147789.
  5. Khan MN, Rahi A, Rajendran VP, Al Hasan M, Anwar S. Real-time crop row detection using computer vision: application in agricultural robots. Front Artif Intell 2024; 7: 1435686. doi:10.3389/frai.2024.1435686.
  6. Ferreira R, Lima AM, da Silva DL, Arias-Garcia J, Yudi J, Hernandes AC. Data labelling and heuristics to estimate sugarcane rows orientation for UAV-aided precision agriculture. Smart Agric Technol 2025; 10: 101425. doi:10.1016/j.atech.2025.101425.
  7. Chen P, Ma X, Wang F, Li J. New method for crop row detection using unmanned aerial vehicle images. Remote Sens 2021; 13(17): 3526. doi:10.3390/rs13173526.
  8. Mhango JK, Harris EW, Green R, Monaghan JM. Mapping potato plant density variation using aerial imagery and deep learning techniques for precision agriculture. Remote Sens 2021; 13(14): 2705. doi:10.3390/rs13142705.
  9. Gao J, Tan F, Cui J, Hou Z. Unmanned aerial vehicle image detection of maize-YOLOv8n seedling leakage. Front Plant Sci 2025; 16: 1569229. doi:10.3389/fpls.2025.1569229.
  10. de Souza FLP, Dias MA, Setiyono TD, Campos S, Shiratsuchi LS, Tao H. Identification of soybean planting gaps using machine learning. Smart Agric Technol 2025; 10: 100779. doi:10.1016/j.atech.2025.100779.
  11. Rocha BM, da Fonseca AU, Pedrini H, Soares F. Automatic detection and evaluation of sugarcane planting rows in aerial images. Inf Process Agric 2023; 10(3): 400-415. doi:10.1016/j.inpa.2022.04.003.
  12. Roboflow - platform for computer vision datasets and models. Available at: https://roboflow.com/.
  13. Khanam R, Hussain M. YOLOv11: an overview of the key architectural enhancements. arXiv 2024; arXiv:2410.17725. Available at: https://arxiv.org/abs/2410.17725.
  14. Pestunov IA, Kalashnikov RA, Ovcharova NV, Bayramov RR. Otsenka polevoy vskhozhesti kukuruzy po RGB-izobrazheniyam s BPLA s ispolzovaniem metodov mashinnogo obucheniya [Field emergence assessment of maize using UAV RGB imagery and machine learning methods, in Russian]. In: Regionalnye problemy distantsionnogo zondirovaniya Zemli: materialy XI Mezhdunarodnoy nauchnoy konferentsii; 2024; Krasnoyarsk, Russia. Krasnoyarsk: Sibirsky federalny universitet; 2024. pp. 334-339.
  15. Abdi H, Williams LJ. Principal component analysis. Wiley Interdiscip Rev Comput Stat 2010; 2(4): 433-459. doi:10.1002/wics.101.
  16. Alt VV, Pestunov IA, Melnikov PV, Yolkin OV. Avtomatizirovannoe obnaruzhenie sornyakov i otsenka kachestva vskhodov selskokhozyaystvennykh kultur po RGB-izobrazheniyam [Automated weed detection and assessment of crop emergence quality from RGB images, in Russian]. Sib Vestn Selskokhozyaystvennoy Nauki 2019; 48(5): 52-60. doi:10.26898/0370-8799-2018-5-7.
  17. Schubert E, Sander J, Ester M, Kriegel HP, Xu X. DBSCAN revisited, revisited: why and how you should (still) use DBSCAN. ACM Trans Database Syst 2017; 42(3): 19. doi:10.1145/3068335.
  18. Akyon FC, Altinuc SO, Temizel A. Slicing aided hyper inference and fine-tuning for small object detection. In: Proc 2022 IEEE Int Conf Image Process (ICIP); 2022. pp. 966-970. doi:10.1109/ICIP46576.2022.9897990.

151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20