An Intelligent Corn Disease Detection System for Integration into Mechanized Crop Protection Systems

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription Access

Abstract

An urgent research challenge is the development of automated methods for monitoring maize diseases using computer vision and unmanned aerial vehicles (UAVs). Traditional visual inspection by agronomists is laborintensive and inefficient for detecting early infection stages, leading to significant yield losses. The aim of this study is to develop and validate a method for detecting maize leaf spot from UAV-acquired RGB images using a convolutional neural network (CNN) ResNet-50. The study object was maize fields in the Republic of Bashkortostan. Imaging was performed with an industrial UAV DJI Matrice 300 equipped with a 20 MP RGB camera. A dataset of ~14,000 images was collected, including 6000 healthy and 8000 diseased leaves. ResNet-50 with fine-tuning was used for binary classification. Model performance was evaluated using Accuracy, Precision, Recall, and F1-score. The model achieved an overall Accuracy of ≈92 % and F1-score of 0.91, reliably distinguishing healthy and infected leaves under field conditions. Based on the infection index I , Variable Rate Application (VRA) maps were generated, prescribing fungicide application rates of 120, 180, andd 250 L/haacross field zones. Unlike most studies limited to classification, the proposed approach is integrated into the agro-engineering framework of precision agriculture, CNN outputs are converted into ISOXML/Shape prescription maps compatible with ISOBUS/ RTK sprayers. The practical significance lies in reducing pesticide costs and chemical load on agroecosystems while maintaining crop protection efficiency. Future work will focus on extending detection to multiple diseases and incorporating multispectral data.

About the authors

S. G. Mudarisov

Bashkir State Agrarian University

Email: bgau@ufanet.ru
Doctor of Technical Sciences 450001, Ufa, ul. 50-letiya Oktyabrya, 34

I. R. Miftakhov

Bashkir State Agrarian University

Email: bgau@ufanet.ru
Candidate of Technical Sciences 450001, Ufa, ul. 50-letiya Oktyabrya, 34

I. M. Farkhutdinov

Bashkir State Agrarian University

Email: bgau@ufanet.ru
Doctor of Technical Sciences 450001, Ufa, ul. 50-letiya Oktyabrya, 34

References

  1. A Review on UAV-Based Applications for Plant Disease Detection and Monitoring / L. Kouadio, M. El Jarroudi, Z. Belabess, et al. // Remote Sensing. 2023. Vol. 15. Article 4273. URL: https://www.mdpi.com/2072-4292/15/17/4273 (дата обращения: 20.09.2025). doi: 10.3390/rs15174273.
  2. DFCANet: A Novel Lightweight Convolutional Neural Network Model for Corn Disease Identification / Ya. Chen, X. Chen, J. Lin, et al. // Agriculture. 2022. Vol. 12. No. 12. P. 2047. doi: 10.3390/agriculture12122047.
  3. Assessment of Map-Based Variable Rate Strategies for Copper Reduction in Hedge Vineyards / F. Garcia-Ruiz, Ja. Campos, J. Llop-Casamada, et al. // Computers and Electronics in Agriculture. 2023. Vol. 207. Article 107753. URL: https://www.sciencedirect.com/science/article/pii/S0168169923001412 (дата обращения: 20.09.2025). doi: 10.1016/j.compag.2023.107753.
  4. ICS-ResNet: A Lightweight Network for Maize Leaf Disease Classification / Zh. Ji, Sh. Bao, M. Chen, et al. // Agronomy. 2024. Vol. 14. Article 1587. URL: https://www.mdpi.com/2073-4395/14/7/1587 (дата обращения: 20.09.2025). doi: 10.3390/agronomy14071587.
  5. Kamilaris A., Prenafeta-Boldú F. X. Deep learning in agriculture: A survey // Computers and Electronics in Agriculture. 2018. Vol. 147. P. 70–90. doi: 10.1016/j.compag.2018.02.016.
  6. Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification / S. Sladojevic, M. Arsenovic, A. Anderla, et al. // Computational Intelligence and Neuroscience. 2016. Vol. 2016. Article 3289801. URL: https://www.hindawi.com/journals/cin/2016/3289801 (дата обращения: 20.09.2025). doi: 10.1155/2016/3289801.
  7. Quantitative Phenotyping of Northern Leaf Blight in UAV Images Using Deep Learning / E. L. Stewart, T. Wiesner-Hanks, N. Kaczmar, et al. // Remote Sensing. 2019. Vol. 11. Article 2209. URL: https://www.mdpi.com/2072-4292/11/19/2209 (дата обращения: 20.09.2025). doi: 10.3390/rs11192209.
  8. Millimeter-Level Plant Disease Detection from Aerial Photographs via Deep Learning and Crowdsourced Data / T. Wiesner-Hanks, H. Wu, E. L. Stewart, et al. // Frontiers in Plant Science. 2019. Vol. 10. Article 1550. URL: https://www.frontiersin.org/articles/10.3389/fpls.2019.01550/full (дата обращения: 20.09.2025). doi: 10.3389/fpls.2019.01550.
  9. Application of Conventional UAV-Based High-Throughput Object Detection to the Early Diagnosis of Pine Wilt Disease by Deep Learning / B. Wu, A. Liang, H. Zhang, et al. // Forest Ecology and Management. 2021. Vol. 486. Article 118986. URL: https://www.sciencedirect.com/science/article/abs/pii/S037811272100075X (дата обращения: 20.09.2025). doi: 10.1016/j.foreco.2021.118986.
  10. Cucumber leaf disease identification with global pooling dilated convolutional neural network / S. Zhang, S. Zhang, C. Zhang, et al. // Computers and Electronics in Agriculture. 2019. Vol. 162. P. 422–430. doi: 10.1016/j.compag.2019.04.037.
  11. Advanced Deep Learning Models for Corn Leaf Disease Classification: A Field Study in Bangladesh / S. N. Mohanty, H. Ghosh, I. S. Rahat, et al. // Engineering Proceedings. 2023. Vol. 59. Article 69. URL: https://www.mdpi.com/2673-4591/59/1/69 (дата обращения: 20.09.2025). doi: 10.3390/engproc2023059069.
  12. Comparison of the Effectiveness of GIS-Based Interpolation Methods for Estimating the Spatial Distribution of Agrochemical Soil Properties / R. Abdulmanov, I. Miftakhov, M. Ishbulatov, et al. // Environmental Technology & Innovation. 2021. Vol. 23. Article 101137. URL: https://www.sciencedirect.com/science/article/abs/pii/S2352186421006180?via%3Dihub (дата обращения: 20.09.2025). doi: 10.1016/j.eti.2021.101137.
  13. Hyperspectral image analysis techniques for the detection and classification of the early onset of plant disease and stress / A. Lowe, N. Harrison, A. P. French, et al. // Plant Methods. 2017. Vol. 13. Article 80. URL: https://plantmethods.biomedcentral.com/articles/10.1186/s13007-017-0233-z (дата обращения: 20.09.2025). doi: 10.1186/s13007-017-0233-z.
  14. Ценч Ю. С., Курбанов Р. К., Захарова Н. И. Развитие систем управления полетом и средств аэрофотосъемки беспилотных воздушных судов сельскохозяйственного назначения // Сельскохозяйственные машины и технологии. 2024. Т. 18. № 2. С. 11–19.
  15. Ценч Ю. С., Захарова Н. И. Тенденции развития технических средств аэрофотосъемки сельскохозяйственных земель // Сельскохозяйственные машины и технологии. 2023. Т. 17. № 3. С. 16–26.
  16. Технические системы цифрового контроля качества обработки почвы / С. И. Старовойтов, Ю. С. Ценч, В. М. Коротченя и др. // Сельскохозяйственные машины и технологии. 2020. Т. 14. № 1. С. 16–21.
  17. Мударисов С. Г., Мифтахов И. Р. Автоматическое обнаружение и идентификация болезней пшеницы с использованием методов глубокого обучения и применением дронов в режиме реального времени // Вестник Казанского государственного аграрного университета. 2024. Т. 19. № 2(74). С. 90–104. doi: 10.12737/2073-0462-2024-90-104.
  18. Detection and classification of corn leaf diseases using ResNet-18 / D. R. Oli, M. Dahal, S. Pokhrel, et al. // International Journal on Engineering Technology. 2025. Vol. 11. No. 1. P. 33–41. doi: 10.3126/injet.v11i1.78606.
  19. ImageNet Large Scale Visual Recognition Challenge / O. Russakovsky, J. Deng, H. Su, et al. // International Journal of Computer Vision. 2015. Vol. 115. P. 211–252. doi: 10.1007/s11263-015-0816-y.
  20. Development and evaluation of an affordable variable rate applicator controller for precision agriculture / A. Abdalla, A. M. Nafchi // AgriEngineering. 2024. Vol. 6. No. 4. P. 4639–4657. doi: 10.3390/agriengineering6040027.
  21. Mapping the Variable-Rate Application (VRA) of Precision Fertilizing for Soybean / M. Mawardi, P. H. T. Nugraheni, L. Sutiarso, et al. // Journal of Advanced Research in Applied Mechanics. 2018. Vol. 51. No. 1. P. 1–9. URL: https://www.akademiabaru.com/submit/index.php/aram/article/view/1825 (дата обращения: 20.09.2025).

Supplementary files

Supplementary Files
Action
1. JATS XML

Copyright (c) 2025 Russian Academy of Sciences

Согласие на обработку персональных данных

 

Используя сайт https://journals.rcsi.science, я (далее – «Пользователь» или «Субъект персональных данных») даю согласие на обработку персональных данных на этом сайте (текст Согласия) и на обработку персональных данных с помощью сервиса «Яндекс.Метрика» (текст Согласия).