Monitoring of pea crops with neural network processing of images obtained using UAVs
https://doi.org/10.32634/0869-8155-2025-397-08-122-128
Abstract
The article is devoted to the development and testing of technology for recognizing pea sprouts and estimating its biomass based on images from UAVs using neural networks. Rocket peas were sown by the “Kuzbass” sowing complex in the Topkinsky district of the Kemerovo Region on an area of 21.55 hectares. The soil type is slightly leached chernozem. The predecessor is spring wheat. The seed depth is 6 cm, the seeding rate is 1.1 million seeds per 1 hectare. Aerial photography was performed three weeks later with a quadcopter with a 20MP camera resolution from a flight altitude of 3 m. The shooting was carried out in two stages — in the early morning in cloudy conditions to obtain images of pea shoots without shadows and in the daytime with shadows from sprouts and weeds. As a result, two sets of 120 source photos were generated to train the neural network. Based on the obtained datasets, the Ultralytics YOLOv8 neural network model was trained. Testing of the obtained models was performed in a Python program for batch image processing and counting the number of plants in each image. The accuracy of recognizing sprouts on the first dataset was 97.3%, on the second — 67.3%. This is due to the different shooting conditions. Combining the two datasets allowed for a recognition accuracy of 94.7%. This is slightly lower than the first option, but much closer to the actual conditions of aerial photography. The result of the work is a program that allows batch image processing for automatic counting of pea sprouts and calculating their area in the images.
About the Authors
D. E. Fedorov
Kuzbass State Agrarian University named after V.N.Poletskov
Russian Federation
Russian Federation
Dmitry Evgenievich Fedorov, Candidate of Technical Sciences
5 Markovtsev Str., Kemerovo, 650056
S. N. Bykov
Kuzbass State Agrarian University named after V.N.Poletskov
Russian Federation
Russian Federation
Sergey Nikolaevich Bykov, Candidate of Technical Sciences
5 Markovtsev Str., Kemerovo, 650056
References
1. Rogachev A.F., Melikhova E.V., Belousov I.S. Research of development and productivity of agricultural crops using unmanned aerial vehicles. Proceedings of Nizhnevolzskiy agrouniversity complex: science and higher vocational education. 2019; (4): 329–339 (in Russian). https://www.elibrary.ru/vqaviv
2. Cheshkova A.F. A review of hyperspectral image analysis techniques for plant disease detection and identification. Vavilov Journal of Genetics and Breeding. 2022; 26(2): 202–213. https://doi.org/10.18699/VJGB-22-25
3. Rogachev A.F., Belousov I.S. Neural network identification of problem areas of the state of crops by methods of artificial intelligence. Proceedings of Nizhnevolzskiy agrouniversity complex: science and higher vocational education. 2022; (3): 459–466 (in Russian). https://www.elibrary.ru/bjmzny
4. Mudarisov S.G., Miftahov I.R. Automatic detection and identification of wheat diseases using deep learning and real-time drones. Vestnik of Kazan State Agrarian University. 2024; 19(2): 90–104 (in Russian). https://doi.org/10.12737/2073-0462-2024-90-104
5. Kutyrev A.I., Filippov R.A. Recognition of generative parts of Fragaria × ananassa using convolutional neural network (CNN). Taurida Herald of the Agrarian Sciences. 2023; (2): 72–86 (in Russian). https://doi.org/10.5281/zenodo.8271986
6. Demidchik V.V. et al. Plant Phenomics: Fundamental Bases, Software and Hardware Platforms, and Machine Learning. Russian Journal of Plant Physiology. 2020; 67(3): 397–412. https://doi.org/10.1134/S1021443720030061
7. Molin A.E., Blekanov I.S., Mitrofanov E.P., Mitrofanova O.A. Synthetic data generation methods for training neural networks in the task of segmenting the level of crop nitrogen status on UAV images of agricultural fields. Vestnik of Saint Petersburg University. Applied Mathematics. Computer Science. Control Processes. 2024; 20(1): 20–33 (in Russian). https://doi.org/10.21638/11701/spbu10.2024.103
8. Semenyuk V.S., Nikitin E.A. System Development for Liquid Chemicals Point Injection Based on Convolutional Neural Network Models. Agricultural Machinery and Technologies. 2021; 15(2): 41–45 (in Russian). https://doi.org/10.22314/2073-7599-2021-15-1-41-45
9. Cini E., Marzialetti F., Paterni M., Berton A., Acosta A.T.R., Ciccarelli D. Integrating UAV imagery and machine learning via Geographic Object Based Image Analysis (GEOBIA) for enhanced monitoring of Yucca gloriosa in Mediterranean coastal dunes. Ocean & Coastal Management. 2024; 258: 107377. https://doi.org/10.1016/j.ocecoaman.2024.107377
10. Marzialetti F., Frate L., De Simone W., Frattaroli A.R., Acosta A.T.R., Carranza M.L. Unmanned Aerial Vehicle (UAV)-Based Mapping of Acacia saligna Invasion in the Mediterranean Coast. Remote Sensing. 2021; 13(17): 3361. https://doi.org/10.3390/rs13173361
11. Costa L.S. et al. Woody Plant Encroachment in a Seasonal Tropical Savanna: Lessons about Classifiers and Accuracy from UAV Images. Remote Sensing. 2023; 15(9): 2342. https://doi.org/10.3390/rs15092342
12. Prasad A., Mehta N., Horak M., Bae W.D. A Two-Step Machine Learning Approach for Crop Disease Detection Using GAN and UAV Technology. Remote Sensing. 2022; 14(19): 4765. https://doi.org/10.3390/rs14194765
13. Zhang J. et al. Multispectral Drone Imagery and SRGAN for Rapid Phenotypic Mapping of Individual Chinese Cabbage Plants. Plant Phenomics. 2022; 2022: 0007. https://doi.org/10.34133/plantphenomics.0007
14. Parasich A., Parasich V., Parasich I. Training set formation in machine learning problems. Survey. Information and Control Systems. 2021; (4): 61–70 (in Russian). https://doi.org/10.31799/1684-8853-2021-4-61-70
15. Braginsky M.Ya., Tarakanov D.V. Plant phenotyping by an adaptive image processing system based on convolutional neural networks. Proceedings in Cybernetics. 2021; (2): 6–16 (in Russian). https://doi.org/10.34822/1999-7604-2021-2-6-16
16. Rogachev A.F., Melikhova E.V. Multi-class recognition of aerial images of agricultural fields. Proceedings of Nizhnevolzskiy agrouniversity complex: science and higher vocational education. 2020; (3): 142–152 (in Russian). https://doi.org/10.32786/2071-9485-2020-03-14
Review
For citations:
Fedorov D.E., Bykov S.N. Monitoring of pea crops with neural network processing of images obtained using UAVs. Agrarian science. 2025;(8):122-128. (In Russ.) https://doi.org/10.32634/0869-8155-2025-397-08-122-128
Views:
15
Email this article 