Russian Federation
Russian Federation
UDC 631.67
UDC 004.9
The relevance of the study is due to the need to create an intelligent system for monitoring the state of crops during the growing season on significant areas. The scientific problem of operational monitoring of the state of crops with subsequent recognition of their condition from color images obtained from unmanned aerial vehicles (UAVs) can be solved by means of neural network algorithms of deep learning that provide analysis and processing of graphical information. As part of the computer implementation of a recurrent neural network with convolutional layers, the authors have formed a dataset of color images of crops obtained using UAVs. In order to solve the problem of class imbalance of the resulting dataset, its augmentation was carried out by artificially adding new images obtained on the basis of existing ones. For the training of a recurrent neural network implemented in Python, including convolutional layers, training and test samples were formed, with the marking of images in four classes: healthy vegetation ("healthy"), affected vegetation ("affected"), soil, unseeded field ("soil") and other objects ("other"). The recognition results obtained in the course of the study can be used to create hybrid architectures with subsequent software implementation of a complex of neural network models that allow identifying patterns of growth and development of various groups of crops.
multiclass recognition, artificial intelligence, phytoagrocenosis, productivity, convolutional neural networks
1. Kamilaris, A., Prenafeta-Boldú, F.X. (2018). Deep Learning in Agriculture: A survey. Computers and Electronics in Agriculture. Available at: www.arxiv.org/pdf/1807.11809
2. Neetu and Ray, S.S. (2019). Exploring machine learning classification algorithms for crop classification using Sentinel 2 data. ISPRS – International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XLII-3/W6. Available at: www.int-arch-photogramm-remote-sens-spatial-infsci.net/XLII-3-W6/573/2019/isprs-archives-XLII-3-W6-573-2019.pdf
3. Liakos, K.G., Busato, P., Moshou, D., Pearson, S., Bochits, D. (2018). Machine Learning in Agriculture: A Review. Sensors (Special Issue "Sensors in Agriculture 2018"). Available at: www.mdpi.com/1424- 8220/18/8/2674/pdf
4. Kitonsa, H., Kruglikov, S.V. (2018). Significance of drone technology for achievement of the united nations sustainable development goals. R-Economy, vol. 4, no. 3, pp. 115-120.
5. Gudfellou Ya., Bendzhio I., Kurvill' A. Glubokoe obuchenie. M.: DMK Press, 2018. 652 s.
6. Cheng, G., Wang, G., Han J. (2022). IS Net: Towards Improving Separability for Remote Sensing Image Change Detection. In IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-11. Art no. 5623811. doi:https://doi.org/10.1109/TGRS.2022.3174276
7. Dubenok N.N., Borodychev V.V., Lytov M.N. Algoritm ucheta prostranstvennoy neodnorodnosti ishodnyh harakteristik oroshaemogo uchastka na osnove GIS-tehnologiy // Rossiyskaya sel'skohozyaystvennaya nauka. 2019. № 1. S. 66-70.
8. Mihaylenko I.M. i dr. Upravlenie agrotehnologiyami i robotizirovannye sredstva realizacii // Innovacii v sel'skom hozyaystve. 2019. № 1 (30). S. 242-258.
9. Rogachev A.F., Melihova E.V., Belousov I.S. Issledovanie razvitiya i produktivnosti sel'skohozyaystvennyh kul'tur s primeneniem bespilotnyh letatel'nyh apparatov // Izvestiya Nizhnevolzhskogo agrouniversitetskogo kompleksa. 2020. № 3 (59). S. 397-406. doi:https://doi.org/10.32786/2071-9485-2019-04-49
10. Asadullaev R.G., Kuz'menko N.I. Tehnologiya intellektual'nogo raspoznavaniya sel'skohozyaystvennyh kul'tur neyronnoy set'yu po mul'tispektral'nym mnogovremennym dannym distancionnogo zondirovaniya Zemli // Ekonomika. Informatika. 2022. № 49 (1). S. 159-168. doi:https://doi.org/10.52575/2687-0932-2022-49-1-159-168
11. Tokarev, K. et al. (2023). Monitoring and Intelligent Management of Agrophytocenosis Productivity Based on Deep Neural Network Algorithms. In: Vasant, P., Weber, GW., Marmolejo-Saucedo, J.A., Munapo, E., Thomas, J.J. (eds) Intelligent Computing & Optimization. ICO 2022. Lecture Notes in Networks and Systems, vol. 569. Springer, Cham. doi:https://doi.org/10.1007/978-3-031-19958-5_65
12. Tokarev K.E., Rudenko A.Yu., Kuz'min V.A., Chernyavskiy A.N. Teoriya i cifrovye tehnologii intellektual'noy podderzhki prinyatiya resheniy dlya uvelicheniya bioproduktivnosti agroekosistem na osnove neyrosetevyh modeley // Izvestiya Nizhnevolzhskogo agrouniversitetskogo kompleksa. 2021. № 4 (64). S. 421- 440. doi:https://doi.org/10.32786/2071-9485-2021-04-42
13. Tokarev K.E., Lebed' N.I., Kuz'min V.A., Chernyavskiy A.N. Teoriya i tehnologii upravleniya orosheniem sel'skohozyaystvennyh kul'tur na osnove informacionnyh tehnologiy podderzhki prinyatiya resheniy i matematicheskogo modelirovaniya // Izvestiya Nizhnevolzhskogo agrouniversitetskogo kompleksa. 2020. № 4 (60). S. 433-448. doi:https://doi.org/10.32786/2071-9485-2020-04-41
14. Lebed' N.I., Tokarev K.E. Povyshenie produktivnosti agrofitocenozov v usloviyah tochnogo zemledeliya s ispol'zovaniem neyrosetevyh algoritmov glubokogo obucheniya: obosnovanie primeneniya i aspekty komp'yuternoy realizacii // Mezhdunarodnyy sel'skohozyaystvennyy zhurnal. 2022. № 6 (390). S. 662-664. doi:https://doi.org/10.55186/25876740_2022_65_6_662
