V.A. Nenashev1, R.M. Voronov2, A.V. Berezin3, A.D. Matveev4, V.K. Losev5

1–5 St. Petersburg State University of Aerospace Instrumentation (St. Petersburg, Russia)

1 nenashev.va@yandex.ru

In modern agriculture, there is a need for efficient methods of monitoring and controlling the condition of agricultural objects. This requires the development of technologies capable of automatically recognizing and counting these objects based on data obtained from small unmanned aerial vehicles. Aim is to develop and implement a method for automatic recognition and counting of agricultural objects based on processing a stream of frames captured by a small unmanned aerial vehicle, in order to improve the efficiency of monitoring and managing agricultural resources. Results. A system has been developed that uses computer vision methods to analyze the video stream and demonstrates high accuracy in recognizing and counting haystacks in the captured frames. Experimental results confirm the effectiveness of the proposed approach. Practical Significance. The developed system has significant practical value for agriculture by automating the process of monitoring and controlling the condition of agricultural objects. This can lead to improved land resource utilization efficiency and reduced manual labor costs.

Nenashev V.A., Voronov R.M., Berezin A.V., Matveev A.D., Losev V.K. Artificial intelligence methods in information‑measuring and control systems. Information-measuring and Control Systems. 2024. V. 22. № 4. P. 85−90. DOI: https://doi.org/10.18127/j20700814 -202404-10 (in Russian)

1. Otmakhova Yu.S., Devyatkin D.A., Usenko N.I. Analiz tsifrovykh tekhnologii v agroprodovolstvennoi sfere s ispolzovaniem metodov obrabotki bolshikh dannykh. Informatsionnoe obshchestvo. 2021. № 4−5. S. 334−344. (in Russian)
2. Otmakhova Yu.S., Kreskin A.D., Devyatkin D.A., Tikhomirov I.A. Analiz nauchnogo i patentnogo landshaftov v sfere sovremennykh tekhnologii glubokoi pererabotki zerna //Innovatsii. 2020. 2 (256). S. 89. (in Russian)
3. Hongkun, Tian, Tianhai Wang, Yadong Liu, Xi Qiao, Yanzhou Li. Computer vision technology in agricultural automation. Information Processing in Agriculture. 2020. V. 7. iss. 1. P. 1−19.
4. Nenashev V.A., Shepeta A.P., Kryachko A.F. Fusion radar and optical information in multiposition on-board location systems. 2020 Wave Electronics and its Application in Information and Telecommunication Systems. WECONF 2020. Saint-Petersburg. 01−05 June 2020. P. 9131451.
5. Nenashev V.A., Khanykov I.G. Formation of fused images of the land surface from radar and optical images in spatially distributed on-board operational monitoring systems. Journal of Imaging. 2021. V. 7. № 12.
6. URL: Seno. Bolshaya rossiiskaya entsiklopediya (bigenc.ru) (data obrashcheniya 03.05.2024). (in Russian)
7. URL: Ultralytics | Revolyutsiya v mire iskusstvennogo intellekta dlya zreniya (data obrashcheniya 03.05.2024). (in Russian)
8. URL: https://roboflow.github.io/roboflow-python (data obrashcheniya 03.05.2024).
9. Peiyuan Jiang, Daji Ergu, Fangyao Liu, Ying Cai, Bo Ma. A review of yolo algorithm developments. Procedia Computer Science. 199:1066−1073. 2022. (data obrashcheniya: 23.03.2023).
10. Jocher G., Chaurasia A., Qiu J. (2023). YOLO by Ultralytics (Version 8.0.0) Rezhim dostupa. URL: https://github.com/ultralytics /ultralytics (data obrashcheniya: 27.03.2023).