In the field conditions, in a set of technical experiments on industrial grain crops, the optical camera system along with a positioning system was tested on ground carrier to assess the contamination of crops by weed plants. To choose optimum parameters of photography that ensure reliable determination of the presence and location of weeds in crops, photography scenarios were implemented at different velocities of the unit and at different camera mount angles. The necessary resolution and quality of photo images was achieved with the camera mount angle values set to 30–45о, the unit movement velocity was 13–15 km/h and the filming frequency was 4 frames per second. The presence of weeds was visually determined with high reliability in the obtained images of the crops. The images with the achieved characteristics (quality and resolution) make feasible the further recognition of target objects in automatic mode based on the developed technologies with artificial intelligence usage.

Belyaev Vladimir I., Zhelezova Sofya V., Kuznetsov Vasilii N., Stepanova Evgeniya V., Prokopchuk Roman E.

1. Belyaev V. I., Volnov V. V., Sokolova L. V. Pryamoi posev zernovykh kul'tur v Altaiskom krae: sovershenstvovanie agrotekhnologii, sistemy mashin i obosnovanie ratsional'nykh parametrov [Direct sowing of grain crops in the Altai region: improvement of agricultural technologies, machine systems and substantiation of rational parameters], Barnaul, Altajskij gosudarstvennyj agrarnyj universitet, 2020, 180 p. (in Russ.).
2. Grunwald L.-C., Belyaev V. I., Meinel T. Improving efficiency of crop protection measures. A technical contribution for better weed control, less pesticide use and decreasing soil tillage intensive in dry farming regions exposed to wind erosion, Switzerland, Springer, 2020. PP. 393–406.
3. Belyaev V. I., Tagiltsev A. V. Tekhnicheskoe obespechenie differentsirovannogo vneseniya sredstv zashchity rastenii [Technical support for the differentiated application of plant protection products]. Proceedings from Agrarian science – agriculture: XV Mezhdunarodnaya nauchno-prakticheskaya konferentsiya – XV International Scientific and Practical Conference. (PP. 11–13), Barnaul, Altajskij gosudarstvennyj agrarnyj universitet, 2020 (in Russ.).
4. Mikhailenko I. M., Voronkov I. V. Metody obnaruzheniya sornyakov, boleznei i vreditelei rastenii po dannym distantsionnogo zondirovaniya [Methods for detecting weeds, diseases and pests of plants according to remote sensing data]. Sovremennye problemy distancionnogo zondirovaniya Zemli iz kosmosa. – Modern problems of remote sensing of the Earth from space, 2016; 13; 3: 72–83 (in Russ.).
5. Esposito M., Crimaldi M., Cirillo V. Drone and sensor technology for sustainable weed management: a review. Chemical and Biological Technologies in Agriculture, 2021; 8: 18.
6. Kalachev A. V., Pelikhov M. E., Novichenko A. I., Leshchev A. M. Razrabotka opticheskogo datchika nalichiya sornykh rastenii [Development of an optical sensor for the presence of weeds]. Prirodoobustroistvo. – Environmental Engineering, 2018; 5: 114–118 (in Russ.).
7. Alt V. V., Pestunov I. A., Melnikov P. V., Elkin O. V. Avtomatizirovannoe obnaruzhenie sornyakov i otsenka kachestva vskhodov sel'skokhozyaistvennykh kul'tur po RGB-izobrazheniyam [Automated detection of weeds and assessment of the quality of seedlings of agricultural crops using RGB images]. Sibirskii vestnik sel'skokhozyaistvennoi nauki. – Siberian Bulletin of Agricultural Science, 2018; 48; 5: 52–60 (in Russ.).
8. Rakhmatulin I., Andreasen C. A concept of a сompact and inexpensive device for controlling weeds with laser beams. Agronomy, 2020; 10; 10: 1616.
9. Yu J., Schumann A. W., Cao Z., Sharpe S. M., Boyd N. S. Weed detection in perennial ryegrass with deep learning convolutional neural network. Frontiers in Plant Science (Sec. Technical Advances in Plant Science), 2019; 10; 1422.
10. Roboty protiv sornyakov [Robots against weeds]. Naukatv.ru Retrieved from https://naukatv.ru/articles/345 (Accessed 10 October 2022) (in Russ.).
11. Pogonyshev V. A., Pogonysheva D. A., Torikov V. E. Neironnye seti v tsifrovom sel'skom khozyaistve [Neural networks in digital agriculture]. Vestnik Bryanskoi gosudarstvennoi sel'skokhozyaistvennoi akademii. – Bulletin of the Bryansk State Agricultural Academy, 2021; 5;87: 68–71 (in Russ.).