MULTI-AGENT SYSTEM USING ARTIFICIAL INTELLIGENCE TO PROCESS IMAGES FROM THE DRONE'S TECHNICAL VISION CAMERAS
Abstract
Multi-agent technology with drones, modern sensors, precise GPS and artificial intelligence, have led to a breakthrough in the field of cyber-physical systems. This article presents a multi-agent system using artificial intelligence to process images from technical vision cameras installed on a drone. A block diagram of a multi-agent system on a drone was developed based on an effective and simple platform taken from the ARRISE 410 octocopter – an agricultural sprayer drone with: intelligent control system; omnidirectional digital microwave radar; 6-axis high-precision accelerometer; electronic level for measuring tilt; real-time optical camera 1 with a first-person view; control panel equipped with the latest Light Bridge 2 signal transmission system; remote control has a design protected from dust and water. The kit must be supplemented with: hyperspectral HS - camera for scanning, its power module and the ability to interface with the ARRISE 410 drone systems, an information compression module. Model for studying the throughput on the DJI Agras T20 hexacopter DJI Agras T20, MikrotikRB411 5G network card, Raspberry Pi 3 microcomputer, 1 Mpix RGB camera, built-in on-board computer Raspberry Pi OV5647 v1.3 and hyperspectral HS - camera 2 Resonon Pika L shoots hyperspectral data with 281 spectral bands with spectral wavelengths from 400 to 1000 nm and a spatial resolution of 900 hyperspectral pixels per image line. The article solves the problem of experimentally and computationally determining the required compression of information obtained from hyperspectral and optical range cameras with transmission through a telecom operator and the Internet for image processing by an artificial Internet
References
1. Berni J.A.J., Zarco-Tejada P.J., Suarez L. и Fereres E. Thermal and Narrowband Multispectral Remote Sensing for Vegetation Monitoring from an Unmanned Aerial Vehicle, IEEE Transactions on Geosci-ence and Remote Sensing, 2009, Vol. 47, pp. 722-738.
2. Li Z., Liu Y., Walker R., Hayward R. и Zhang J. Towards automatic power line detection for a UAV surveillance system using pulse coupled neural filter and an improved Hough transform, Machine Vision and Applications, 2010, Vol. 21, No. 5, pp. 677-686.
3. Birk A., Viggerikh B., Byulov Kh., Pfingstorn M. i Shvertfeger S. Bezopasnost', zashchita i spasatel'nye operatsii s ispol'zovaniem bespilotnykh letatel'nykh apparatov (BPLA) [Security, Defense, and Rescue Operations Using Unmanned Aerial Vehicles (UAVs)], J. Intel. Robotizirovannye sistemy [J. Intel. Robotic Systems], 2011, Vol. 64, No. 1, pp. 57-76.
4. Deniel K. i Vitfel'd K. Ispol'zovanie infrastruktur obshchedostupnykh setey dlya distantsionnogo zondi-rovaniya s pomoshch'yu BPLA v grazhdanskikh operatsiyakh po obespecheniyu bezopasnosti [Using public network infrastructures for UAV remote sensing in civil security operations], 2011.
5. Faial B.S., Freitas H., Gomes P.H., Mano L.Ya., Pessin G., de Karval'yu A.S., Krishnamachari B., Dzh. Ueyama. Adaptivnyy podkhod k raspyleniyu pestitsidov na osnove bespilotnykh letatel'nykh appa-ratov v dinamicheskikh sredakh [Adaptive approach to pesticide spraying based on unmanned aerial ve-hicles in dynamic environments], Vychisl. Elektron. Agric. [Calculation. The electron. Agric], 2017, 138 p.
6. Available at: https://docs.yandex.ru/docs/view?tm=1728206370&tld=ru&lang=ru&name=215085.pdf&text.
7. Pablo Khorstrand, Raal' Gerra, Aytami Rodriges, Mariya Dias, Sebast'yan Lopes, Khoze Fko Lopes. Platforma BPLA na osnove giperspektral'nogo datchika dlya zakhvata izobrazheniy i bortovoy obrabotki [A UAV platform based on a hyperspectral sensor for image capture and on-board processing]. Availa-ble at: https://innoter.com/articles/giperspektralnaya-semka/.
8. Adaoi T. et al. Giperspektral'naya s"emka: obzor datchikov na baze BPLA, obrabotki dannykh i prilozheniy dlya sel'skogo i lesnogo khozyaystva [Hyperspectral imaging: An overview of UAV-based sensors, data processing, and applications for agriculture and forestry], Udalennaya chuvstvitel'nost' [Remote Sensitivity], 2017, Vol. 9, 11, 1110 p.
9. Khant-mladshiy E.R. i Dotri K.S.T. Kakaya pol'za ot bespilotnykh letatel'nykh apparatov dlya dis-tantsionnogo zondirovaniya sel'skogo khozyaystva i tochnogo zemledeliya? [What is the use of un-manned aerial vehicles for remote sensing of agriculture and precision farming?], Int. J. Remote Sens., 2018, Vol. 39, pp. 15-16.
10. Huang J., Wang H., Dai Q. i Han D. Analiz dannykh NDVI dlya identifikatsii sel'skokhozyaystven-nykh kul'tur i otsenki urozhaynosti [NDVI data analysis for crop identification and yield estimation], IEEE J. Sel. Temy Prikladnoe nablyudenie za Zemley Distantsionnoe zondirovanie [IEEE J. Sel. Topics Applied Earth Observation and Remote Sensing], 2014, Vol. 7, pp. 4374-4384.
11. Rey-Caramés C., Diago M.P., Martín M.P., Lobo A. i Tardaguila J. Ispol'zovanie mnogospektral'nykh izobrazheniy RPAS dlya kharakteristiki moshchnosti, razvitiya list'ev, komponentov urozhaynosti i iz-menchivosti sostava yagod v predelakh vinogradnika [Using multispectral RPAS images to characterize power, leaf development, yield components, and berry composition variability within a vineyard], Udalennaya chuvstvitel'nost' [Remote Sensitivity], 2015, Vol. 7, No. 11, pp. 14458-14481. Available at: http://www.mdpi.com/2072-4292/7/11/14458.
12. Giperspektral'nye kamery serii Specim FX1 [Specim FX1 series hyperspectral cameras]. Available: May 4, 2019. Available at: http://www.specim.fi/fx/.
13. Available at: https://sovzond.ru/press-center/articles/bpla/5601/.
14. Available at: https://geon.ru/product/dji-agras-t20-s-4-dop-akb-i-zu- geksakopter/?ysclid=m7aoja559 g30884089
15. Available at: https://compacttool.ru/camera-5-mpix-dlya-raspberry-pi?ysclid=m7apxj7qdy527308006.
16. Available at: https://resonon.com/Pika-L.
17. Available at: https://tixer.ru/catalog/raspberrypi/raspberry_pi_3_model_b_v1_2/?ysclid=m7aq4e66hj 615743840.
18. Verevkin A.L., Sirenko E.A. Simvoly ikh prednaznachenie i napravlenie nauchnogo issledovaniya. Vsemirnyy tekhnologicheskiy universitet YuNESKO. Moskovskiy tekhnologicheskiy institut [Symbols, their purpose and the direction of scientific research UNESCO World Technological University. Mos-cow Institute of Technology], Mater. mezhdunarodnogo foruma. Vyp. 1. «Innovatsii v sfere zhizned-eyatel'nosti cheloveka ХХI veka» [Materials of the international forum. Issue 1. "Innovations in the sphere of human activity of the 21st century]. Rostov-on-Don: Gingo, 2015, pp. 249-251.
19. Available at: https://compacttool.ru/camera-5-mpix-dlya-raspberry-pi?ysclid=m7aiz70xdw920542036.
20. Available at: https://compacttool.ru/camera-5-mpix-dlya-raspberry-pi?ysclid=m7aiz70xdw920542036.
21. Available at: https://www.researchgate.net/publication/372604327_FPGA-based_Hyperspectral_Lossy_ Compressor_with_Adaptive_Distortion_Feature_for_Unexpected_Scenarios#pf3.
