Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 21, 2024
Number 1 Number 2 Number 3
Volume 20, 2023
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 19, 2022
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 18, 2021
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 17, 2020
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 16, 2019
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 15, 2018
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 14, 2017
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 13, 2016
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 12, 2015
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 11, 2014
Number 1 Number 2 Number 3 Number 4
Volume 10, 2013
Number 1 Number 2 Number 3 Number 4
Volume 9, 2012
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 8, 2011
Number 1 Number 2 Number 3 Number 4
Volume 7, 2010
Number 1 Number 2 Number 3 Number 4
Issue 6, 2009
Volume 1 Volume 2
Issue 5, 2008
Volume 1 Volume 2
Issue 4, 2007
Volume 1 Volume 2
Issue 3, 2006
Volume 1 Volume 2
Issue 2, 2005
Volume 1 Volume 2
Issue 1, 2004
Volume 1
Search
Find:
русский
ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2023, Vol. 20, No. 1, pp. 55-66

A technique for segmenting images of unmanned aerial vehicles using neural networks

M.Yu. Kataev 1 , E.Yu. Kartashov 1 , V.V. Ryabukhin 1 , E.V. Makarov 1 , O.A. Pasko 2 
1 Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russia
2 National Open Institute St. Petersburg, Saint Petersburg, Russia
Accepted: 31.01.2023
DOI: 10.21046/2070-7401-2023-20-1-55-66
Unmanned Aerial Vehicles (UAVs) have become widely known in various sectors of the economy, including agriculture. Basic advantages of UAVs are high speed, high spatial resolution (centimeters) and a large area of agricultural fields covered by the digital image (orthophotomap). Working with an orthophotomap helps reduce the proportion of routine work and reduces the time for specialists to monitor the state of agricultural plants. Significant technological progress in the development of UAV design tools, measurement techniques, software for processing of measurement results (images) has allowed creating a direction called “precision agriculture”. Processing of images obtained using UAVs is typically performed by computer vision methods or using neural networks. Convolutional Neural Networks (CNNs) have become the most popular type of neural networks in recent years. Despite the fact that CNN have become a powerful tool for solving a variety of UAV image processing problems, there are tasks that are not solved accurately enough using both computer vision methods and typical CNN algorithms. The article provides a technique for segmenting images of agricultural fields obtained using UAVs using CNN. The problem solution features associated with small amount of data (images of homogeneous types of surface, for example, only soil) for training CNN are considered and obtained segmentation results are presented.
Keywords: unmanned aerial vehicle, UAV, image, convolutional neural network, segmentation
Full text

References:

  1. Bespilotnye letatel’nye apparaty (Unmanned aerial vehicles), Voronezh: Nauchnaya kniga, 2015, 616 p. (in Russian).
  2. Beard R. W., McLain T. W., Small Unmanned Aircraft: Theory and Practice, Princeton, NJ: Princeton Univ. Press, 2012. 320 p.
  3. Gafarov F. M., Galimyanov A. F., Iskusstvennye neironnye seti i prilozheniya (Artificial neural networks and applications), Kazan: Izd. Kazanskogo universiteta, 2018, 121 p. (in Russian).
  4. Golovko V. A., Krasnoproshin V. V., Neirosetevye tekhnologii obrabotki dannykh (Neural network technologies of data processing), Minsk: BGU, 2017, 263 p. (in Russian).
  5. Gonzalez R. C., Woods R. E., Digital Image Processing, 2 nd ed., Upper Saddle River, NJ: Prentice Hall, 2002, 185 p.
  6. Kataev M. Yu., Elgin K. S., Sorokin I. B., Methods of technical vision for mapping the state of agricultural fields, Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2018, Vol. 21, No. 4, pp. 75–80 (in Russian), DOI: 10.21293/1818-0442-2018-21-4-75-80.
  7. Kataev M. Yu., Kartashov E. Yu., Kuznetsov A. A., Method of clustering agricultural fields by RGB images of unmanned aerial vehicles, Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2021, Vol. 24, No. 3, pp. 50–56 (in Russian), DOI: 10.21293/1818-0442-2021-24-3-50-56.
  8. Kovyazin V. F., Pasko O. A., Lepikhina O. Yu., Trushnikov V. E., Assessment of the forest land inventory accuracy using aerial laser scanning, Geodezia i kartografia, 2022, Vol. 6, pp. 54–63 (in Russian), DOI: 10.22389/0016-7126-2022-984-6-54-63.
  9. Limonov A. N., Gavrilova L. A., Fotogrammetriya i distantsionnoe zondirovanie (Photogrammetry and remote sensing), Moscow: Akademicheskii proekt, 2018, 297 p. (in Russian).
  10. Nekhin S. S., Oleinik S. V., Automation of photogrammetric collection of three-dimensional information at the CFS, Izvestiya vyshikh uchebnikh zavedenii. Geodeziya i aehrofotosemka, 2011, No. 2, pp. 70–74 (in Russian).
  11. Pasko O. A., Zakharchenko A. V., Cadastral and geoecological characteristics of especially valuable productive agricultural lands, Bull. Tomsk Polytechnic University. Geo Assets Engineering, 2020. Vol. 331, No. 11, pp. 7–19 (in Russian), DOI: 10.18799/24131830/2020/11/2881.
  12. Plastinin A. I., Kupriyanov A. V., Il’yasova N. Yu., Development of methods for the formation of color-texture features for the analysis of biomedical images, Komp’yuternaya optika, 2007, Vol. 31, No. 2, pp. 82–85 (in Russian).
  13. Forecast of scientific and technological development of the agro-industrial complex of the Russian Federation for the period up to 2030, Ministry of Agriculture of the Russian Federation, 2017, 140 p. (in Russian).
  14. Savin I. Yu., Lupyan E. A., Bartalev S. A., Efficient space monitoring of crops in Russia, Geomatika, 2011, No. 2(11), pp. 69–76 (in Russian), https://doi.org/10.14529/cmse170303.
  15. Sozykin A. V., Review of deep neural network training methods, Vestnik Yuzhno-Ural’skogo gosudarstvennogo universiteta. Ser. “Vychislitel’naya matematika i informatika”, 2017, Vol. 6(3), pp. 28–59 (in Russian), DOI: 10.25018/0236-1493-2018-12-0-192-198.
  16. Tikhonov A. A., Akmatov D. Zh., Review of programs for processing aerial photography data, Gornyi informatsionno-analiticheskii byulleten’, 2018, No. 12, pp. 192–198 (in Russian).
  17. Tkacheva A. A., Favorskaya M. N., Modeling of three-dimensional scenes of forest areas according to laser scanning data and aerial photographs, Informatsionno-upravlyayushchie sistemy, 2015, Vol. 6(79), pp. 40–49 (in Russian), DOI: 10.15217/issn1684-8853.2015.6.40.
  18. Tochnoe sel’skoe khozyaistvo (Precision Agriculture), Shpaar D., Zakharenko A. V., Yakushev V. P. (eds.), Saint Petersburg; Pushkin, 2009, 397 p. (in Russian).
  19. Truflyak E. V., Kurchenko N. Yu., Kreimer A. S., Monitoring i prognozirovanie v oblasti tochnogo sel'skogo khozyaistva po itogam 2021 g. (Monitoring and forecasting in the field of precision agriculture based on the results of 2021), Krasnodar: KubGAU, 2022, 210 p. (in Russian).
  20. Fetisov V. S., Bespilotnaya aviatsiya: terminologiya, klassifikatsiya, sovremennoe sostoyanie (Unmanned aviation: terminology, classification, current state), Ufa: Foton, 2014, 217 p. (in Russian).
  21. Forsyth D. A., Ponce J., Computer Vision. A Modern Approach, Prentice Hall, 2002, 693 p.
  22. Haykin S., Neural Networks: A Comprehensive Foundation, 2 nd ed., Upper Saddle River, NJ: Prentice Hall, 1999, 842 p.
  23. Shagaida N. I., Uzun V. Ya., Development trends and main challenges of the agricultural sector of Russia, Ekonomika sel’skokhozyaistvennykh i pererabatyvayushchikh predpriyatii, 2017, No. 9, pp. 2–9 (in Russian).
  24. Yakushev V. P., Dubenok N. N., Loupian E. A., Earth remote sensing technologies for agriculture: application experience and development prospects, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2019, Vol. 16, No. 3, pp. 11–23 (in Russian), DOI: 10.21046/2070-7401-2019-16-3-11-23.
  25. Bhatt D., Patel C., Talsania H., CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope, Electronics, 2021, Vol. 10(20), Art. No. 2470, 28 p., https://doi.org/10.3390/electronics10202470.
  26. Escamilla-Garcia A., Soto-Zarazua G. M., Toledano-Ayala M., Rivas-Araiza E., Gastelum-Barrios A., Applications of Artificial Neural Networks in Greenhouse Technology and Overview for Smart Agriculture Development, Applied Sciences, 2020, Vol. 10(11), Art. No. 3835, 43 p., https://doi.org/10.3390/app10113835.
  27. Kasajima I., Measuring plant colors, Plant Biotechnology, 2019, Vol. 36(2), pp. 63–75, https://doi.org/10.5511/plantbiotechnology.19.0322a.
  28. Pasko O., Staurskaya N., Zakharchenko A., Zharnikov V., Larionov Y., Bio-Farming as the Basis of Environmentally-Sustainable Arable Farming at the Time of Global Warming, Research Anthology on Strategies for Achieving Agricultural Sustainability, 2022, pp. 600–627, DOI: 10.4018/978-1-6684-5352-0.ch031.
  29. Priya S., Identification of weeds using HSV color spaces and labelling with machine learning algorithms, Intern. J. Recent Technology and Engineering, 2019, Vol. 8(1), pp. 1781–1786.
  30. Ryan M., Agricultural Big Data Analytics and the Ethics of Power, J. Agricultural and Environmental Ethics, 2019, Vol. 33, pp. 49–69 (in Russian), https://doi.org/10.1007/s10806-019-09812-0.
  31. Wang A. A., Zhang W., Wei X., A review on weed detection using ground-based machine vision and image processing techniques, Computers and Electronics in Agriculture, 2019, Vol. 158, pp. 226–240, DOI: 10.1016/j.compag.2019.02.005.
  32. Zhong Y., Hu X., Luo C., WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF[J], Remote Sensing of Environment, 2020, Vol. 250, 5 p., https://doi.org/10.48550/arXiv.2012.13920.