Proceedings of TUSUR University / Archive / Issue of Journal № 2, t. 28, 2025 / Automated Generation of Tree Crown Images Dataset for Neural Network Training using UAV-Acquired Imagery

Automated Generation of Tree Crown Images Dataset for Neural Network Training using UAV-Acquired Imagery

DOI: 10.21293/1818-0442-2025-28-2-130-136

Download article in PDF format

JATS xml

Abstract: Tree mapping is an important type of information demanded in various fields of research and practice. However, it is an expensive and time-consuming process, which makes it difficult to monitor large areas. Therefore, automated methods are necessary to optimize tree mapping in forest areas. This article proposes a software tool based on a dataset of tree crown images acquired using unmanned aerial vehicles (UAV), necessary for training neural networks. The basis of the accumulated dataset consists of tree crowns in high spatial resolution (1–10 cm) RGB images. The current dataset contains coniferous tree crown images acquired from different heights. To prepare this dataset, a method for extracting the crowns of each tree was applied in a semi-automatic image annotation program. The proposed tool can be successfully used for training neural networks and other machine learning approaches as well as computer vision techniques.

Keywords: Unmanned Aerial Vehicle (UAV), RGB, tree, crowns, image segmentation

For citation:
Kataev M. Yu., Kartashov E. Yu., Lukyanov A. K., Skvortsov Ya. O., Shurygin Yu. A., Kataev-Mihail-Yurievich M. Yu. Automated Generation of Tree Crown Images Dataset for Neural Network Training using UAV-Acquired Imagery. Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2025, vol. 28, no. 2, pp. 130–136. DOI: 10.21293/1818-0442-2025-28-2-130-136

Authors and copyright holders:

Kataev M. Yu.
Kartashov E. Yu.
Lukyanov A. K. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
Skvortsov Ya. O. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
Shurygin Yu. A. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
Kataev-Mihail-Yurievich M. Yu. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)

1. Kurbanov E.A., Vorob'ev O.N. Distancionnye metody v lesnom hozyajstve [Remote Sensing Methods in Forestry] textbook, Yoshkar-Ola, Volga State University of Technology, 2020, 266 p. (in Russ.).
2. Szeliski R. Computer vision: algorithms and applications. Springer Nature, 2022, 1232 p.
3. Anirad K., Siddha G., Mekher K. [Artificial Intelligence and Computer Vision. Real Projects on Python, Keras, and TensorFlow]. St. Petersburg, Piter, 2023, 624 p. (in Russ.)
4. Braginsky M.Ya., Tarakanov D.V. Estimation of plants health using convolutional neural networks. Proceedings of Cybernetics, 2021, vol. 1 (41), pp. 41–50.
5. Tolkach I.V. Methods for estimating pine taxation and interpretation indices in digital images. Problems of forestry and silviculture, collection of scientific papers: Gomel, Forest Institute of the National Academy of Sciences of Belarus, 2012, no. 72, pp. 354–362.
6. Minaev V.N., Leont'ev L.L., Kovyazin F.V. Taksaciya lesa [Forest Taxation]. St. Petersburg: Lan', 2020, 240 p. (in Russ.)
7. Kuz'menkov M.V., Kulagin A.P., Tarkan A.V., Buzunovskij R.S. Taksacionno-lesoustroitel'nyj spravochnik [Forest Inventory and Management Handbook], Minsk: Editorial office of the journal «Lesnoe i ohotnich'e hozyajstvo», 2019, 336 p. (in Russ.)
8. Kataev M.Y., Kartashov E.Y., Smirnov D.S. Methodology and software for atmospheric correction of unmanned aerial vehicle images in the task of safe vegetation location. Proceedings of TUSUR, 2021, vol. 24, no. 4, pp. 73–78.
9. Rodriguez E., Schlerf P.M., Roder A., Stoffels J., Udelhoven T. Forest disturbance characterization in the era of earth observation big data: A mapping review. International Journal of Applied Earth Observation and Geoinformation, 2024, vol. 128, pp. 1–13.
10. Kataev M.Y., Kartashov E.Y., Kuznetsov A.A. Methodology for clustering agricultural fields from RGB images of unmanned aerial vehicles. Proceedings of TUSUR, 2021, vol.24, no. 3, pp. 50–56.
11. Kinoshenko D., Mashtalir V., Shlyakhov V. A Partition Metric for Clustering Features Analysis. International Journal «Information Theories and Applications», 2007, vol. 14, no. 3, pp. 230–236.
12. Alexeeva V.A. [Using machine learning methods in binary classification tasks]. Automation of management processes, 2015, no. 4, pp. 58–63.
13. Kolesnikov A.A., Kikin P.M., Kommisarova E.V., Kasianova E.L. Use of machine learning technologies in solving geoinformation tasks. Proceedings of the International Conference InterCarto. InterGIS, Petrozavodsk, 2018, no. 24, pp. 371–384.
14. Smirnov A.V., Ivanov E.S. Using convolutional neural network mechanism for object search in aerial images. Program Systems: Theory and Applications, 2017, no. 4 (35), pp. 85–99.
15. Geetha G., Nafeesathu S. A Review on Various Image Interpolation Techniques. International Research Journal of Engineering and Technology (IRJET), 2021, vol. 8, no 7, pp. 467–470.
16. Quan Y., Zhang D., Zhang L., Tang J. Centralized Feature Pyramid for Object Detection. IEEE Transactions on Image Processing, 2023, vol. 32, pp. 4341–4354.