INTELLIGENT MAPPING AND FACTOR RECOGNITION SYSTEM BASED ON REMOTE SENSING AND COMPUTER VISION TECHNOLOGIES

Modern agriculture faces a number of serious challenges, including climate change, soil degradation, water scarcity, biological threats and the negative impact of anthropogenic factors. A special place among these challenges is occupied by field weediness, which requires accurate monitoring and timely response. This study is devoted to the development of a system for automatic recognition and mapping of weeds with high geospatial accuracy based on UAV data. The proposed approach includes the application of computer vision algorithms for weed detection, data augmentation techniques to improve recognition accuracy, and the author’s map splicing method to provide accurate geo-referencing of detected weeds. Experimental tests confirmed the effectiveness of the developed system in the tasks of automatic detection of weeds and creation of geo-referenced maps of their distribution. Implementation of this system will allow agricultural producers to carry out spot treatment of weedy areas, optimize the use of herbicides and increase the efficiency of weed control.

1. Mohsan, S.A.H., Othman, N.Q.H., Li, Y. Unmanned Aerial Vehicles (UAVs): Practical Aspects, Applications, Open Challenges, Security Issues, and Future Trends. Intelligent Service Robotics, 16, 109–137 (2023). https://doi.org/10.1007/s11370-022-00452-4.

2. Rovira-Sugranes, A., Razi, A., Afghah, F., Chakareski, J. A Review of AI-Enabled Routing Protocols for UAV Networks: Trends, Challenges, and Future Outlook. Ad Hoc Networks, 130, 102790 (2022). https://doi.org/10.1016/j.adhoc.2022.102790.

3. Shadrin, D. Weed Detection on Embedded Systems Using Computer Vision Algorithms. Computer Optics, 49 (1), 85–101 (2025). https://doi.org/ 10.18287/2412-6179-CO-1454.

4. Mumuni, A., Mumuni, F. Data Augmentation with Automated Machine Learning: Approaches and Performance Comparison with Classical Data Augmentation Methods. arXiv preprint, 1, 1–29 (2025). https://doi.org/10.48550/arXiv.2403.08352.

5. Adaev, N., Amaeva, A., Israfilova, M. Monitoring the State of Agricultural Lands in the Chechen Republic Using GIS Technologies. Reliability: Theory & Applications, 19 (6 (81)), 189–207 (2024).

6. OpenCV [Electronic resource]. Available at: https://docs.opencv.org/master/ (accessed: 05.04.2025).

7. Pillow [Electronic resource]. Available at: https://pillow.readthedocs.io/ (accessed: 25.04.2025).

8. GDAL [Electronic resource]. Available at: https://gdal.org/documentation/ (accessed: 25.04.2025).

9. Rasterio [Electronic resource]. Available at: https://rasterio.readthedocs.io/ (accessed: 25.04.2025).

10.