Accuracy assessment of landmine detection by infrared aerial imaging
DOI:
https://doi.org/10.36023/ujrs.2025.12.4.294Keywords:
landmine detection, infrared imaging, unmanned aerial vehicle, correct detection probability, false alarm rate, precision, recall, F1-scoreAbstract
Ukraine is currently one of the most mine-contaminated countries in the world, posing a significant threat to the population, environment, and economic recovery. One promising direction for improving the effectiveness of counter-mine activities is the use of Unmanned Aerial Vehicles (UAVs) equipped with infrared (IR) cameras for the remote detection of mines and other explosive devices. The objective of this study is to develop and evaluate an approach for automated mine detection using IR images acquired from UAVs.
This work presents an approach to detecting mines and other explosive objects on IR images, which is based on the anomaly detection method with subsequent threshold processing of the results. Based on this approach, a software module was developed using the Python programming language, which includes image display, application of the anomaly detection method, and threshold processing to obtain binary classification maps.
To test this approach, experimental studies were conducted using a DJI Matrice 300 RTK quadcopter equipped with a Zenmuse H20T IR camera. A total of 34 IR images were used, which contained 206 mines of different types. The presented approach was applied to these images, resulting in binary classification maps. After assessing the accuracy, the following indicators were determined: overall accuracy was 89.32%, precision - 0.79, recall - 0.89, and F1-score- 0.84.
The results obtained confirm the effectiveness and practical suitability of the proposed approach for remote mine detection tasks using UAVs. In the future, it is planned to improve the algorithmic part of the method, in particular, to introduce pre-processing stages of IR images and expand testing to different types of mines and shooting conditions.
Author Contributions: Conceptualization: S.V. Shklyar; Methodology: S.V. Shklyar; Formal Analysis: S.V. Shklyar and A.A. Andreiev; Investigation: A.A. Andreiev and S.I. Golubov; Data Curation: A.A. Andreiev and S.I. Golubov; Writing – Original Draft Preparation: A.A. Andreiev and S.I. Golubov; Writing – Review & Editing: S.I. Golubov; Visualization: S.I. Golubov. All authors have read and agreed to the published version of the manuscript.
Data Availability Statement: Data available on reasonable request from the authors.
Acknowledgments: The authors are grateful to the National Academy of Sciences of Ukraine for supporting this research. We are also grateful to the reviewers and editors for their valuable comments, recommendations, and attention to the work.
Conflicts of Interest: The authors declare no conflict of interest
References
Borodina, O. A., & Liashenko, V. I. (2022). Post-war economic recovery: World experience and an attempt to adapt it for Ukraine. Visnyk ekonomichnoi nauky Ukrainy, 1(42), 121–134 https://doi.org/10.37405/17297206.2022.1(42).121-134 (in Ukrainian)
Dalianis, H. (2018). Evaluation Metrics and Evaluation. In Evaluation Metrics and Evaluation (pp. 45–53). Springer, Cham. https://doi.org/10.1007/978-3-319-78503-5_6
DJI. (n.d.). D-RTK 2 High-Precision GNSS Mobile Station. Retrieved from https://www.dji.com/global/d-rtk-2/info
DJI Enterprise. (n.d.). Zenmuse H20 Series: Specs. Retrieved from https://enterprise.dji.com/zenmuse-h20-series/specs
Heuschmid, D., Wacker, O., Zimmermann, Y., Penava, P., & Buettner, R. (2025). Advancements in landmine detection: Deep learning-based analysis with thermal drones. IEEE Access: Practical Innovations, Open Solutions, 1(1), 1–1. https://doi.org/10.1109/access.2025.3572196
Howard, R. M. (2022). Arbitrarily accurate analytical approximations for the error function. Mathematics and Computational Applications, 27(1), Article 14. https://doi.org/10.3390/mca27010014
Kurtseiov, T. L., Mosov, S. P., Trembovetskyi, M. P., & Yasko, V. A. (2020). Mine weapons in the focus of modern wars and armed conflicts. Zbirnyk naukovykh prats CVSD NUOU, 2(69), 116–121. (in Ukrainian)
Ministry of Economy of Ukraine. (2025, February 27). Ukraine's demining needs reduced by $5 billion due to progress in land clearance – RDNA4 report. Retrieved from https://me.gov.ua/News/Detail/f9f18a5a-63c1-43d4-8fec-b4dcc721caba (in Ukrainian)
Mosov, S., & Neroba, V. (2019). Directions of application of unmanned aviation for demining tasks: World experience. Zbirnyk naukovykh prats NADPSU im. B Khmelnytskoho, 1(79), 172–185. (in Ukrainian)
OpenGlobalRights. (n.d.). Addressing the threat that mines pose to civilians in Ukraine. Retrieved from www.openglobalrights.org/addressing-the-threat-that-mines-pose-to-civilians-in-ukraine/?lang=Ukrainian
Popov, M., Stankevich, S., Mosov, S., Dugin, S., Golubov, S., Andreiev, A., Lysenko, A., & Saprykin, I. (2024). Concept of a geoinformation platform for landmines and other explosive objects detection and mapping with UAV. Radioelectronic and Computer Systems, 2024(4), 207–216. https://doi.org/10.32620/reks.2024.4.17
Shimoi, N., Takita, Y., Nonaml, K., & Wasaki, K. (2001). Land Mine Detecting Technology by Using IR Cameras. SICE Annual Conference.
Centre of Operational Standards and Training Methodology of the Armed Forces of Ukraine. (2019). Engineer training: Reference material for commanders (instructors) for preparation for conducting engineering training classes (Order No. 8 of 10.01.2019). Ministry of Defence of Ukraine. Retrieved from https://ivms.mil.gov.ua/wp-content/uploads/2023/01/inzhenerna-pidgotovka.pdf (in Ukrainian)
UN News. (n.d.). Landmines still pose a threat to two million Ukrainians. Retrieved from https://ukraine.un.org/en/123917-landmines-still-pose-threat-two-million-ukrainians
Verkhovna Rada of Ukraine. (2025, November 6). Parliament adopted as a basis a draft law providing new social guarantees for military personnel during service. Retrieved from https://www.rada.gov.ua/news/news_kom/267509.html (in Ukrainian)
Zmiievskyi, H. A., Puhach, V. V., Kurtov, A. I., & Chepurnyi, V. P. (2024). Tactical aerial reconnaissance using unmanned aerial systems: Training manual. Yaroslav Mudryi National Law University. Retrieved from https://dspace.nlu.edu.ua/bitstream/123456789/20165/1/Takt_pov_rozvidka_2024.pdf (in Ukrainian)
Downloads
Published
How to Cite
Issue
Section
License
Licensing conditions: the authors retain their copyrights and grant the journal the right of first publication of a work, simultaneously licensed in accordance with the Creative Commons Attribution License International CC-BY, which allows you to share the work with proof of authorship of the work and initial publication in this journal.
The authors, directing the manuscript to the editorial office of the Ukrainian Journal of Remote Sensing of the Earth, agree that the editorial board transfers the rights to protection and use of the manuscript (material submitted to the journal editorial board, including such protected copyright objects as photographs of the author, drawings, charts, tables, etc.), including reproduction in print and on the Internet; for distribution; to translate the manuscript into any languages; export and import of copies of the journal with the article of the authors for the purpose of distribution, informing the public. The above rights are transferred by the authors to the editors, without limitation of their validity, and in the territory of all countries of the world without limitation, including in Ukraine.
The authors guarantee that they have exclusive rights to use the submitted material. The editors are not liable to third parties for breach of data by the authors of the guarantees. The authors retain the right to use the published material, its fragments and parts for personal, including scientific and educational purposes. The rights to the manuscript are considered to be transferred by the authors of the editorial board from the moment of the publication of the issue of the journal in which it is published. Reprinting of materials published in the journal by other individuals and legal entities is possible only with the consent of the publisher, with the obligatory indication of the issue of the journal in which the material was published.
