INVESTIGATION OF THE IMPACT OF COMPLEX FIRE CONDITIONS ON THE QUALITY OF SURVEILLANCE AND FLIGHT SAFETY OF UAVS
Abstract
Aviation monitoring of fires with the help of unmanned aerial vehicles (UAVs), in particular,
forest ones, during which the search for various objects of interest is carried out: people, cars,
etc., is one of the most effective measures to reduce the level of possible losses. In this paper, we
consider approaches to the formation of algorithms for processing and improving images obtained
in the process of monitoring the fire situation, based on the use of neural networks, as well as
image filtering algorithms, in order to search for various objects of interest. Fire monitoring using
an UAV is a two-criteria task: there is a need to protect the device from the thermal effects of the
fire as much as possible, as well as to maximize the observability, which can be achieved by reducing
the altitude of the flight. This paper presents the empirical models developed by the authors for
the flight safety of an unmanned aerial vehicle and the observability of objects of interest in the
process of monitoring the fire situation. The proposed models allow us to take into account the
features of the monitoring conditions, such as the priority of detecting the object of interest to the
security of the reconnaissance vehicle itself, air humidity, terrain and type of terrain, time of day,
and so on. An example of the application of the contrast model is considered on the example of the
search and detection of the "letter"label. On the basis of the conducted experiment on the recognition
of the mark in the smoke, the analysis of the proposed models is carried out, the quantitative
results are given. The paper describes the criteria for the optimal choice of the altitude of the
flight of the device over the observed scene, which are formed on the basis of the base of expert
assessments, as well as the proposed models of the observability and safety of the UAV flight. Depending
on the target search task, the optimality criterion for choosing the UAV flight altitude
over the observed scene may vary.
References
Drone: A Brief Survey, 11th International Conference on Information and Communication
Technology Convergence, South Korea, 2020, pp. 728-732.
2. Sudhakar S., Vijayakumar V., Sathiya Kumar C., Priya V., Ravi L., Subramaniyaswamy V.
Unmanned Aerial Vehicle (UAV) based Forest Fire Detection and monitoring for reducing
false alarms in forest-fires,Computer Communications, 2020, Vol. 149, pp. 1-16.
3. Khan A., Gupta S., Gupta S.K. Multi-hazard disaster studies: Monitoring, detection, recovery,
and management, based on emerging technologies and optimal techniques, International Journal
of Disaster Risk Reduction, 2020, Vol. 47, art. no. 101642.
4. Kim N.V., Mikhailov N.A., Mokrova M.I. Drone Searches in Challenging Conditions, Russian
Engineering Research, 2020, Vol. 40, No. 7, pp. 583-585. ISSN 1068-798X.
5. Zhai Q., Ye Z.-S. How reliable should military UAVs be?, IISE Transactions. Taylor and
Francis Ltd., 2020, Vol. 52 (11), pp. 1234-1245.
6. Zhou Z., Wang X., Li C., Zeng M., Li Z. Adaptive deep feature aggregation using Fourier transform
and low-pass filtering for robust object retrieval, Journal of Visual Communication and
Image Representation, 2020.
7. Martin Hahner, Dengxin Dai, Christos Sakaridis, Jan-Nico Zaech, Luc Van Gool. Semantic
Understanding of Foggy Scenes with Purely Synthetic Data, arXiv, 2020. Available at:
https://arxiv.org/abs/1910.03997.
8. Magnus Wrenninge, Jonas Unger. Synscapes: A Photorealistic Synthetic Dataset for Street
Scene Parsing, arXiv, 2018. Available at: https://arxiv.org/abs/1810.08705.
9. Evdokimenkov Veniamin N., Kim Nikolay V., Kozorez Dmitriy A., Mokrova Mariya I. Control
of unmanned aerial vehicles during fire situation monitoring, INCAS Bulletin, 2019, Vol. 11,
Special Issue, pp. 66-73. Doi: 10.13111/2066-8201.
10. Sarmanaev S.Kh., Basharin V.A., Tolkach P.G., Shcherbashov K.A. Toksiko-khimicheskie
povrezhdeniya pri pozhare [Toxico-chemical damage in a fire], Biomeditsinskiy zhurnal "Medline.
ru" [Biomedical Journal "Medline.ru"], Vol. 16. Toksikologiya. 26 March 2015.
11. Nekrasov O.N. Prognozirovanie pozharnoy obstanovki i skorosti rasprostraneniya lesnogo pozhara s
uchetom rel'efa mestnosti, pogodnykh usloviy i meropriyatiy dlya pozharnykh [Forecasting of the
fire situation and the speed of forest fire propagation taking into account the terrain, weather conditions
and measures for firefighters], Nauchno-obrazovatel'nye problemy grazhdanskoy zashchity
[Scientific and educational problems of civil protection], 2014, No. 3.
12. Kudrin A.Yu., Podrezov Yu.V. Analiz sovremennykh sredstv i metodov bor'by s prirodnymi
pozharami [Analysis of modern means and methods of fighting natural fires], Tekhnologii
grazhdanskoy bezopasnosti [Technologies of civil security], 2006, No. 4.
13. Georgiev G.D., Hristov G., Zahariev P., Kinaneva D. Forest Monitoring System for Early Fire
Detection Based on Convolutional Neural Network and UAV imagery, 28th National Conference
with International Participation, TELECOM 2020 – Proceedings, 2020, pp. 57-60.
14. Lee I.K., Trinder J.C., Sowmya A. Application of u-net convolutional neural network to bushfire
monitoring in Australia with sentinel-1/-2 data, International Archives of the Photogrammetry,
Remote Sensing and Spatial Information Sciences – ISPRS Archives, 2020, pp. 573-578.
15. Adão T., Pinho T.M., Pádua L. et al. Using virtual scenarios to produce machine learnable
environments for wildfire detection and segmentation, International Archives of the Photogrammetry,
Remote Sensing and Spatial Information Sciences – ISPRS Archives, Vol. 42, Issue
3/W8, 20 August 2019, pp. 9-15.
16. Shobeiry P., Xin M., Hu X., Chao H. Uav path planning for wildfire tracking using partially
observable Мarkov decision process, AIAA Scitech 2021 Forum, pp. 1-18.
17. Sousa M.J., Moutinho A., Almeida M. Thermal infrared sensing for near real-time data-driven fire
detection and monitoring systems, 2020 Sensors, Switzerland, Vol. 20 (23), 6803, pp. 1-29.
18. Gorelik A.L., Skripkin V.A. Recognition methods. Moscow: Nauka. 2004.
19. Merino L., Caballero F., De Dios J.R.M., Maza I., Ollero A. An unmanned aircraft system for
automatic forest fire monitoring and measure-ment, Journal of Intelligent and Robotic Systems,
2012, Vol. 65 (1), pp. 533-548.
20. Rodin C.D., De Lima L.N., De Alcantara Andrade F.A., Haddad D.B., Johansen T.A., Storvold R.
Object Classification in Thermal Images us-ing Convolutional Neural Networks for Search and
Rescue Missions with Un-manned Aerial Systems, Proceedings of the International Joint Conference
on Neural Networks, 2018-July,8489465.
