|
Article information
2021 , Volume 26, ¹ 3, p.118-129
Izvozchikova V.V., Shardakov V.M., Zaporozhko V.V.
Development of hardware and software complex for monitoring fires by unmanned aerial vehicles
The paper addresses the problem of fire detection that is based on information obtained by an unmanned aerial vehicle. The purpose of this work is the possibility of early detection of ignition in oil and gas wells. An algorithm for fire detection based on the application of the RGB color model to the obtained video images of the studied area is proposed. The algorithm is based on the methods of spatial image segmentation and color quantization. According to the presented algorithm, a quadcopter transmits the incoming image from the digital video camera to the terminal, scanning the monitoring zone and GPS coordinates set by the operator. The algorithm for detecting the fire source is divided into four stages: analysis of the color intensity on the frame; checking the color of the area specified by the operator for coincidence with the range of fire; determining the fire coverage area in a certain territory and analyzing the change in the shape of the fire center relative to the angle of the moving unmanned aerial vehicle; determining the direction of fire propagation. Accurate automated determination of coordinates is carried out using the GPS signal of the fire, which allows starting localization and eliminating the fire source in a timely manner, thereby preventing a negative impact on people, nature and wildlife, as well as reducing the damage caused by the fire. A prototype of a software and hardware complex for remote dynamic monitoring, including an on-board information processing system for an unmanned aerial vehicle (UAV) and an information system, has been modelled. The paper presents the requirements for unmanned aerial vehicles, as well as analysis for the cost of the quadcopter’s flight time. The results of the experiments have shown the ability of the algorithm proposed by the authors to successfully detect the source of a fire on the ground. The created software and hardware complex allows quickly developing and making the most optimal decisions on the direction of fire crews and fire equipment to the fire sites, which is especially important for remote areas
[full text] [link to elibrary.ru]
Keywords: fire source, territory monitoring, robotic platforms, detection of natural and manmade fires, unmanned aerial vehicles, fire coordinates
doi: 10.25743/ICT.2021.26.3.008
Author(s):
Izvozchikova Vera Vasilyevna
PhD. , Associate Professor
Position: Associate Professor
Office: Orenburg state University
Address: 460018, Russia, Orenburg, 13, Aven. Pobedy
Phone Office: (332) 37-25-52
E-mail: VIZA-8.11@mail.ru
SPIN-code: 7062-9125Shardakov Vladimir Mikhailovich
Position: Master student
Office: Orenburg state University
Address: 460018, Russia, Orenburg, 13, Aven. Pobedy
Phone Office: (332) 37-25-52
E-mail: werovulv@inbox.ru
SPIN-code: 9777-7718Zaporozhko Veronika Vyacheslavovna
Associate Professor
Position: Associate Professor
Office: Orenburg state University
Address: 460018, Russia, Orenburg, 13, Aven. Pobedy
Phone Office: (332) 37-25-52
E-mail: mag_pearl@mail.ru
SPIN-code: 9884-0222 References:
1. Liu S., Hu L. Development of four rotor fire extinguishing system for synchronized monitoring of air and ground for fire fighting. International Conference on Intelligent Robotics and Applications (ICIRA2019), Intelligent Robotics and Applications. 2019: 267–278.
2. Naderpour M., Mojaddadi R., Nima K., Biswajeet P. Forest fire induced Natech risk assessment: A survey of geospatial technologies. Reliability Engineering and System Safety. 2019; (191):106558.
3. Hsieh J.C. Fire warning system by using GPS monitoring and quadcopters. International Conference on Universal Access in Human-Computer Interaction (UAHCI2017). Universal Access in Human-Computer Interaction, Human and Technological Environments. 2017; (10279):518–526.
4. Motaparthi A., Katukam R. MAV for fire existinguiging: A review. International Journal of Engineering Innovation & Research. 2014; 3(3):297–299. ISSN:2277-5668.
5. Pilz U., Gropengießer W., Walder F., Witt J., Werner H. Quadrocopter localization using RTK-GPS and vision-based trajectory tracking. International Conference on Intelligent Robotics and Applications, (ICIRA2011). Intelligent Robotics and Applications. 2011: 12–21.
6. Mishra S., Zhang W. Hybrid low pass and de-trending filter for robust position estimation of quadcopters. Dynamic Systems and Control Division. 2016; 2(DSCC2016-9921):V002T29A004. Available at: https://www.researchgate.net/publication/313786654_Hybrid_Low_Pass_and_Derending_Filter_for_Robust_Position_Estimation_of_Quadcopters
7. Palestini L., Binotti G. Image/data transmission systems of the Italian fire and rescue service in emergency contexts: An overview of methods and technologies to support decision-making. Enhancing CBRNE Safety & Security: Proceedings of the SICC2017 Conference. Italy, Rome. 2017: 129–139.
Available at: https://link.springer.com/chapter/10.1007%2F978-3-319-91791-7_1
8. Golodov V., Buraya A., Bessonov V. Detection of forest fires based on aerial survey data using neural network technologies. International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon). Vladivostok, Russia. 2019: 19229086.
9. Krushel E.G., Lyutaya T.P., Privalov O.O., Shcherbakov M.V. Fire-dangerous situations recognition in the forest areas and forest shelter belts. Proceedings of the Volgograd state technical University. 2018; 218(8):39–42. (In Russ.)
10. Stula M., Krstinic D., Seric L. Intelligent forest fire monitoring system. Information Systems Frontiers. 2012; (14):725–739.
11. Hua L., Shao G. The progress of operational forest fire monitoring with infrared remote sensing. Journal of Forestry Research. 2017; (28):215–229.
12. Frizzi S., Kaabi R., Bouchouicha R., Ginoux J.M., Moreau E., Fnaiech F. Convolutional neural network for video fire and smoke detection. IECON 2016 — 42nd Annual Conference of the IEEE Industrial Electronics Society. Florence, Italy. 2016: 16557369.
13. Zhu H., Jin L. Design of forest fire prevention system based on images recognition algorithm. Journal of Multidisciplinary Engineering Science and Technology. 2019; 6(7):10403–10405.
14. Zhang Q.X., Lin G.H., Zhang Y.M., Xu G., Wang J.J. Wildland forest fire smoke detection based on faster R-CNN using synthetic smoke images. Procedia Engineering. 2018; (211):441–446.
15. Tian Q., Yan Y., Lu G. An autoadaptive edge-detection algorithm for flame and fire image processing. IEEE Transactions on Instrumentation and Measurement. 2012; 61(5):1486–1493.
16. Kalpana Y., Padmaa M. An efficient edge detection algorithm for flame and fire image processing. International Conference on Communication and Signal Processing. Melmaruvathur, India. 2014; 14737228.
17. Mezhenin A., Izvozchikova V., Shardakov V., Korotkikh A. Technologies of reconstruction and procedural generation of three-dimensional content. Journal of Physics: Conference Series, Proceedings of the International Scientific Conference on Applied Physics, Information Technologies and Engineering 2019, APITECH 2019, 25–27 September 2019, Krasnoyarsk, Russian Federation / Krasnoyarsk Science and Technology City Hall. 2019; 1399(3): 6.
18. Shardakov V., Parfenov D., Bolodurina I., Izvozchikova V., Zaporozhko V., Mezhenin A. Development of an effective model of parallel processing of multimedia data on the CPU and GPU in the cloud system. Journal of Physics: Conference Series, Proceedings of the International Scientific Conference on Applied Physics, Information Technologies and Engineering 2019, APITECH 2019, 25–27 September 2019, Krasnoyarsk, Russian Federation / Krasnoyarsk Science and Technology City Hall. 2019; 1399(3): 8.
Bibliography link:
Izvozchikova V.V., Shardakov V.M., Zaporozhko V.V. Development of hardware and software complex for monitoring fires by unmanned aerial vehicles // Computational technologies. 2021. V. 26. ¹ 3. P. 118-129
|
