Proceedings of the 2022 Seventh International Conference on Research in Intelligent and Computing in Engineering

DOI: http://dx.doi.org/10.15439/2022R19

Citation: Proceedings of the 2022 Seventh International Conference on Research in Intelligent and Computing in Engineering, Vu Dinh Khoa, Shivani Agarwal, Gloria Jeanette Rincon Aponte, Nguyen Thi Hong Nga, Vijender Kumar Solanki, Ewa Ziemba (eds). ACSIS, Vol. 33, pages 135–140 (2022)

Full text

Abstract. The naturally occurring wildfires and the people-related forest fires are events, which in many cases have significant impact on the environment, the wildlife and the human population. The most devastating among these events usually start in unpopulated remote areas, which are difficult to inspect or are not constantly being monitored or observed. This gives the local small-sized fires enough time to evolve into full-scale wide-area disasters, which in turn makes their suppression and extinguishing very difficult. In this paper, we present an autonomous system for early detection of forest fires, named THEASIS-M. The presented system represents a solution that is based on a combination of innovative technologies, including computer vision algorithms, artificial intelligence and unmanned aerial vehicles. In the first part of the study, we provide an overview on the present applications of the UAVs in the forestry domain. The paper then introduces the general architecture of the THEASIS-M system and its components. The system itself is fully autonomous and is based on several different types of UAVs, including a fixed-wing drone, which provides the overall forest monitoring capabilities of the proposed solution, and a rotary-wing UAV that is used for confirmation and monitoring of the detected fire event. The widely used technologies for computer vision and image processing, which are used for the detection of fire and smoke in the real-time video streams sent from the UAVs to the ground control station, are highlighted in the next section of this study. Finally, the experimental tests and demonstrations of the proposed THEASIS-M system are presented and briefly discussed.

References

1. S. Sudhakar et al. (2020) Unmanned Aerial Vehicle (UAV) based forest fire detection and monitoring for reducing false alarms in forest-fires. Computer Communications: 149, 2020, pp. 1-16. https://doi.org/10.1016/j.comcom.2019.10.007
2. Thiel C. et al. (2020) Monitoring selective logging in a pine-dominated forest in central Germany with repeated drone flights utilizing a low cost RTK quadcopter. Drones 2020, 4, 11. https://doi.org/10.3390/drones4020011
3. Sharifah M. S. M. D. et al. (2020) Applications of drone in disaster management: A scoping review. Science & Justice: 62 (1), 2022, pp. 30-42. https://doi.org/10.1016/j.scijus.2021.11.002
4. Abderahman Rejeb et al. (2022) Drones in agriculture: A review and bibliometric analysis. Computers and Electronics in Agriculture: 198, 2022, 107017. https://doi.org/10.1016/j.compag.2022.107017
5. Zilong Wang et al. (2022) Predicting transient building fire based on external smoke images and deep learning. Journal of Building Engineering: 47 (15), 2022, 103823. https://doi.org/10.1016/j.jobe.2021.103823
6. Ali Hosseini, Mahdi Hashemzadeh and Nacer Farajzadeh (2022). UFS-Net: A unified flame and smoke detection method for early detection of fire in video surveillance applications using CNNs. Journal of Computational Science: 61, 2022, 101638. https://doi.org/10.1016/j.jocs.2022.101638
7. Seong G.Kong et al. (2016) Fast fire flame detection in surveillance video using logistic regression and temporal smoothing. Fire Safety Journal: 79, 2016, pp. 37-43. https://doi.org/10.1016/j.firesaf.2015.11.015
8. G. D. Georgiev et al. (2020) Forest Monitoring System for Early Fire Detection Based on Convolutional Neural Network and UAV imagery. In proceeding of 28th National Conference with International Participation TELECOM-2020, pp. 57-60. http://dx.doi.org/10.1109/TELECOM50385.2020.9299566
9. D. Kinaneva et al. (2020) An artificial intelligence approach to real-time automatic smoke detection by unmanned aerial vehicles and forest observation systems. 2020 International Conference on Biomedical Innovations and Applications (BIA): 2020, pp. 133-138, http://dx.doi.org/10.1109/BIA50171.2020.9244498
10. ALTi Transition-F vertical take-off and landing (VTOL) fixed-wing UAV. Available at: www.altiuas.com [Access: 9/2022].
11. NightHawk 2 EO/IR camera. Available at: www.nextvision-sys.com/nighthawk-2 [Access: 9/2022].
12. The DJI Matrice 210 RTK unmanned aerial vehicle. Available at: www.dji.com [Access: 9/2022].
13. The Zenmuse XT2 thermal camera. Available at: www.heliguy.com [Access: 9/2022].
14. S.Karma et al. (2015) Use of unmanned vehicles in search and rescue operations in forest fires: Advantages and limitations observed in a field trial. International Journal of Disaster Risk Reduction: 13, 2015, pp. 307-312, https://doi.org/10.1016/j.ijdrr.2015.07.009
15. M. Mohan, C.A. Silva, C. Klauberg, P. Jat, G. Catts, A. Cardil, A.T. Hudak, and M. Dia (2017) Individual Tree Detection from Unmanned Aerial Vehicle (UAV) Derived Canopy Height Model in an Open Canopy Mixed Conifer Forest. Forests 8(9):340, https://doi.org/10.3390/f8090340
16. C. L. Scher, E. Griffoul and C. H. Cannon (2019) Drone-based photogrammetry for the construction of high-resolution models of individual trees. Trees vol. 33/2019, pp. 1385–1397. https://doi.org/10.1007/s00468-019-01866-x
17. J. Li, B. Yang, Y. Cong, L. Cao, X. Fu and Z. Dong (2019) 3D Forest Mapping Using A Low-Cost UAV Laser Scanning System: Investigation and Comparison. Remote Sensing, 11(6):717 2019, https://doi.org/10.3390/rs11060717
18. M. Pierzchała, P. Giguère, R. Astrup (2018) Mapping forests using an unmanned ground vehicle with 3D LiDAR and graph-SLAM. Computers and Electronics in Agriculture, Volume 145, 2018, pp. 217-225, ISSN 0168-1699, https://doi.org/10.1016/j.compag.2017.12.034
19. Official webpage of the SFEDA transnational project. Available at: www.interreg-balkanmed.eu/approved-project/22/ [Access: 9/2022].