Early Forest Fire Detection Using Drones and Artificial Intelligence

被引:0
作者
Kinaneva, Diyana [1 ]
Hristov, Georgi [1 ]
Raychev, Jordan [1 ]
Zahariev, Plamen [1 ]
机构
[1] Univ Ruse, Dept Telecommun, Ruse, Bulgaria
来源
2019 42ND INTERNATIONAL CONVENTION ON INFORMATION AND COMMUNICATION TECHNOLOGY, ELECTRONICS AND MICROELECTRONICS (MIPRO) | 2019年
关键词
early forest fire detection platform; drones; UAVs; artificial intelligence; computer vision;
D O I
10.23919/mipro.2019.8756696
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Forest and urban fires have been and still are serious problem for many countries in the world. Currently, there are many different solutions to fight forest fires. These solutions mainly aim to mitigate the damage caused by the fires, using methods for their early detection. In this paper, we discuss a new approach for fire detection and control, in which modern technologies are used. In particular, we propose a platform that uses Unmanned Aerial Vehicles (UAVs), which constantly patrol over potentially threatened by fire areas. The UAVs also utilize the benefits from Artificial Intelligence (AI) and are equipped with on-board processing capabilities. This allows them to use computer vision methods for recognition and detection of smoke or fire, based on the still images or the video input from the drone cameras. Several different scenarios for the possible use of the UAVs for forest fire detection are presented and analyse in the paper, including a solution with the use of a combination between a fixed and rotary-wing drones.
引用
收藏
页码:1060 / 1065
页数:6
相关论文
共 7 条
[1]  
[Anonymous], J DIGITAL INFORM MAN
[2]  
[Anonymous], VEH NAV INF SYST C 1
[3]  
[Anonymous], KOMPYUTARNI NAUKI KO
[4]  
[Anonymous], INT INF HID MULT SIG
[5]  
[Anonymous], SEC TECHN 2003 P IEE
[6]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90
[7]  
San-Miguel-Ayanz J., 2018, EUR 29318 EN, DOI DOI 10.2760/663443