Wildfire monitoring from electric networks and transmission lines
DOI:
https://doi.org/10.35699/2316-770X.2019.12703Keywords:
Environmental monitoring, Interaction with society, Wildfire detectionAbstract
Electric networks and transmission lines are many times seen as something hazardous, even when bringing life quality and progress to society. Few people agree to have an electric network or line crossing their lands. The environmental monitoring of electric networks and lines allows society to see in the internet what is happening around electric networks and lines and, hence, promotes a closer relation between society and utilities vital to economic and social development. In this work, the environmental monitoring is made using fire detection, a phenomenon that damages not only electric networks and lines, but also humans, animals and plants around. Such wildfire detection is performed using deep learning, which can achieve precisions of about 99% and detect fire and smoke in adverse situations.
References
DATA SCIENCE ACADEMY. Deep learning book. [2018]. Disponível em: http://deeplearningbook.com.br. Acesso em: 11 nov. 2019.
INPE. [2019]. Disponível em: http://queimadas.dgi.inpe.br/queimadas/portal-static/situa-cao-atual/. Acesso em: 15 nov. 2019.
WWF. Five things you need to know about our living planet in 2018. [2018]. Disponível em: https://www.dw.com/en/five-things-you-need-to-know-about-our-living-planet-in--2018/a-46074931. Acesso em: 15 nov. 2019.
CEMIG. Cemig alerta para aumento de queimadas nesta época do ano. [2017]. Disponível em: ht-tps://www.cemig.com.br/sites/Imprensa/pt-br/Paginas/cemig-queimadas-seguranca--alerta.aspx. Acesso em: 15 nov. 2019.
DIOS, J. R. M. et al. Computer vision techniques for forest fire perception. Image and Vision Compu-ting, v. 26, n. 4, p. 550-562, 2008. DOI: https://doi.org/10.1016/j.imavis.2007.07.002
HOHBERG, S. P. Wildfire smoke detection using convolutional neural networks. 2015. Master Thesis (Master of Science). Fachbereich Mathematik und Informatik, Freie Universitt Berlin, Berlin, 2015.
KONG, S. G. et al. Fast fire flame detection in surveillance video using logistic regression and temporal smoothing. Fire Safety Journal, v. 79, p. 37- 43, 2016. DOI: https://doi.org/10.1016/j.firesaf.2015.11.015
STEFFENS, C. R. Um sistema de detecção de fogo baseado em vídeo. 2015. Dissertação (Mestrado em Engenharia da Computação) – Centro de Ciências Computacionais, Universidade Federal do Rio Grande, Rio Grande, 2015.
VIEIRA, D. A. G. et al. Visão computacional para monitoramento ambiental das áreas cobertas por linhas de transmissão utilizando reconhecimento de padrões. In: CONGRESSO DE INOVAÇÃO TECNOLÓGICA EM ENERGIA ELÉTRICA – CITENEL, 8., 2015, Costa do Sauípe. Anais do CITE-NEL 2015. Brasília, DF: ANEEL – Agência Nacional de Energia Elétrica, 2015. p. 1-8.
Imagenet. [2019]. Disponível em: http://www.image-net.org/challenges/LSVRC/. Acesso em: 15 nov. 2019.
REDMON, J. et al. You only look once: Unified, real-time object detection. In: CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, 2016, Las Vegas. Proceedings of the CVPR 2016. Las Vegas: IEEE, 2016. p. 779-788. DOI: https://doi.org/10.1109/CVPR.2016.91
