Early fire detection using convolutional neural networks during surveillance for effective disaster management
Early fire detection using convolutional neural networks during surveillance for effective disaster management
Khan Muhammad,Jamil Ahmad,S. Baik
2017 · DOI: 10.1016/j.neucom.2017.04.083
Neurocomputing · 464 Citations
TLDR
An early fire detection framework using fine-tuned convolutional neural networks for CCTV surveillance cameras, which can detect fire in varying indoor and outdoor environments is proposed and an adaptive prioritization mechanism for cameras in the surveillance system is proposed to ensure the autonomous response.