• Sirigandam Umamaheshwari
• Bandi Jhansi
• Konda Mahathi
• K Karunakar

Fire disasters can be both manufactured and naturally occurred, but most of them are man-made disasters. Fire disasters result in huge losses both economically and ecologically. We need an early fire detection system, that produces an autonomous response and helps in the early detection of disaster occurrence. Therefore, we propose an early fire detection framework using convolutional neural networks (CNN) for cameras, which detect fire in varying indoor and outdoor environments. In such cases, if the surveillance area is too large such as large buildings, complex spaces, or it would be tough to feature recognition. Applying the convolutional neural network (CNN) technology to image recognition can avoid randomness to a large extent in the feature extraction process. To ensure the autonomous response, we propose an efficient mechanism for cameras in the surveillance system.

Images, deep learning, disaster management, Fire detection.

"Early Fire Detection System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 6, page no.a759-a763, June-2021, Available :http://www.jetir.org/papers/JETIR2106105.pdf

"Early Fire Detection System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 6, page no. ppa759-a763, June-2021, Available at : http://www.jetir.org/papers/JETIR2106105.pdf