Deep Convolutional Neural Network for Fire Detection

Aim:

          To efficient RCNN based system for fire detection in videos captured in uncertain surveillance scenarios

Synopsis:

          Vision based fire detection framework has lately picked up popularity when contrasted with customary fire  recognition framework dependent on sensors. The need of  video perception at private, Modern, business regions and  woods areas has expanded the use of vision based fire  acknowledgment system Recently lots of fire related accidents  has occurred due to improper Surveillance or unable to cover  those uncertain regions like restricted areas in forest or any  factory buildings. In order to overcome such accidents , we  propose a new method using Convolutional neural networks (RCNN).

Proposed System

          We propose an efficient RCNN based system for fire detection in videos captured in uncertain surveillance scenarios. Our approach uses light-weight deep neural networks with no dense fully connected layers, making it computationally inexpensive. Once detect a fire the information will pass through the firebase. Firebase is a one type of database. Then the firebase to send  a notification in android smartphone.