A Prefatory Approach Towards Monitoring and Detection of Fire Outbreak Using Artificial Neural Network

Abstract

Fire incidents had always been a primary concern in domestic and industrial properties, buildings, sites and offices. The end results of fire outbreaks can be exceedingly devastating and usually amount to serious losses of lives and properties. They also consist of alarm circuits and some manual call points often referred to as detection zones. Recent researches on fire related systems which are adaptations of the conventional fire systems, have dwelt comprehensively on technologies that can provide possible fire detection services by the integration of sensors that are capable of reacting to certain fire based parameters such as rise in temperature/heat, accumulation of pressure, smoke and other combustible elements etc.. The perceived setback of these sensors is that they need considerable time for responding as they require product of fire (e.g., smoke, temperature etc.) to reach the sensors. However, as computing power increases, and its effect is felt across most spheres of human existence, artificial intelligence based systems have been in the fore front of the discourse due to its ability to adequately minimize or exclude human involvement in most emergency or delicate activities. Therefore, implementing a computer vision-based fire monitoring and detection system using low cost surveillance cameras and artificial neural network is proposed and will sufficiently enhance the ability to monitor, detect and generally manage fire outbreaks in deployed buildings. The proposed system seek to significantly provide a more precise and accurate tool for the detection of fire situations and sufficiently eliminate the tendency for false fire alarms since it will be dependent on convolutional neural network trained with captured frames of video images of fire in order to accurately tell a fire situation. The primary purpose of this study is to develop an intelligent system for monitoring and detection of fire outbreak using computer vision and artificial neural network. Other objectives include: to develop a suitable neural network upon which the model will be trained and to implement the model using python programming language..The technology adopted in this study is expected to perform better unlike the conventional fire detection and alarm systems which are heavily reliant on sensors that are only effective with proximity and location of use.