Fire Detection in Video Stream by Using Simple Artificial Neural Network

Abstract

This paper deals with the preliminary research of the fire detection in a video stream. Early fire detection can save lives and properties from huge losses and damages. Therefore the surveillance of the areas is necessary. Early fire discovery with high accuracy, i.e. a low number of false positive or false negative cases, is essential in any environment, especially in places with the high motion of people. The traditional fire detection sensors have some drawbacks: they need separate systems and infrastructure to be implemented, to use sensors in the case of the industrial environment with open fire technologies is often impossible, and others. The fire detection in a video stream is one of the possible and feasible solutions suitable for replacement or supplement of conventional fire detection sensors without a need for installation a huge infrastructure. The paper provides the state of the art in the fire detection. The following part of the paper proposes the new system of feature extraction and describes the feedforward neural network which was used for the training and testing of the proposed idea. The promising results are presented with over 93% accuracy on a selected dataset of movies which consist of more and highly varied instances than published by other researchers involved in the fire detection field. The structure of the neural networks promises higher computational speed than currently implemented deep learning systems.

Control of Acoustic Extinguisher with Deep Neural Networks for Fire Detection

“…Classical sensors may not always be highly efficient, thus the development of more advanced methods for fire detection is necessary. Artificial Neural Networks (ANN) are very efficient in finding various burning objects by analysing images from thermal cameras [17], [18] and can be used successfully to detect fire [19], [20]. They can replace any expensive sensors by just using a surveillance system.…”

A Review of Environmentally Friendly Approaches in Fire Extinguishing: From Chemical Sciences to Innovations in Electrical Engineering

“…The velocity of air movement at the edge of the flames increases, while the density of the acoustic jet affects the operating range of the acoustic extinguisher. This paper demonstrated the feasibility of using Deep Neural Networks for flame detection based on learning from images or video streams [ 55 , 56 , 57 , 58 , 59 , 60 ]. Such a system, consisting of a computer module, a USB camera, and a Movidius stick vision processing unit, may be connected to an acoustic fire extinguisher and can allow it to be activated when the flames are detected.…”

Analysis of Flame Suppression Capabilities Using Low-Frequency Acoustic Waves and Frequency Sweeping Techniques

“…A recent scientific novelty is the use of neural networks for flame detection and wireless links for communication with the extinguishing system (innovation), thanks to which-in the case of flame detection-the extinguishing system can switch on automatically. In this respect, numerous studies and works on image recognition as well as robotics and teletransmission are important [16][17][18][19][20][21][22][23][24][25]. Moreover, intensive scientific development has made it possible to use modulated waves as well as unmodulated waveforms to extinguish flames.…”