Open AccessA Robust and Dynamic Fire Detection Algorithm using Convolutional Neural Network
Author(s) -
K.Sivasankari,
Shubham Singh,
Kanhaiya Kumar,
Aman Dubey
Publication year - 2021
Publication title -
indian journal of image processing and recognition (ijipr)
Language(s) - English
Resource type - Journals
ISSN - 2582-8037
DOI - 10.54105/ijipr.b1007.061221
Subject(s) - fire detection , smoke , convolutional neural network , computer science , artificial intelligence , preprocessor , process (computing) , set (abstract data type) , pattern recognition (psychology) , data set , algorithm , engineering , architectural engineering , programming language , operating system , waste management
he major part of the underlying idea is going to detect the fire from upcoming smoke and the shade color of the smoke using convolutional neural network. The fire detection followed by the smoke detection is going to depend on the shade and the direction vector analysis in this paper. Image processing from the available set of data is very vague ideation so in order to strengthen the idea we are incorporating two main features that is the smoke shade and direction vector. For this major process we will involve data preprocessing through bi-variate hypothesis to select two variables as the color of smoke and the direction of the smoke and hence do the further analysis on other features that how are they going to help in the upcoming detection neurons for the robust algorithm of fire detection.