ResNet-50 based fire and smoke images classification

Fires are becoming a greater threat to people's lives, property, and the environment. Image technologies, as compared to traditional fire detection approaches, hold a lot of promise for overcoming the problem of a high false alarm rate. However, one of the key drawbacks of these systems is thei...

Full description

Saved in:
Bibliographic Details
Main Authors: Jabnouni, Hedi, Arfaoui, Imen, Cherni, Mohamed Ali, Bouchouicha, Moez, Sayadi, Mounir
Format: Conference Proceeding
Language:English
Subjects:
Classification algorithms
Convolution
Convolutional neural network
Fire and smoke images
Heuristic algorithms
Image classification
Image recognition
Neural networks
resnet-50
Transfer learning
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fires are becoming a greater threat to people's lives, property, and the environment. Image technologies, as compared to traditional fire detection approaches, hold a lot of promise for overcoming the problem of a high false alarm rate. However, one of the key drawbacks of these systems is their time-consuming and labor-intensive creation. In fact, multi-feature techniques, such as chromatic characteristics, dynamic features, texture features, and contour features, are frequently used to create implemented algorithms. Therefore, we provide, in this paper, a study of some transfer learning model, and we compare it to a proposed model based on convolution neural network (CNN) algorithm. To do this, we consider a proper database composed by a total of 28334 images classified into three categories: 7329 fire images, 9205 smoke images and 11800 other images.
ISSN:2687-878X
DOI:10.1109/ATSIP55956.2022.9805875