Smoke detection using simplified descriptors of video information

Automatic visual detection of smoke in confined or open spaces is overriding to issue early warnings that can save lives or prevent irreparable damage. While fire presents a range of characteristic colour, smoke does not present a readily apparent pattern. Changes its shape, does not contain clear e...

Descripción completa

Detalles Bibliográficos
Autores principales: Monte, Gustavo, Marasco, Damian, Pastore, Juan Ignacio, Liscovsky, Pablo, Ballarin, Virginia
Formato: Artículo acceptedVersion
Lenguaje:Inglés
Inglés
Publicado: 2023
Materias:
—smoke detection; real time; embedded systems; video processing; image representation
Acceso en línea:http://hdl.handle.net/20.500.12272/8087
Aporte de:
RIA - Repositorio Institucional Abierto (UTN) de Universidad Tecnológica Nacional
id I68-R174-20.500.12272-8087
record_format dspace
spelling I68-R174-20.500.12272-80872023-06-22T13:40:07Z Smoke detection using simplified descriptors of video information Monte, Gustavo Marasco, Damian Pastore, Juan Ignacio Liscovsky, Pablo Ballarin, Virginia —smoke detection; real time; embedded systems; video processing; image representation Automatic visual detection of smoke in confined or open spaces is overriding to issue early warnings that can save lives or prevent irreparable damage. While fire presents a range of characteristic colour, smoke does not present a readily apparent pattern. Changes its shape, does not contain clear edges, presents a chaotic behaviour and colour manifests from white to black, including all nuances. This paper presents an algorithm that efficiently pre-process a frame that extracts the main component of information, decreasing orders of magnitude the source size. From this new structure, algorithms based on the temporal and spatial change of subsets of the new structure are applied. Decision is based on fusion of weak classifiers. The algorithms are described and validated with experimental results of real-time detection for open and confined spaces, considering simplicity and efficiency of the proposed method suitable for embedded systems. Fil: Monte, Gustavo. Universidad Tecnológica Nacional. Facultad Regional Del Neuquen ; Argentina. Fil: Marasc, Damian. Universidad Tecnológica Nacional. Facultad Regional Del Neuquen ; Argentina. Fil: Liscovsky, Pablo. Universidad Tecnológica Nacional. Facultad Regional Del Neuquen ; Argentina. Fil: Ballarin, Virginia. Universidad Nacional de Mar del Plata. Facultad de Ingeniera; Argentina. Fil: Pastore, Juan Ignacio. Universidad Nacional de Mar del Plata. Facultad de Ingeniera; CONICET; Argentina. Peer Reviewed 2023-06-22T13:40:07Z 2023-06-22T13:40:07Z 2017-03-22 info:eu-repo/semantics/article acceptedVersion http://hdl.handle.net/20.500.12272/8087 101109 eng eng openAccess http://creativecommons.org/licenses/by-nc-nd/4.0/ Attribution-NonCommercial-NoDerivatives 4.0 Internacional creative commos pdf
institution Universidad Tecnológica Nacional
institution_str I-68
repository_str R-174
collection RIA - Repositorio Institucional Abierto (UTN)
language Inglés
Inglés
topic —smoke detection; real time; embedded systems; video processing; image representation
spellingShingle —smoke detection; real time; embedded systems; video processing; image representation
Monte, Gustavo
Marasco, Damian
Pastore, Juan Ignacio
Liscovsky, Pablo
Ballarin, Virginia
Smoke detection using simplified descriptors of video information
topic_facet —smoke detection; real time; embedded systems; video processing; image representation
description Automatic visual detection of smoke in confined or open spaces is overriding to issue early warnings that can save lives or prevent irreparable damage. While fire presents a range of characteristic colour, smoke does not present a readily apparent pattern. Changes its shape, does not contain clear edges, presents a chaotic behaviour and colour manifests from white to black, including all nuances. This paper presents an algorithm that efficiently pre-process a frame that extracts the main component of information, decreasing orders of magnitude the source size. From this new structure, algorithms based on the temporal and spatial change of subsets of the new structure are applied. Decision is based on fusion of weak classifiers. The algorithms are described and validated with experimental results of real-time detection for open and confined spaces, considering simplicity and efficiency of the proposed method suitable for embedded systems.
format Artículo
acceptedVersion
author Monte, Gustavo
Marasco, Damian
Pastore, Juan Ignacio
Liscovsky, Pablo
Ballarin, Virginia
author_facet Monte, Gustavo
Marasco, Damian
Pastore, Juan Ignacio
Liscovsky, Pablo
Ballarin, Virginia
author_sort Monte, Gustavo
title Smoke detection using simplified descriptors of video information
title_short Smoke detection using simplified descriptors of video information
title_full Smoke detection using simplified descriptors of video information
title_fullStr Smoke detection using simplified descriptors of video information
title_full_unstemmed Smoke detection using simplified descriptors of video information
title_sort smoke detection using simplified descriptors of video information
publishDate 2023
url http://hdl.handle.net/20.500.12272/8087
work_keys_str_mv AT montegustavo smokedetectionusingsimplifieddescriptorsofvideoinformation
AT marascodamian smokedetectionusingsimplifieddescriptorsofvideoinformation
AT pastorejuanignacio smokedetectionusingsimplifieddescriptorsofvideoinformation
AT liscovskypablo smokedetectionusingsimplifieddescriptorsofvideoinformation
AT ballarinvirginia smokedetectionusingsimplifieddescriptorsofvideoinformation
_version_ 1769989305007079424

Ejemplares similares