Effective Smoke Detection Using Spatial-Temporal Energy and Weber Local Descriptors in Three Orthogonal Planes (WLD-TOP)

Video-based fire detection (VFD) technologies have received significant attention from both academic and industrial communities recently. However, existing VFD approaches are still susceptible to false alarms due to changes in illumination, camera noise, variability of shape, motion, colour, irregul...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ojo, John Adedapo, Oladosu, Jamiu Alabi
Formato: Articulo
Lenguaje:Inglés
Publicado: 2018
Materias:
Ciencias Informáticas
video-based smoke detection
weber local descriptor
three orthogonal planes
dynamic texture descriptors
support vector machine
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/66739
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-66739
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
video-based smoke detection
weber local descriptor
three orthogonal planes
dynamic texture descriptors
support vector machine
spellingShingle Ciencias Informáticas
video-based smoke detection
weber local descriptor
three orthogonal planes
dynamic texture descriptors
support vector machine
Ojo, John Adedapo
Oladosu, Jamiu Alabi
Effective Smoke Detection Using Spatial-Temporal Energy and Weber Local Descriptors in Three Orthogonal Planes (WLD-TOP)
topic_facet Ciencias Informáticas
video-based smoke detection
weber local descriptor
three orthogonal planes
dynamic texture descriptors
support vector machine
description Video-based fire detection (VFD) technologies have received significant attention from both academic and industrial communities recently. However, existing VFD approaches are still susceptible to false alarms due to changes in illumination, camera noise, variability of shape, motion, colour, irregular patterns of smoke and flames, modelling and training inaccuracies. Hence, this work aimed at developing a VSD system that will have a high detection rate, low false-alarm rate and short response time. Moving blocks in video frames were segmented and analysed in HSI colour space, and wavelet energy analysis of the smoke candidate blocks was performed. In addition, Dynamic texture descriptors were obtained using Weber Local Descriptor in Three Orthogonal Planes (WLD-TOP). These features were combined and used as inputs to Support Vector Classifier with radial based kernel function, while post-processing stage employs temporal image filtering to reduce false alarm. The algorithm was implemented in MATLAB 8.1.0.604 (R2013a). Accuracy of 99.30%, detection rate of 99.28% and false alarm rate of 0.65% were obtained when tested with some online videos. The output of this work would find applications in early fire detection systems and other applications such as robot vision and automated inspection.
format Articulo
Articulo
author Ojo, John Adedapo
Oladosu, Jamiu Alabi
author_facet Ojo, John Adedapo
Oladosu, Jamiu Alabi
author_sort Ojo, John Adedapo
title Effective Smoke Detection Using Spatial-Temporal Energy and Weber Local Descriptors in Three Orthogonal Planes (WLD-TOP)
title_short Effective Smoke Detection Using Spatial-Temporal Energy and Weber Local Descriptors in Three Orthogonal Planes (WLD-TOP)
title_full Effective Smoke Detection Using Spatial-Temporal Energy and Weber Local Descriptors in Three Orthogonal Planes (WLD-TOP)
title_fullStr Effective Smoke Detection Using Spatial-Temporal Energy and Weber Local Descriptors in Three Orthogonal Planes (WLD-TOP)
title_full_unstemmed Effective Smoke Detection Using Spatial-Temporal Energy and Weber Local Descriptors in Three Orthogonal Planes (WLD-TOP)
title_sort effective smoke detection using spatial-temporal energy and weber local descriptors in three orthogonal planes (wld-top)
publishDate 2018
url http://sedici.unlp.edu.ar/handle/10915/66739
work_keys_str_mv AT ojojohnadedapo effectivesmokedetectionusingspatialtemporalenergyandweberlocaldescriptorsinthreeorthogonalplaneswldtop
AT oladosujamiualabi effectivesmokedetectionusingspatialtemporalenergyandweberlocaldescriptorsinthreeorthogonalplaneswldtop
bdutipo_str Repositorios
_version_ 1764820480551813123

Ejemplares similares