Automatic Handgun Detection with Deep Learning in Video Surveillance Images

There is a great need to implement preventive mechanisms against shootings and terrorist acts in public spaces with a large influx of people. While surveillance cameras have become common, the need for monitoring 24/7 and real-time response requires automatic detection methods. This paper presents a...

Descripción completa

Detalles Bibliográficos
Autores: Salido Tercero, Jesús, Lomas, Vanesa, Ruiza-Santaquiteria Alegre, Jesús, Deniz, Oscar
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Universidad de Castilla-La Mancha
Repositorio:RUIdeRA. Repositorio Institucional de la UCLM
OAI Identifier:oai:ruidera.uclm.es:10578/38096
Acceso en línea:https://hdl.handle.net/10578/38096
Access Level:acceso abierto
Palabra clave:Building automation
Computer vision
Deep learning
Gun detection
Terrorism
Weapon detection
id ES_ce9e29caa31cb845a59e0d4dca1db623
oai_identifier_str oai:ruidera.uclm.es:10578/38096
network_acronym_str ES
network_name_str España
repository_id_str
spelling Automatic Handgun Detection with Deep Learning in Video Surveillance ImagesSalido Tercero, JesúsLomas, VanesaRuiza-Santaquiteria Alegre, JesúsDeniz, OscarBuilding automationComputer visionDeep learningGun detectionTerrorismWeapon detectionThere is a great need to implement preventive mechanisms against shootings and terrorist acts in public spaces with a large influx of people. While surveillance cameras have become common, the need for monitoring 24/7 and real-time response requires automatic detection methods. This paper presents a study based on three convolutional neural network (CNN) models applied to the automatic detection of handguns in video surveillance images. It aims to investigate the reduction of false positives by including pose information associated with the way the handguns are held in the images belonging to the training dataset. The results highlighted the best average precision (96.36%) and recall (97.23%) obtained by RetinaNet fine-tuned with the unfrozen ResNet-50 backbone and the best precision (96.23%) and F1 score values (93.36%) obtained by YOLOv3 when it was trained on the dataset including pose information. This last architecture was the only one that showed a consistent improvement—around 2%—when pose information was expressly considered during training.MDPI202420242021info:eu-repo/semantics/articleapplication/pdfapplication/pdfhttps://hdl.handle.net/10578/38096reponame:RUIdeRA. Repositorio Institucional de la UCLMinstname:Universidad de Castilla-La ManchaInglésinfo:eu-repo/semantics/openAccessoai:ruidera.uclm.es:10578/380962026-05-27T07:36:41Z
dc.title.none.fl_str_mv Automatic Handgun Detection with Deep Learning in Video Surveillance Images
title Automatic Handgun Detection with Deep Learning in Video Surveillance Images
spellingShingle Automatic Handgun Detection with Deep Learning in Video Surveillance Images
Salido Tercero, Jesús
Building automation
Computer vision
Deep learning
Gun detection
Terrorism
Weapon detection
title_short Automatic Handgun Detection with Deep Learning in Video Surveillance Images
title_full Automatic Handgun Detection with Deep Learning in Video Surveillance Images
title_fullStr Automatic Handgun Detection with Deep Learning in Video Surveillance Images
title_full_unstemmed Automatic Handgun Detection with Deep Learning in Video Surveillance Images
title_sort Automatic Handgun Detection with Deep Learning in Video Surveillance Images
dc.creator.none.fl_str_mv Salido Tercero, Jesús
Lomas, Vanesa
Ruiza-Santaquiteria Alegre, Jesús
Deniz, Oscar
author Salido Tercero, Jesús
author_facet Salido Tercero, Jesús
Lomas, Vanesa
Ruiza-Santaquiteria Alegre, Jesús
Deniz, Oscar
author_role author
author2 Lomas, Vanesa
Ruiza-Santaquiteria Alegre, Jesús
Deniz, Oscar
author2_role author
author
author
dc.subject.none.fl_str_mv Building automation
Computer vision
Deep learning
Gun detection
Terrorism
Weapon detection
topic Building automation
Computer vision
Deep learning
Gun detection
Terrorism
Weapon detection
description There is a great need to implement preventive mechanisms against shootings and terrorist acts in public spaces with a large influx of people. While surveillance cameras have become common, the need for monitoring 24/7 and real-time response requires automatic detection methods. This paper presents a study based on three convolutional neural network (CNN) models applied to the automatic detection of handguns in video surveillance images. It aims to investigate the reduction of false positives by including pose information associated with the way the handguns are held in the images belonging to the training dataset. The results highlighted the best average precision (96.36%) and recall (97.23%) obtained by RetinaNet fine-tuned with the unfrozen ResNet-50 backbone and the best precision (96.23%) and F1 score values (93.36%) obtained by YOLOv3 when it was trained on the dataset including pose information. This last architecture was the only one that showed a consistent improvement—around 2%—when pose information was expressly considered during training.
publishDate 2021
dc.date.none.fl_str_mv 2021
2024
2024
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/10578/38096
url https://hdl.handle.net/10578/38096
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:RUIdeRA. Repositorio Institucional de la UCLM
instname:Universidad de Castilla-La Mancha
instname_str Universidad de Castilla-La Mancha
reponame_str RUIdeRA. Repositorio Institucional de la UCLM
collection RUIdeRA. Repositorio Institucional de la UCLM
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869420007485603840
score 15.812429

Similares en LA Referencia