DeepGun: Deep Feature-Driven One-Class Classifier for Firearm Detection Using Visual Gun Features and Human Body Pose Estimation

The increasing frequency of mass shootings at public events and public buildings underscores the limitations of traditional surveillance systems, which rely on human operators monitoring multiple screens. Delayed response times often hinder security teams from intervening before an attack unfolds. S...

ver descrição completa

Detalhes bibliográficos
Autores: Singh, Harbinder, Muñoz Navarrete, Juan Daniel, Déniz Suárez, Óscar, Ruiz-Santaquiteria Alegre, Jesús, Bueno García, María Gloria
Formato: artículo
Fecha de publicación:2025
País:España
Recursos:Universidad de Castilla-La Mancha
Repositorio:RUIdeRA. Repositorio Institucional de la UCLM
OAI Identifier:oai:ruidera.uclm.es:10578/46296
Acesso em linha:http://dx.doi.org/10.3390/app15115830
https://hdl.handle.net/10578/46296
Access Level:acceso abierto
Palavra-chave:Anomaly
Deep learning
Human action recognition
One-class classifiers
Surveillance
id ES_1e9b594365911c6cd12e98ebbc8a8d70
oai_identifier_str oai:ruidera.uclm.es:10578/46296
network_acronym_str ES
network_name_str España
repository_id_str
spelling DeepGun: Deep Feature-Driven One-Class Classifier for Firearm Detection Using Visual Gun Features and Human Body Pose EstimationSingh, HarbinderMuñoz Navarrete, Juan DanielDéniz Suárez, ÓscarRuiz-Santaquiteria Alegre, JesúsBueno García, María GloriaAnomalyDeep learningHuman action recognitionOne-class classifiersSurveillanceThe increasing frequency of mass shootings at public events and public buildings underscores the limitations of traditional surveillance systems, which rely on human operators monitoring multiple screens. Delayed response times often hinder security teams from intervening before an attack unfolds. Since firearms are rarely seen in public spaces and constitute anomalous observations, firearm detection can be considered as an anomaly detection (AD) problem, for which one-class classifiers (OCCs) are well-suited. To address this challenge, we propose a holistic firearm detection approach that integrates OCCs with visual hand-held gun features and human pose estimation (HPE). In the first stage, a variational autoencoder (VAE) learns latent representations of firearm-related instances, ensuring that the latent space is dedicated exclusively to the target class. Hand patches of variable sizes are extracted from each frame using body landmarks, dynamically adjusting based on the subject’s distance from the camera. In the second stage, a unified feature vector is generated by integrating VAE-extracted latent features with landmark-based arm positioning features. Finally, an isolation forest (IFC)-based OCC model evaluates this unified feature representation to estimate the probability that a test sample belongs to the firearm-related distribution. By utilizing skeletal representations of human actions, our approach overcomes the limitations of appearance-based gun features extracted by camera, which are often affected by background variations. Experimental results on diverse firearm datasets validate the effectiveness of our anomaly detection approach, achieving an F1-score of 86.6%, accuracy of 85.2%, precision of 95.3%, recall of 74.0%, and average precision (AP) of 83.5%. These results demonstrate the superiority of our method over traditional approaches that rely solely on visual features.MDPI202620262025info:eu-repo/semantics/articleapplication/pdfapplication/pdfhttp://dx.doi.org/10.3390/app15115830https://hdl.handle.net/10578/46296reponame:RUIdeRA. Repositorio Institucional de la UCLMinstname:Universidad de Castilla-La ManchaInglésHorizon Europe dAIEdge Grant n. 101120726SBPLY/21/180501/000025info:eu-repo/semantics/openAccessoai:ruidera.uclm.es:10578/462962026-05-27T07:36:41Z
dc.title.none.fl_str_mv DeepGun: Deep Feature-Driven One-Class Classifier for Firearm Detection Using Visual Gun Features and Human Body Pose Estimation
title DeepGun: Deep Feature-Driven One-Class Classifier for Firearm Detection Using Visual Gun Features and Human Body Pose Estimation
spellingShingle DeepGun: Deep Feature-Driven One-Class Classifier for Firearm Detection Using Visual Gun Features and Human Body Pose Estimation
Singh, Harbinder
Anomaly
Deep learning
Human action recognition
One-class classifiers
Surveillance
title_short DeepGun: Deep Feature-Driven One-Class Classifier for Firearm Detection Using Visual Gun Features and Human Body Pose Estimation
title_full DeepGun: Deep Feature-Driven One-Class Classifier for Firearm Detection Using Visual Gun Features and Human Body Pose Estimation
title_fullStr DeepGun: Deep Feature-Driven One-Class Classifier for Firearm Detection Using Visual Gun Features and Human Body Pose Estimation
title_full_unstemmed DeepGun: Deep Feature-Driven One-Class Classifier for Firearm Detection Using Visual Gun Features and Human Body Pose Estimation
title_sort DeepGun: Deep Feature-Driven One-Class Classifier for Firearm Detection Using Visual Gun Features and Human Body Pose Estimation
dc.creator.none.fl_str_mv Singh, Harbinder
Muñoz Navarrete, Juan Daniel
Déniz Suárez, Óscar
Ruiz-Santaquiteria Alegre, Jesús
Bueno García, María Gloria
author Singh, Harbinder
author_facet Singh, Harbinder
Muñoz Navarrete, Juan Daniel
Déniz Suárez, Óscar
Ruiz-Santaquiteria Alegre, Jesús
Bueno García, María Gloria
author_role author
author2 Muñoz Navarrete, Juan Daniel
Déniz Suárez, Óscar
Ruiz-Santaquiteria Alegre, Jesús
Bueno García, María Gloria
author2_role author
author
author
author
dc.subject.none.fl_str_mv Anomaly
Deep learning
Human action recognition
One-class classifiers
Surveillance
topic Anomaly
Deep learning
Human action recognition
One-class classifiers
Surveillance
description The increasing frequency of mass shootings at public events and public buildings underscores the limitations of traditional surveillance systems, which rely on human operators monitoring multiple screens. Delayed response times often hinder security teams from intervening before an attack unfolds. Since firearms are rarely seen in public spaces and constitute anomalous observations, firearm detection can be considered as an anomaly detection (AD) problem, for which one-class classifiers (OCCs) are well-suited. To address this challenge, we propose a holistic firearm detection approach that integrates OCCs with visual hand-held gun features and human pose estimation (HPE). In the first stage, a variational autoencoder (VAE) learns latent representations of firearm-related instances, ensuring that the latent space is dedicated exclusively to the target class. Hand patches of variable sizes are extracted from each frame using body landmarks, dynamically adjusting based on the subject’s distance from the camera. In the second stage, a unified feature vector is generated by integrating VAE-extracted latent features with landmark-based arm positioning features. Finally, an isolation forest (IFC)-based OCC model evaluates this unified feature representation to estimate the probability that a test sample belongs to the firearm-related distribution. By utilizing skeletal representations of human actions, our approach overcomes the limitations of appearance-based gun features extracted by camera, which are often affected by background variations. Experimental results on diverse firearm datasets validate the effectiveness of our anomaly detection approach, achieving an F1-score of 86.6%, accuracy of 85.2%, precision of 95.3%, recall of 74.0%, and average precision (AP) of 83.5%. These results demonstrate the superiority of our method over traditional approaches that rely solely on visual features.
publishDate 2025
dc.date.none.fl_str_mv 2025
2026
2026
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://dx.doi.org/10.3390/app15115830
https://hdl.handle.net/10578/46296
url http://dx.doi.org/10.3390/app15115830
https://hdl.handle.net/10578/46296
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Horizon Europe dAIEdge Grant n. 101120726
SBPLY/21/180501/000025
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_ 1869404351046352896
score 15,811543

Registos relacionados