Cargando…

Research on Anomaly Detection of Surveillance Video Based on Branch-Fusion Net and CSAM

As the monitor probes are used more and more widely these days, the task of detecting abnormal behaviors in surveillance videos has gained widespread attention. The generalization ability and parameter overhead of the model affect how accurate the detection result is. To deal with the poor generaliz...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Pengjv, Lu, Yuanyao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9919792/
https://www.ncbi.nlm.nih.gov/pubmed/36772423
http://dx.doi.org/10.3390/s23031385
_version_ 1784886911727304704
author Zhang, Pengjv
Lu, Yuanyao
author_facet Zhang, Pengjv
Lu, Yuanyao
author_sort Zhang, Pengjv
collection PubMed
description As the monitor probes are used more and more widely these days, the task of detecting abnormal behaviors in surveillance videos has gained widespread attention. The generalization ability and parameter overhead of the model affect how accurate the detection result is. To deal with the poor generalization ability and high parameter overhead of the model in existing anomaly detection methods, we propose a three-dimensional multi-branch convolutional fusion network, named “Branch-Fusion Net”. The network is designed with a multi-branch structure not only to significantly reduce parameter overhead but also to improve the generalization ability by understanding the input feature map from different perspectives. To ignore useless features during the model training, we propose a simple yet effective Channel Spatial Attention Module (CSAM), which sequentially focuses attention on key channels and spatial feature regions to suppress useless features and enhance important features. We combine the Branch-Fusion Net and the CSAM as a local feature extraction network and use the Bi-Directional Gated Recurrent Unit (Bi-GRU) to extract global feature information. The experiments are validated on a self-built Crimes-mini dataset, and the accuracy of anomaly detection in surveillance videos reaches 93.55% on the test set. The result shows that the model proposed in the paper significantly improves the accuracy of anomaly detection in surveillance videos with low parameter overhead.
format Online
Article
Text
id pubmed-9919792
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-99197922023-02-12 Research on Anomaly Detection of Surveillance Video Based on Branch-Fusion Net and CSAM Zhang, Pengjv Lu, Yuanyao Sensors (Basel) Article As the monitor probes are used more and more widely these days, the task of detecting abnormal behaviors in surveillance videos has gained widespread attention. The generalization ability and parameter overhead of the model affect how accurate the detection result is. To deal with the poor generalization ability and high parameter overhead of the model in existing anomaly detection methods, we propose a three-dimensional multi-branch convolutional fusion network, named “Branch-Fusion Net”. The network is designed with a multi-branch structure not only to significantly reduce parameter overhead but also to improve the generalization ability by understanding the input feature map from different perspectives. To ignore useless features during the model training, we propose a simple yet effective Channel Spatial Attention Module (CSAM), which sequentially focuses attention on key channels and spatial feature regions to suppress useless features and enhance important features. We combine the Branch-Fusion Net and the CSAM as a local feature extraction network and use the Bi-Directional Gated Recurrent Unit (Bi-GRU) to extract global feature information. The experiments are validated on a self-built Crimes-mini dataset, and the accuracy of anomaly detection in surveillance videos reaches 93.55% on the test set. The result shows that the model proposed in the paper significantly improves the accuracy of anomaly detection in surveillance videos with low parameter overhead. MDPI 2023-01-26 /pmc/articles/PMC9919792/ /pubmed/36772423 http://dx.doi.org/10.3390/s23031385 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zhang, Pengjv
Lu, Yuanyao
Research on Anomaly Detection of Surveillance Video Based on Branch-Fusion Net and CSAM
title Research on Anomaly Detection of Surveillance Video Based on Branch-Fusion Net and CSAM
title_full Research on Anomaly Detection of Surveillance Video Based on Branch-Fusion Net and CSAM
title_fullStr Research on Anomaly Detection of Surveillance Video Based on Branch-Fusion Net and CSAM
title_full_unstemmed Research on Anomaly Detection of Surveillance Video Based on Branch-Fusion Net and CSAM
title_short Research on Anomaly Detection of Surveillance Video Based on Branch-Fusion Net and CSAM
title_sort research on anomaly detection of surveillance video based on branch-fusion net and csam
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9919792/
https://www.ncbi.nlm.nih.gov/pubmed/36772423
http://dx.doi.org/10.3390/s23031385
work_keys_str_mv AT zhangpengjv researchonanomalydetectionofsurveillancevideobasedonbranchfusionnetandcsam
AT luyuanyao researchonanomalydetectionofsurveillancevideobasedonbranchfusionnetandcsam