Deep social force network for anomaly event detection

Abstract Anomaly event detection is vital in surveillance video analysis. However, how to learn the discriminative motion in the crowd scene is still not tackled. Here, a deep social force network by exploiting both social force extracting and deep motion coding is proposed. Given a grid of particle...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xingming Yang, Zhiming Wang, Kewei Wu, Zhao Xie, Jinkui Hou
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Photography TR1-1050 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/f9b737b35a6a4726b5ad426c877f8b3f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f9b737b35a6a4726b5ad426c877f8b3f
record_format	dspace
spelling	oai:doaj.org-article:f9b737b35a6a4726b5ad426c877f8b3f2021-11-29T03:38:16ZDeep social force network for anomaly event detection1751-96671751-965910.1049/ipr2.12299https://doaj.org/article/f9b737b35a6a4726b5ad426c877f8b3f2021-12-01T00:00:00Zhttps://doi.org/10.1049/ipr2.12299https://doaj.org/toc/1751-9659https://doaj.org/toc/1751-9667Abstract Anomaly event detection is vital in surveillance video analysis. However, how to learn the discriminative motion in the crowd scene is still not tackled. Here, a deep social force network by exploiting both social force extracting and deep motion coding is proposed. Given a grid of particles with velocity provided by the optical flow, the interaction force in the crowd scene is investigated and a social force module is embedded in a deep network. A deep motion convolution was further designed with a 3D (DMC‐3D) module. The DMC‐3D not only eliminates the noise motion in the crowd scene with a spatial encoder–decoder but also learns the 3D feature with a spatio‐temporal encoder. The deep social force coding is modelled with multiple features, in which each feature can describe specific anomaly motion. The experiments on UCF‐Crime and ShanghaiTech datasets demonstrate that our method can predict the temporal localization of anomaly events and outperform the state‐of‐the‐art methods.Xingming YangZhiming WangKewei WuZhao XieJinkui HouWileyarticlePhotographyTR1-1050Computer softwareQA76.75-76.765ENIET Image Processing, Vol 15, Iss 14, Pp 3441-3453 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Photography TR1-1050 Computer software QA76.75-76.765
spellingShingle	Photography TR1-1050 Computer software QA76.75-76.765 Xingming Yang Zhiming Wang Kewei Wu Zhao Xie Jinkui Hou Deep social force network for anomaly event detection
description	Abstract Anomaly event detection is vital in surveillance video analysis. However, how to learn the discriminative motion in the crowd scene is still not tackled. Here, a deep social force network by exploiting both social force extracting and deep motion coding is proposed. Given a grid of particles with velocity provided by the optical flow, the interaction force in the crowd scene is investigated and a social force module is embedded in a deep network. A deep motion convolution was further designed with a 3D (DMC‐3D) module. The DMC‐3D not only eliminates the noise motion in the crowd scene with a spatial encoder–decoder but also learns the 3D feature with a spatio‐temporal encoder. The deep social force coding is modelled with multiple features, in which each feature can describe specific anomaly motion. The experiments on UCF‐Crime and ShanghaiTech datasets demonstrate that our method can predict the temporal localization of anomaly events and outperform the state‐of‐the‐art methods.
format	article
author	Xingming Yang Zhiming Wang Kewei Wu Zhao Xie Jinkui Hou
author_facet	Xingming Yang Zhiming Wang Kewei Wu Zhao Xie Jinkui Hou
author_sort	Xingming Yang
title	Deep social force network for anomaly event detection
title_short	Deep social force network for anomaly event detection
title_full	Deep social force network for anomaly event detection
title_fullStr	Deep social force network for anomaly event detection
title_full_unstemmed	Deep social force network for anomaly event detection
title_sort	deep social force network for anomaly event detection
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/f9b737b35a6a4726b5ad426c877f8b3f
work_keys_str_mv	AT xingmingyang deepsocialforcenetworkforanomalyeventdetection AT zhimingwang deepsocialforcenetworkforanomalyeventdetection AT keweiwu deepsocialforcenetworkforanomalyeventdetection AT zhaoxie deepsocialforcenetworkforanomalyeventdetection AT jinkuihou deepsocialforcenetworkforanomalyeventdetection
_version_	1718407685586550784

Deep social force network for anomaly event detection

Ejemplares similares