Live Spoofing Detection for Automatic Human Activity Recognition Applications

Human Activity Recognition (HAR) has become increasingly crucial in several applications, ranging from motion-driven virtual games to automated video surveillance systems. In these applications, sensors such as smart phone cameras, web cameras or CCTV cameras are used for detecting and tracking phys...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Viktor Dénes Huszár, Vamsi Kiran Adhikarla
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep learning human activity recognition spoof detection spoof attack database security smart cities Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/3a2f0617f97245988fedbf630bee9811
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3a2f0617f97245988fedbf630bee9811
record_format	dspace
spelling	oai:doaj.org-article:3a2f0617f97245988fedbf630bee98112021-11-11T19:16:59ZLive Spoofing Detection for Automatic Human Activity Recognition Applications10.3390/s212173391424-8220https://doaj.org/article/3a2f0617f97245988fedbf630bee98112021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7339https://doaj.org/toc/1424-8220Human Activity Recognition (HAR) has become increasingly crucial in several applications, ranging from motion-driven virtual games to automated video surveillance systems. In these applications, sensors such as smart phone cameras, web cameras or CCTV cameras are used for detecting and tracking physical activities of users. Inevitably, spoof detection in HAR is essential to prevent anomalies and false alarms. To this end, we propose a deep learning based approach that can be used to detect spoofing in various fields such as border control, institutional security and public safety by surveillance cameras. Specifically, in this work, we address the problem of detecting spoofing occurring from video replay attacks, which is more common in such applications. We present a new database containing several videos of users juggling a football, captured under different lighting conditions and using different display and capture devices. We train our models using this database and the proposed system is capable of running in parallel with the HAR algorithms in real-time. Our experimental results show that our approach precisely detects video replay spoofing attacks and generalizes well, even to other applications such as spoof detection in face biometric authentication. Results show that our approach is effective even under resizing and compression artifacts that are common in HAR applications using remote server connections.Viktor Dénes HuszárVamsi Kiran AdhikarlaMDPI AGarticledeep learninghuman activity recognitionspoof detectionspoof attack databasesecuritysmart citiesChemical technologyTP1-1185ENSensors, Vol 21, Iss 7339, p 7339 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning human activity recognition spoof detection spoof attack database security smart cities Chemical technology TP1-1185
spellingShingle	deep learning human activity recognition spoof detection spoof attack database security smart cities Chemical technology TP1-1185 Viktor Dénes Huszár Vamsi Kiran Adhikarla Live Spoofing Detection for Automatic Human Activity Recognition Applications
description	Human Activity Recognition (HAR) has become increasingly crucial in several applications, ranging from motion-driven virtual games to automated video surveillance systems. In these applications, sensors such as smart phone cameras, web cameras or CCTV cameras are used for detecting and tracking physical activities of users. Inevitably, spoof detection in HAR is essential to prevent anomalies and false alarms. To this end, we propose a deep learning based approach that can be used to detect spoofing in various fields such as border control, institutional security and public safety by surveillance cameras. Specifically, in this work, we address the problem of detecting spoofing occurring from video replay attacks, which is more common in such applications. We present a new database containing several videos of users juggling a football, captured under different lighting conditions and using different display and capture devices. We train our models using this database and the proposed system is capable of running in parallel with the HAR algorithms in real-time. Our experimental results show that our approach precisely detects video replay spoofing attacks and generalizes well, even to other applications such as spoof detection in face biometric authentication. Results show that our approach is effective even under resizing and compression artifacts that are common in HAR applications using remote server connections.
format	article
author	Viktor Dénes Huszár Vamsi Kiran Adhikarla
author_facet	Viktor Dénes Huszár Vamsi Kiran Adhikarla
author_sort	Viktor Dénes Huszár
title	Live Spoofing Detection for Automatic Human Activity Recognition Applications
title_short	Live Spoofing Detection for Automatic Human Activity Recognition Applications
title_full	Live Spoofing Detection for Automatic Human Activity Recognition Applications
title_fullStr	Live Spoofing Detection for Automatic Human Activity Recognition Applications
title_full_unstemmed	Live Spoofing Detection for Automatic Human Activity Recognition Applications
title_sort	live spoofing detection for automatic human activity recognition applications
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/3a2f0617f97245988fedbf630bee9811
work_keys_str_mv	AT viktordeneshuszar livespoofingdetectionforautomatichumanactivityrecognitionapplications AT vamsikiranadhikarla livespoofingdetectionforautomatichumanactivityrecognitionapplications
_version_	1718431577992593408

Live Spoofing Detection for Automatic Human Activity Recognition Applications

Ejemplares similares