Autoencoder-based abnormal activity detection using parallelepiped spatio-temporal region

The spread of surveillance cameras has necessitated the monitoring of large quantities of surveillance video feeds. A manual monitoring system is near impossible due to the large man-hour requirements. Recently, automatic abnormal activity detection has been an area of interest among researchers. A...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IET computer vision Jg. 13; H. 1; S. 23 - 30
Hauptverfasser:	George, Michael, Jose, Babita Roslind, Mathew, Jimson, Kokare, Pranjali
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	The Institution of Engineering and Technology 01.02.2019 Wiley
Schlagworte:	autoencoder-based abnormal activity detection automatic abnormal activity detection feature extraction histogram of optical flow orientation and magnitude HOFM feature extraction image motion analysis image reconstruction image sequences manual monitoring system neural nets novel nonuniform spatio-temporal region object detection parallelepiped spatio-temporal region Research Article spatio-temporal feature standard abnormality detection datasets surveillance cameras surveillance video feeds video cameras video signal processing video surveillance surveillance video feeds autoencoder-based abnormal activity detection video cameras object detection image reconstruction HOFM feature extraction image motion analysis surveillance cameras standard abnormality detection datasets feature extraction parallelepiped spatio-temporal region novel nonuniform spatio-temporal region spatio-temporal feature manual monitoring system video signal processing video surveillance image sequences neural nets automatic abnormal activity detection histogram of optical flow orientation and magnitude
ISSN:	1751-9632, 1751-9640, 1751-9640
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!