Motion segmentation and abnormal behavior detection via behavior clustering

We consider a change detection problem in video surveillance applications and propose busy-idle rates, meaningful and easy to compute features, to characterize the behavior profile of a given pixel. We describe the geometry independence property of these features, and use them to model the typical b...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Ermis, E.B., Saligrama, V., Jodoin, P.-M., Konrad, J.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	abnormality detection Behavior modeling Computer vision Geometry geometry independence Motion detection Motion segmentation Object detection Phase detection Solid modeling Statistics Surveillance Tracking
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!