In latest years modern world's needs of safety caused a speed spreading of video surveillance systems, more and more frequently collocated in the most crowded places. Thus, a lot of theoretical approaches working with data coming from heterogeneous sources and defining some very complex event detection algorithms have been proposed in the literature. In this paper, we present a distributed framework for event detection in video surveillance context. The overall process is described, starting from the video frames captured by different kinds of sensors and cameras till at the end some high-level event detection algorithms performed in a distributed environment for finding potentially dangerous activities are applied. The conducted experiments confirm the efficiency achieved by our distributed framework.
A Distributed Framework for Event Detection in Video Surveillance Context
Persia F.
;
2015-01-01
Abstract
In latest years modern world's needs of safety caused a speed spreading of video surveillance systems, more and more frequently collocated in the most crowded places. Thus, a lot of theoretical approaches working with data coming from heterogeneous sources and defining some very complex event detection algorithms have been proposed in the literature. In this paper, we present a distributed framework for event detection in video surveillance context. The overall process is described, starting from the video frames captured by different kinds of sensors and cameras till at the end some high-level event detection algorithms performed in a distributed environment for finding potentially dangerous activities are applied. The conducted experiments confirm the efficiency achieved by our distributed framework.File | Dimensione | Formato | |
---|---|---|---|
DiSTRIBUTED_FRAMEWORK.pdf
solo utenti autorizzati
Tipologia:
Documento in Versione Editoriale
Licenza:
Creative commons
Dimensione
672.75 kB
Formato
Adobe PDF
|
672.75 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.