In this paper we present a non-parametric approach to anomaly detection in surveillance videos. The real-time system uses spatio-temporal features, integrated in a multi-scale approach. The system can localize anomalies temporally (at frame level) and spatially (within frame). The systems has been compared to state-of-the-art approaches on a real-world UCSD dataset. According to experiments our method consistently outperforms other real-time approaches.

Multi-scale and real-time non-parametric approach for anomaly detection and localization / M. Bertini;A. Del Bimbo;L. Seidenari. - In: COMPUTER VISION AND IMAGE UNDERSTANDING. - ISSN 1077-3142. - STAMPA. - 116:(2012), pp. 320-329. [10.1016/j.cviu.2011.09.009]

Multi-scale and real-time non-parametric approach for anomaly detection and localization

M. Bertini;A. Del Bimbo;L. Seidenari
2012

Abstract

In this paper we present a non-parametric approach to anomaly detection in surveillance videos. The real-time system uses spatio-temporal features, integrated in a multi-scale approach. The system can localize anomalies temporally (at frame level) and spatially (within frame). The systems has been compared to state-of-the-art approaches on a real-world UCSD dataset. According to experiments our method consistently outperforms other real-time approaches.
2012
116
320
329
M. Bertini;A. Del Bimbo;L. Seidenari
File in questo prodotto:
File Dimensione Formato  
cviu12.pdf

Accesso chiuso

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 1.37 MB
Formato Adobe PDF
1.37 MB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/555486
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 134
  • ???jsp.display-item.citation.isi??? 113
social impact