In the last decades, many efforts have been devoted to develop methods for automatic scene understanding in the context of video surveillance applications. This paper presents a novel non-object centric approach for complex scene analysis. Similarly to previous methods, we use low-level cues to individuate atomic activities and create clip histograms. Differently from recent works, the task of discovering high-level activity patterns is formulated as a convex prototype learning problem. This problem results into a simple linear program that can be solved efficiently with standard solvers. The main advantage of our approach is that, using as objective function the Earth Mover's Distance (EMD), the similarity among elementary activities is taken into account in the learning phase. To improve scalability we also consider some variants of EMD adopting L1 as ground distance for one and two dimensional, linear and circular histograms. As in these cases only the similarity between neighboring atomic activities is taken into account, we also propose an automatic strategy for sorting them. Experimental results on publicly available datasets show that our method compares favorably with state-of-the-art approaches, often outperforming them.

A Prototype Learning Framework using EMD: Application to Complex Scenes Analysis

Ricci, Elisa;Messelodi, Stefano
2013-01-01

Abstract

In the last decades, many efforts have been devoted to develop methods for automatic scene understanding in the context of video surveillance applications. This paper presents a novel non-object centric approach for complex scene analysis. Similarly to previous methods, we use low-level cues to individuate atomic activities and create clip histograms. Differently from recent works, the task of discovering high-level activity patterns is formulated as a convex prototype learning problem. This problem results into a simple linear program that can be solved efficiently with standard solvers. The main advantage of our approach is that, using as objective function the Earth Mover's Distance (EMD), the similarity among elementary activities is taken into account in the learning phase. To improve scalability we also consider some variants of EMD adopting L1 as ground distance for one and two dimensional, linear and circular histograms. As in these cases only the similarity between neighboring atomic activities is taken into account, we also propose an automatic strategy for sorting them. Experimental results on publicly available datasets show that our method compares favorably with state-of-the-art approaches, often outperforming them.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11582/83801
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact