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 nonobject 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 in a simple linear program that can be solved efficiently with standard solvers. The main advantage of our approach is that, using as the 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 1D and 2D, linear and circular histograms. In these cases, only the similarity between neighboring atomic activities, corresponding to adjacent histogram bins, is taken into account. Therefore, we also propose an automatic strategy for sorting atomic activities. 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, E.; Zen, Gloria; Sebe, Niculae; Messelodi, S.. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - 2013, 35:3(2013), pp. 513-526. [10.1109/TPAMI.2012.131]

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

E. Ricci;Zen, Gloria;Sebe, Niculae;
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 nonobject 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 in a simple linear program that can be solved efficiently with standard solvers. The main advantage of our approach is that, using as the 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 1D and 2D, linear and circular histograms. In these cases, only the similarity between neighboring atomic activities, corresponding to adjacent histogram bins, is taken into account. Therefore, we also propose an automatic strategy for sorting atomic activities. Experimental results on publicly available datasets show that our method compares favorably with state-of-the-art approaches, often outperforming them.
2013
3
Ricci, E.; Zen, Gloria; Sebe, Niculae; Messelodi, S.
A Prototype Learning Framework using EMD: Application to Complex Scenes Analysis / Ricci, E.; Zen, Gloria; Sebe, Niculae; Messelodi, S.. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - 2013, 35:3(2013), pp. 513-526. [10.1109/TPAMI.2012.131]
File in questo prodotto:
File Dimensione Formato  
PAMI2013.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.63 MB
Formato Adobe PDF
1.63 MB Adobe PDF   Visualizza/Apri

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/11572/91543
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 28
  • ???jsp.display-item.citation.isi??? 26
social impact