In this paper we address the issue of how form and motion can be integrated in order to provide suitable information to attentively track multiple moving objects. Such integration is designed in a Bayesian framework, and a Belief Propagation technique is exploited to perform coherent form/motion labeling of regions of the observed scene. Experiments on both synthetic and real data are presented and discussed

Bayesian propagation for perceiving moving objects / G. Boccignone, A. Marcelli, P. Napoletano, V. Caggiano, G. Di Fiore. - In: INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE. - ISSN 0218-0014. - 20:6(2006), pp. 835-847.

Bayesian propagation for perceiving moving objects

G. Boccignone;
2006

Abstract

In this paper we address the issue of how form and motion can be integrated in order to provide suitable information to attentively track multiple moving objects. Such integration is designed in a Bayesian framework, and a Belief Propagation technique is exploited to perform coherent form/motion labeling of regions of the observed scene. Experiments on both synthetic and real data are presented and discussed
Bayesian belief propagation; Motion estimation and segmentation; Tracking; Visual attention
Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni
Settore INF/01 - Informatica
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE
Article (author)
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

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: http://hdl.handle.net/2434/142892
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact