How visual attention is shared between objects moving in an observed scene is a key issue to situate vision in the world. In this note, we discuss how a computational model taking into account such issue, can be designed in a bayesian framework. To validate the model, experiments with eye-tracked human subjects are presented and discussed.

A bayesian approach to situated vision / G. Boccignone, V. Caggiano, G.D. Fiore, A. Marcelli, P. Napoletano - In: Brain, Vision, and Artificial Intelligence / [a cura di] M. De Gregorio, V. Di Maio, M. Frucci, C. Musio. - [s.l] : Springer, 2005. - ISBN 3540292829. - pp. 367-376 (( Intervento presentato al 1. convegno International Symposium on Brain, Vision, and Artificial Intelligence tenutosi a Napoli nel 2005.

A bayesian approach to situated vision

G. Boccignone;
2005

Abstract

How visual attention is shared between objects moving in an observed scene is a key issue to situate vision in the world. In this note, we discuss how a computational model taking into account such issue, can be designed in a bayesian framework. To validate the model, experiments with eye-tracked human subjects are presented and discussed.
motion segmentation; framework; tracking
Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni
ICIB-CNR
IISF
Regione Campania
EBSA
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
chp%3A10.1007%2F11565123_35.pdf

non disponibili

Tipologia: Publisher's version/PDF
Dimensione 435.14 kB
Formato Adobe PDF
435.14 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
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/2434/494331
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 3
social impact