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 labelling of regions of the observed scene.
Inference of moving forms via Belief Propagation / G. Boccignone, A. Marcelli, P. Napoletano - In: The 18th International conference on pattern recognition : 20–24 august, 2006 Hong Kong : proceedings. 2Los Alamitos : Institute of electrical and electronics engineers, 2006. - ISBN 0769525210. - pp. 191-194 (( Intervento presentato al 18. convegno International Conference on Pattern Recognition tenutosi a Honk Kong nel 2006.
Inference of moving forms via Belief Propagation
G. BoccignonePrimo
;
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 labelling of regions of the observed scene.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.