We present a probabilistic model for motion estimation in which motion characteristics are inferred on the basis of a finite mixture of motion models. The model is graphically represented in the form of a pairwise Markov Random Field network upon which a Loopy Belief Propagation algorithm is exploited to perform inference. Experiments on different video clips are presented and discussed.
Motion estimation via belief propagation / G. Boccignone, A. Marcelli, P. Napoletano, M. Ferraro - In: Image Analysis and Processing, 2007. ICIAP 2007. 14th International Conference on[s.l] : IEEE, 2007. - ISBN 0769528775. - pp. 55-60 (( Intervento presentato al 14. convegno International Conference on Image Analysis and Processing tenutosi a Modena nel 2007.
Motion estimation via belief propagation
G. Boccignone
;
2007
Abstract
We present a probabilistic model for motion estimation in which motion characteristics are inferred on the basis of a finite mixture of motion models. The model is graphically represented in the form of a pairwise Markov Random Field network upon which a Loopy Belief Propagation algorithm is exploited to perform inference. Experiments on different video clips are presented and discussed.
| File | Dimensione | Formato | |
|---|---|---|---|
|
04362757.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
406.96 kB
Formato
Adobe PDF
|
406.96 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
