Title :
Inference of moving forms via Belief Propagation
Author :
Boccignone, Giuseppe ; Marcelli, Angelo ; Napoletano, P.
Author_Institution :
Dipt. di Ingegneria dell´Informazione e Ingegneria Elettrica, Univ. di Salerno, Fisciano
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
Keywords :
Bayes methods; belief networks; image motion analysis; Bayesian framework; belief propagation; motion labelling; moving form inference; moving object tracking; Bayesian methods; Belief propagation; Information analysis; Labeling; Layout; Motion analysis; Motion estimation; Performance analysis; Shape; Tracking;
Conference_Titel :
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
0-7695-2521-0
DOI :
10.1109/ICPR.2006.710