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.
Citation:
Giuseppe Boccignone, Angelo Marcelli, Paolo Napoletano, "Inference of moving forms via Belief Propagation," icpr, vol. 2, pp.191-194, 18th International Conference on Pattern Recognition (ICPR'06) Volume 2, 2006