Abstract : In high-level scene interpretation, it is useful to exploit the evolving probabilistic context for stepwise interpretation decisions. We present a new approach based on a general probabilistic framework and beam search for exploring alternative interpretations. As probabilistic scene models, we propose Bayesian Compositional Hierarchies (BCHs) which provide object-centered representations of compositional hierarchies and efficient evidence-based updates. It is shown that a BCH can be used to represent the evolving context during stepwise scene interpretation and can be combined with low-level image analysis to provide dynamic priors for object classification, improving classification and interpretation. Experimental results are presented illustrating the feasibility of the approach for the interpretation of facade images.
https://hal.inria.fr/hal-01054597 Contributor : Hal IfipConnect in order to contact the contributor Submitted on : Thursday, August 7, 2014 - 3:13:06 PM Last modification on : Thursday, March 5, 2020 - 5:43:03 PM Long-term archiving on: : Wednesday, November 26, 2014 - 1:50:33 AM
Bernd Neumann, Kasim Terzic. Context-Based Probabilistic Scene Interpretation. Third IFIP TC12 International Conference on Artificial Intelligence (AI) / Held as Part of World Computer Congress (WCC), Sep 2010, Brisbane, Australia. pp.155-164, ⟨10.1007/978-3-642-15286-3_15⟩. ⟨hal-01054597⟩