Issue No. 10 - October (2009 vol. 31)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2009.64
Renaud Detry , University of Liège, Belgium
Nicolas Pugeault , University of Southern Denmark, Denmark
Justus H. Piater , University of Liège, Belgium
We present an object representation framework that encodes probabilistic spatial relations between 3D features and organizes these features in a hierarchy. Features at the bottom of the hierarchy are bound to local 3D descriptors. Higher level features recursively encode probabilistic spatial configurations of more elementary features. The hierarchy is implemented in a Markov network. Detection is carried out by a belief propagation algorithm, which infers the pose of high-level features from local evidence and reinforces local evidence from globally consistent knowledge, effectively producing a likelihood for the pose of the object in the detection scene. We also present a simple learning algorithm that autonomously builds hierarchies from local object descriptors. We explain how to use our framework to estimate the pose of a known object in an unknown scene. Experiments demonstrate the robustness of hierarchies to input noise, viewpoint changes, and occlusions.
Computer vision, 3D object representation, pose estimation, nonparametric belief propagation.
R. Detry, J. H. Piater and N. Pugeault, "A Probabilistic Framework for 3D Visual Object Representation," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 31, no. , pp. 1790-1803, 2009.