A Probabilistic Framework for 3D Visual Object Representation.

Renaud Detry, Nicolas Pugeault, Justus H. PiaterIEEE TPAMI 2009 · OpenReview

Abstract

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.
BibTeX
@article{detry2009probabilistic,
  author = {Renaud Detry and Nicolas Pugeault and Justus H. Piater},
  title = {{A Probabilistic Framework for 3D Visual Object Representation.}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2009},
  url = {https://openreview.net/forum?id=r7w4qBe_6B},
}

Loading related content...

Figure