A probabilistic framework for 3D visual object representation

Dentry, R., Pugeault, N. and Piater, J. H. (2009) A probabilistic framework for 3D visual object representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(10), pp. 1790-1803. (doi: 10.1109/TPAMI.2009.64)

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.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Pugeault, Dr Nicolas
• Authors: Dentry, R., Pugeault, N., and Piater, J. H.
• College/School: College of Science and Engineering > School of Computing Science
• Journal Name: IEEE Transactions on Pattern Analysis and Machine Intelligence
• Publisher: IEEE
• ISSN: 0162-8828
• ISSN (Online): 1939-3539
• Published Online: 17 March 2009