PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A Probabilistic Framework for 3D Visual Object Representation
Renaud Detry, Nicolas Pugeault and Justus Piater
IEEE transactions in Pattern Analysis and Machine Intelligence Volume 31, Number 10, pp. 1790-1803, 2009. ISSN 0162-8828

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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Machine Vision
Theory & Algorithms
ID Code:7170
Deposited By:Nicolas Pugeault
Deposited On:07 March 2011