Probabilistic Pose Recovery Using Learned Hierarchical Object Models

Authors:
Renaud Detry;Nicolas Pugeault;Justus Piater
Affiliations:
Université de Liège, Liège, Belgium;University of Southern Denmark, Odense, Denmark,The University of Edinburgh,Edinburgh, Scotland, UK;Université de Liège, Liège, Belgium
Venue:
Cognitive Vision
Year:
2009

Citing 5
Cited 1

Probabilistic reasoning in intelligent systems: networks of plausible inference

Probabilistic reasoning in intelligent systems: networks of plausible inference
Hierarchical Part-Based Visual Object Categorization

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Feature Hierarchies for Object Classification

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Nonparametric belief propagation

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Multi-modal primitives as functional models of hyper-columns and their use for contextual integration

BVAI'05 Proceedings of the First international conference on Brain, Vision, and Artificial Intelligence

Adapting preshaped grasping movements using vision descriptors

SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a probabilistic representation for 3D objects, and details the mechanism of inferring the pose of real-world objects from vision. Our object model has the form of a hierarchy of increasingly expressive 3D features, and probabilistically represents 3D relations between these. Features at the bottom of the hierarchy are bound to local perceptions; while we currently only use visual features, our method can in principle incorporate features from diverse modalities within a coherent framework. Model instances are detected using a Nonparametric Belief Propagation algorithm which propagates evidence through the hierarchy to infer globally consistent poses for every feature of the model. Belief updates are managed by an importance-sampling mechanism that is critical for efficient and precise propagation. We conclude with a series of pose estimation experiments on real objects, along with quantitative performance evaluation.