A Fast Discriminant Approach to Active Object Recognition and Pose Estimation

Authors:
Catherine Laporte;Rupert Brooks;Tal Arbel
Affiliations:
McGill University, Canada;McGill University, Canada;McGill University, Canada
Venue:
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Year:
2004

Citing 0
Cited 4

Efficient Discriminant Viewpoint Selection for Active Bayesian Recognition

International Journal of Computer Vision
Robust sequential view planning for object recognition using multiple cameras

Image and Vision Computing
Robotic object detection: learning to improve the classifiers using sparse graphs for path planning

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
Contextually guided semantic labeling and search for three-dimensional point clouds

International Journal of Robotics Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new criterion for viewpoint selection in the context of active Bayesian object recognition and pose estimation. Recognition is performed by probabilistically fusing successive observations with the current belief state of the system. Based on the current belief state, the next viewpoint is chosen to maximize the expected discriminability of the current competing hypotheses. Experiments on a difficult database of aircraft models show that this approach achieves comparable recognition performance to the widely used information theoretic approaches at a much lower computational cost.