Bayesian Optimization of 3D Feature Parameters for 6D Pose Estimation

Frederik Hagelskjær, Norbert Krüger, Anders Glent Buch

2019

Abstract

6D pose estimation using local features has shown state-of-the-art performance for object recognition and pose estimation from 3D data in a number of benchmarks. However, this method requires extensive knowledge and elaborate parameter tuning to obtain optimal performances. In this paper, we propose an optimization method able to determine feature parameters automatically, providing improved point matches to a robust pose estimation algorithm. Using labeled data, our method measures the performance of the current parameter setting using a scoring function based on both true and false positive detections. Combined with a Bayesian optimization strategy, we achieve automatic tuning using few labeled examples. Experiments were performed on two recent RGB-D benchmark datasets. The results show significant improvements by tuning an existing algorithm, with state-of-art performance.

Download


Paper Citation


in Harvard Style

Hagelskjær F., Krüger N. and Buch A. (2019). Bayesian Optimization of 3D Feature Parameters for 6D Pose Estimation. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 135-142. DOI: 10.5220/0007568801350142


in Bibtex Style

@conference{visapp19,
author={Frederik Hagelskjær and Norbert Krüger and Anders Glent Buch},
title={Bayesian Optimization of 3D Feature Parameters for 6D Pose Estimation},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={135-142},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007568801350142},
isbn={978-989-758-354-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - Bayesian Optimization of 3D Feature Parameters for 6D Pose Estimation
SN - 978-989-758-354-4
AU - Hagelskjær F.
AU - Krüger N.
AU - Buch A.
PY - 2019
SP - 135
EP - 142
DO - 10.5220/0007568801350142
PB - SciTePress