Accurate Fiducial Mapping For Pose Estimation Using Manifold Optimization

Xiao Hu, Jakob Jakobsen, Per Knudsen, Jiang Wei

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

4 Downloads (Pure)

Abstract

The accurate pose estimation for moving objects within a given workspace is one of the most fundamental tasks for many applications including augmented reality, robotics’ control, planning and navigation. The information of objects’ pose is often given by motion capture systems and global positioning systems indoor and outdoor respectively. However, motion capture systems are costly and limited in workspace, while global positioning systems degrade severely in clustering environments. In this paper, we propose an approach to build a map of fiducial markers based on manifold optimization and then extend the fiducial map for pose estimation. The fiducial map based pose estimation system is cost-effective, lightweight and can work both indoor and outdoor. The proposed method starts by fiducial detection and pose estimation for collected images in order to establish an initial graph which stacks measurements of markers’relative poses. Then for each relative pose, multiple measurements are fused using manifold optimization for an optimal estimation.To deal with pose ambiguity problem, inlier poses are selected using the random sample consensus algorithm. Finally, a global pose optimization is done on manifold to minimize per frame reprojection errors. Mapping experiments with synthetic and realdata demonstrated the accuracy and consistency of the proposed approach. The accuracy of pose estimation using prebuilt fiducialmap was evaluated by benchmark tests with motion capturesystem
Original languageEnglish
Title of host publication2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN)
PublisherIEEE
Publication date2018
Pages206-212
ISBN (Electronic)978-1-5386-5635-8
DOIs
Publication statusPublished - 2018
Event2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN) - Nantes, France
Duration: 24 Sep 201827 Sep 2018

Conference

Conference2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN)
CountryFrance
CityNantes
Period24/09/201827/09/2018

Keywords

  • Fiducial Markers
  • Mapping
  • Localization
  • Pose Estimation
  • Manifold
  • Pose Optimization

Cite this

Hu, X., Jakobsen, J., Knudsen, P., & Wei , J. (2018). Accurate Fiducial Mapping For Pose Estimation Using Manifold Optimization. In 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN) (pp. 206-212). IEEE. https://doi.org/I: 10.1109/IPIN.2018.8533854
Hu, Xiao ; Jakobsen, Jakob ; Knudsen, Per ; Wei , Jiang. / Accurate Fiducial Mapping For Pose Estimation Using Manifold Optimization. 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN). IEEE, 2018. pp. 206-212
@inproceedings{192f8089ec064c4a96a365cc7724f218,
title = "Accurate Fiducial Mapping For Pose Estimation Using Manifold Optimization",
abstract = "The accurate pose estimation for moving objects within a given workspace is one of the most fundamental tasks for many applications including augmented reality, robotics’ control, planning and navigation. The information of objects’ pose is often given by motion capture systems and global positioning systems indoor and outdoor respectively. However, motion capture systems are costly and limited in workspace, while global positioning systems degrade severely in clustering environments. In this paper, we propose an approach to build a map of fiducial markers based on manifold optimization and then extend the fiducial map for pose estimation. The fiducial map based pose estimation system is cost-effective, lightweight and can work both indoor and outdoor. The proposed method starts by fiducial detection and pose estimation for collected images in order to establish an initial graph which stacks measurements of markers’relative poses. Then for each relative pose, multiple measurements are fused using manifold optimization for an optimal estimation.To deal with pose ambiguity problem, inlier poses are selected using the random sample consensus algorithm. Finally, a global pose optimization is done on manifold to minimize per frame reprojection errors. Mapping experiments with synthetic and realdata demonstrated the accuracy and consistency of the proposed approach. The accuracy of pose estimation using prebuilt fiducialmap was evaluated by benchmark tests with motion capturesystem",
keywords = "Fiducial Markers, Mapping, Localization, Pose Estimation, Manifold, Pose Optimization",
author = "Xiao Hu and Jakob Jakobsen and Per Knudsen and Jiang Wei",
year = "2018",
doi = "I: 10.1109/IPIN.2018.8533854",
language = "English",
pages = "206--212",
booktitle = "2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN)",
publisher = "IEEE",
address = "United States",

}

Hu, X, Jakobsen, J, Knudsen, P & Wei , J 2018, Accurate Fiducial Mapping For Pose Estimation Using Manifold Optimization. in 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN). IEEE, pp. 206-212, 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN), Nantes, France, 24/09/2018. https://doi.org/I: 10.1109/IPIN.2018.8533854

Accurate Fiducial Mapping For Pose Estimation Using Manifold Optimization. / Hu, Xiao; Jakobsen, Jakob; Knudsen, Per; Wei , Jiang.

2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN). IEEE, 2018. p. 206-212.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Accurate Fiducial Mapping For Pose Estimation Using Manifold Optimization

AU - Hu, Xiao

AU - Jakobsen, Jakob

AU - Knudsen, Per

AU - Wei , Jiang

PY - 2018

Y1 - 2018

N2 - The accurate pose estimation for moving objects within a given workspace is one of the most fundamental tasks for many applications including augmented reality, robotics’ control, planning and navigation. The information of objects’ pose is often given by motion capture systems and global positioning systems indoor and outdoor respectively. However, motion capture systems are costly and limited in workspace, while global positioning systems degrade severely in clustering environments. In this paper, we propose an approach to build a map of fiducial markers based on manifold optimization and then extend the fiducial map for pose estimation. The fiducial map based pose estimation system is cost-effective, lightweight and can work both indoor and outdoor. The proposed method starts by fiducial detection and pose estimation for collected images in order to establish an initial graph which stacks measurements of markers’relative poses. Then for each relative pose, multiple measurements are fused using manifold optimization for an optimal estimation.To deal with pose ambiguity problem, inlier poses are selected using the random sample consensus algorithm. Finally, a global pose optimization is done on manifold to minimize per frame reprojection errors. Mapping experiments with synthetic and realdata demonstrated the accuracy and consistency of the proposed approach. The accuracy of pose estimation using prebuilt fiducialmap was evaluated by benchmark tests with motion capturesystem

AB - The accurate pose estimation for moving objects within a given workspace is one of the most fundamental tasks for many applications including augmented reality, robotics’ control, planning and navigation. The information of objects’ pose is often given by motion capture systems and global positioning systems indoor and outdoor respectively. However, motion capture systems are costly and limited in workspace, while global positioning systems degrade severely in clustering environments. In this paper, we propose an approach to build a map of fiducial markers based on manifold optimization and then extend the fiducial map for pose estimation. The fiducial map based pose estimation system is cost-effective, lightweight and can work both indoor and outdoor. The proposed method starts by fiducial detection and pose estimation for collected images in order to establish an initial graph which stacks measurements of markers’relative poses. Then for each relative pose, multiple measurements are fused using manifold optimization for an optimal estimation.To deal with pose ambiguity problem, inlier poses are selected using the random sample consensus algorithm. Finally, a global pose optimization is done on manifold to minimize per frame reprojection errors. Mapping experiments with synthetic and realdata demonstrated the accuracy and consistency of the proposed approach. The accuracy of pose estimation using prebuilt fiducialmap was evaluated by benchmark tests with motion capturesystem

KW - Fiducial Markers

KW - Mapping

KW - Localization

KW - Pose Estimation

KW - Manifold

KW - Pose Optimization

U2 - I: 10.1109/IPIN.2018.8533854

DO - I: 10.1109/IPIN.2018.8533854

M3 - Article in proceedings

SP - 206

EP - 212

BT - 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN)

PB - IEEE

ER -

Hu X, Jakobsen J, Knudsen P, Wei J. Accurate Fiducial Mapping For Pose Estimation Using Manifold Optimization. In 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN). IEEE. 2018. p. 206-212 https://doi.org/I: 10.1109/IPIN.2018.8533854