High Precision and Pose Estimation Based on Improved Point Cloud Algorithm for Noncooperative Targets
- 10.2991/cnci-19.2019.68How to use a DOI?
- Binocular vision, RANSAC, pose estimation, crust, noncooperative target.
Aiming at protecting the space environment such as removing space debris and repairing malfunctioning targets, it is vital importance to measure the pose of space targets. In this paper we propose a high precision pose estimation algorithm based on point cloud. The optimized Random Sample Consensus (RANSAC) algorithm which apply iterative solution can effectively delete false matching points. The experiment system consists of a satellite model and a binocular camera. The proposed method is a vital part of new autonomous spacecraft measurement which only use a binocular camera system at different perspectives to complete the pose estimation. After obtaining the cloud data of a target, we use the improved crust algorithm to accomplish the three-dimensional model. Finally, the experiment has shown that the vision based method can obtain the pose information of the targets effectively.
- © 2019, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Liang Wei AU - Jia Liu AU - Guiyang Zhang AU - Ju Huo PY - 2019/05 DA - 2019/05 TI - High Precision and Pose Estimation Based on Improved Point Cloud Algorithm for Noncooperative Targets BT - Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019) PB - Atlantis Press SP - 493 EP - 499 SN - 2352-538X UR - https://doi.org/10.2991/cnci-19.2019.68 DO - 10.2991/cnci-19.2019.68 ID - Wei2019/05 ER -