CaltechAUTHORS
  A Caltech Library Service

Pose Estimation of Uncooperative Spacecraft from Monocular Images Using Neural Network Based Keypoints

Harvard, Alexei and Capuano, Vincenzo and Shao, Eugene Y. and Chung, Soon-Jo (2020) Pose Estimation of Uncooperative Spacecraft from Monocular Images Using Neural Network Based Keypoints. In: AIAA Scitech 2020 Forum. American Institute of Aeronautics and Astronautics , Reston, VA, Art. No. 2020-1874. ISBN 978-1-62410-595-1. https://resolver.caltech.edu/CaltechAUTHORS:20200113-084156386

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200113-084156386

Abstract

A novel method for monocular-based pose estimation of uncooperative spacecraft using keypoints specialized for a given target is presented. A set of robust keypoints are created by examining the effectiveness of existing localization algorithms by simulating and testing different perspectives. The feature extraction and matching is used to build a model of the spacecraft before the flight mission using the same feature extraction algorithms that can be used during the mission. Further, a visibility map is determined for each keypoint to aid in outlier filtering, matching, and measurement covariance estimation. For initialization and matching, a Convolutional Neural Network (CNN) is trained to generate descriptors robust to illumination, scale, and affine changes for the pre-computed keypoints. In the second part of the paper, we focus on pose determination and filtering after keypoint-to-model matching. While several approaches for pose acquisition have been formulated, we propose a novel method for tracking that makes use of a nonlinear filter, based on the spacecraft translational and rotational relative dynamics which estimates the covariance of the vision-based observations using the keypoint preprocessing information. Further, the estimated propagated covariance for each extracted feature is used for aiding the feature matching.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.2514/6.2020-1874DOIArticle
ORCID:
AuthorORCID
Capuano, Vincenzo0000-0002-6886-5719
Chung, Soon-Jo0000-0002-6657-3907
Additional Information:© 2020 American Institute of Aeronautics and Astronautics. Published Online: 5 Jan 2020.
Group:GALCIT
Other Numbering System:
Other Numbering System NameOther Numbering System ID
AIAA Paper2020-1874
Record Number:CaltechAUTHORS:20200113-084156386
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200113-084156386
Official Citation:Pose Estimation of Uncooperative Spacecraft from Monocular Images Using Neural Network Based Keypoints. Alexei Harvard, Vincenzo Capuano, Eugene Y. Shao, and Soon-Jo Chung. AIAA Scitech 2020 Forum. January 2020; doi: 10.2514/6.2020-1874
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:100664
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:13 Jan 2020 17:16
Last Modified:13 Jan 2020 17:16

Repository Staff Only: item control page