Skip to main navigation Skip to search Skip to main content

Pose estimation of space objects based on hybrid feature matching of contour points

  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents an improved pose estimation algorithm for vision-based space objects.The major weakness of most existing methods is limited convergence radius.In most cases they ignore the influence of translation, only focusing on rotation parameters.To breakthrough these limits, we utilizes hybrid local image features to explicitly establish 2D-3D correspondences between the input image and 3D model of space objects, and then estimate rotation and translation parameters based on the correspondences.Experiments with simulated models are carried out, and the results show that our algorithm can successfully estimate the pose of space objects with large convergence radius and high accuracy.

Original languageEnglish
Title of host publicationAdvances in Image and Graphics Technologies - 11th Chinese Conference, IGTA 2016, Proceedings
EditorsTieniu Tan, Ran He, Guoping Wang, Xiaoru Yuan, Sheng Li, Shengjin Wang, Yue Liu
PublisherSpringer Verlag
Pages184-191
Number of pages8
ISBN (Print)9789811022593
DOIs
StatePublished - 2016
Event11th Chinese Conference on Advances in Image and Graphics Technologies, IGTA 2016 - Beijing, China
Duration: 8 Jul 20169 Jul 2016

Publication series

NameCommunications in Computer and Information Science
Volume634
ISSN (Print)1865-0929

Conference

Conference11th Chinese Conference on Advances in Image and Graphics Technologies, IGTA 2016
Country/TerritoryChina
CityBeijing
Period8/07/169/07/16

Keywords

  • 2D-3D correspondences
  • Hybrid local image features
  • Pose estimation
  • Space object

Fingerprint

Dive into the research topics of 'Pose estimation of space objects based on hybrid feature matching of contour points'. Together they form a unique fingerprint.

Cite this