Teach it Yourself - Fast Modeling of Industrial Objects for 6D Pose Estimation

Thomas Sølund, Thiusius Rajeeth Savarimuthu, Anders Glent Buch, Anders Billesø Beck, Norbert Krüger, Henrik Aanæs

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

Abstract

In this paper, we present a vision system that allows a human to create new 3D models of novel industrial parts by placing the part in two different positions in the scene. The two shot modeling framework generates models with a precision that allows the model to be used for 6D pose estimation without loss in pose accuracy. We quantitatively show that our modeling framework reconstructs noisy but adequate object models with a mean RMS error at 2.7 mm, a mean standard deviation at 0.025 mm and a completeness of 70.3 % over all 14 reconstructed models, compared to the ground truth CAD models. In addition, the models are applied in a pose estimation application, evaluated with 37 different scenes with 61 unique object poses. The pose estimation results show a mean translation error on 4.97 mm and a mean rotation error on 3.38 degrees.
Original languageEnglish
Title of host publicationComputer Vision Systems : 10th International Conference, ICVS 2015, Copenhagen, Denmark, July 6-9, 2015, Proceedings
PublisherSpringer
Publication date2015
Pages289-302
ISBN (Print)978-3-319-20903-6
ISBN (Electronic)978-3-319-20904-3
Publication statusPublished - 2015
Event10th International Conference on Computer Vision Systems - Copenhagen, Denmark
Duration: 6 Jul 20159 Jul 2015
Conference number: 10

Conference

Conference10th International Conference on Computer Vision Systems
Number10
CountryDenmark
CityCopenhagen
Period06/07/201509/07/2015
SeriesLecture Notes in Computer Science
Volume9163
ISSN0302-9743

Keywords

  • 3D modeling
  • Pose estimation
  • Robot manipulation
  • Flexible automation

Fingerprint Dive into the research topics of 'Teach it Yourself - Fast Modeling of Industrial Objects for 6D Pose Estimation'. Together they form a unique fingerprint.

Cite this