Extended 3D Line Segments from RGB-D Data for Pose Estimation

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

Abstract

We propose a method for the extraction of complete and rich symbolic line segments in 3D based on RGB-D data. Edges are detected by combining cues from the RGB image and the aligned depth map. 3D line segments are then reconstructed by back-projecting 2D line segments and intersecting this with local surface patches computed from the 3D point cloud. Different edge types are classified using the new enriched representation and the potential of this representation for the task of pose estimation is demonstrated.
Original languageEnglish
Title of host publicationImage Analysis : 18th Scandinavian Conference, SCIA 2013, Espoo, Finland, June 17-20, 2013. Proceedings
EditorsJoni-Kristian Kämäräinen, Markus Koskela
PublisherSpringer
Publication date2013
Pages54-65
ISBN (Print)978-3-642-38885-9
ISBN (Electronic)978-3-642-38886-6
DOIs
Publication statusPublished - 2013
EventScandinavian Conference on Image Analysis - Helsinki, Finland
Duration: 17. Jun 201320. Jun 2013
Conference number: 18

Conference

ConferenceScandinavian Conference on Image Analysis
Number18
Country/TerritoryFinland
CityHelsinki
Period17/06/201320/06/2013
SeriesLecture Notes in Computer Science
Volume7944
ISSN0302-9743

Keywords

  • Edge detection
  • Pose estimation

Fingerprint

Dive into the research topics of 'Extended 3D Line Segments from RGB-D Data for Pose Estimation'. Together they form a unique fingerprint.

Cite this