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

Publikation: Kapitel i bog/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer 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.
OriginalsprogEngelsk
TitelImage Analysis : 18th Scandinavian Conference, SCIA 2013, Espoo, Finland, June 17-20, 2013. Proceedings
RedaktørerJoni-Kristian Kämäräinen, Markus Koskela
ForlagSpringer
Publikationsdato2013
Sider54-65
ISBN (Trykt)978-3-642-38885-9
ISBN (Elektronisk)978-3-642-38886-6
DOI
StatusUdgivet - 2013
BegivenhedScandinavian Conference on Image Analysis - Helsinki, Finland
Varighed: 17. jun. 201320. jun. 2013
Konferencens nummer: 18

Konference

KonferenceScandinavian Conference on Image Analysis
Nummer18
Land/OmrådeFinland
ByHelsinki
Periode17/06/201320/06/2013
NavnLecture Notes in Computer Science
Vol/bind7944
ISSN0302-9743

Fingeraftryk

Dyk ned i forskningsemnerne om 'Extended 3D Line Segments from RGB-D Data for Pose Estimation'. Sammen danner de et unikt fingeraftryk.

Citationsformater