DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Deep Learning for Pose Estimation from RGB-D Images

Henkel, Dimitri (2017) Deep Learning for Pose Estimation from RGB-D Images. Diploma. DLR-Interner Bericht. DLR-IB-RM-OP-2017-277.

Full text not available from this repository.


This thesis presents a learning based approach for fast orientation estimation from RGB-D images. For this purpose a special type of a deep convolutional neural network is used - the Autoencoder. As those need lots of labeled data for training two solutions are presented. First, it is shown that they can be trained in an unsupervised fashion on unlabeled real data which then can be assigned pose labels to using synthetic images generated from the object’s CAD model. Secondly, it is shown that using synthetic data for training only is sufficient for orientation estimation. The approach presented has an inference time of less than 2 ms per object and has a low code complexity consisting of only few convolutional and pooling layer.

Item URL in elib:https://elib.dlr.de/116846/
Document Type:Monograph (DLR-Interner Bericht, Diploma)
Title:Deep Learning for Pose Estimation from RGB-D Images
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Henkel, DimitriDimitri.Henkel (at) dlr.deUNSPECIFIED
Date:1 September 2017
Refereed publication:No
Open Access:No
Gold Open Access:No
In ISI Web of Science:No
Keywords:Deep Learning, Robotics, Computer Vision
Institution:Technische Universität Dresden
Department:Institut für Künstliche Intelligenz
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Technik für Raumfahrtsysteme
DLR - Research theme (Project):R - Vorhaben Multisensorielle Weltmodellierung
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Deposited By: Brucker, Manuel
Deposited On:19 Dec 2017 14:55
Last Modified:19 Dec 2017 14:55

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.