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

Combining Global and Local 6DoF Pose Estimation for Real-World Applications

Rothe, Jakob (2022) Combining Global and Local 6DoF Pose Estimation for Real-World Applications. DLR-Interner Bericht. DLR-IB-RM-OP-2022-96. Master's. Technical University of Munich.

[img] PDF - Only accessible within DLR


In this thesis, we tightly integrate object detection, pose estimation and tracking into a single, effective pipeline. For object pose detection on resource constrained robotic hardware, we train a lightweight SSDlite detector and Augmented AutoEncoders. To avoid manual labeling, we only train on photorealistic data generated using BlenderProc. We investigate photo-metric augmentations to reduce the sim2real gap. Furthermore, we develop techniques for tracking loss detection based on features and metrics extracted from an existing tracker, as well as the trained bounding box detector and pose estimator. The goal is thereby to automatically alternate between accurate and fast object tracking and (re-)initialization with global object pose detection. For tracking loss detection, different statistical and learning-based methods are evaluated on the YCB-Video dataset. Finally, we test our pipeline on the anthropomorphic robot David for 6-DoF pose estimation and tracking of IKEA dishes.

Item URL in elib:https://elib.dlr.de/187680/
Document Type:Monograph (DLR-Interner Bericht, Master's)
Title:Combining Global and Local 6DoF Pose Estimation for Real-World Applications
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Date:15 July 2022
Refereed publication:No
Open Access:No
Gold Open Access:No
In ISI Web of Science:No
Keywords:object detection, pose estimation, tracking, tracking loss detection
Institution:Technical University of Munich
Department:Department of Informatics
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Robotics
DLR - Research area:Raumfahrt
DLR - Program:R RO - Robotics
DLR - Research theme (Project):R - Multisensory World Modelling (RM) [RO]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Deposited By: Stoiber, Manuel
Deposited On:28 Jul 2022 11:21
Last Modified:28 Jul 2022 11:21

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.