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

A Sparse Gaussian Approach to Region-Based 6DoF Object Tracking

Stoiber, Manuel and Pfanne, Martin and Strobl, Klaus and Triebel, Rudolph and Albu-Schäffer, Alin Olimpiu (2020) A Sparse Gaussian Approach to Region-Based 6DoF Object Tracking. In: 15th Asian Conference on Computer Vision, ACCV 2020, 12623, pp. 666-682. Springer Nature Switzerland. 15th Asian Conference on Computer Vision, ACCV 2020, 2020-11-30 - 2020-12-04, Kyoto, Japan. doi: 10.1007/978-3-030-69532-3_40. ISBN 978-303069531-6. ISSN 0302-9743.

[img] PDF - Only accessible within DLR
[img] PDF - Only accessible within DLR


We propose a novel, highly efficient sparse approach to region-based 6DoF object tracking that requires only a monocular RGB camera and the 3D object model. The key contribution of our work is a probabilistic model that considers image information sparsely along correspondence lines. For the implementation, we provide a highly efficient discrete scale-space formulation. In addition, we derive a novel mathematical proof that shows that our proposed likelihood function follows a Gaussian distribution. Based on this information, we develop robust approximations for the derivatives of the log-likelihood that are used in a regularized Newton optimization. In multiple experiments, we show that our approach outperforms state-of-the-art region-based methods in terms of tracking success while being about one order of magnitude faster. The source code of our tracker is publicly available.

Item URL in elib:https://elib.dlr.de/139320/
Document Type:Conference or Workshop Item (Speech)
Additional Information:Best paper award.
Title:A Sparse Gaussian Approach to Region-Based 6DoF Object Tracking
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Stoiber, ManuelUNSPECIFIEDhttps://orcid.org/0000-0002-0762-9288UNSPECIFIED
Pfanne, MartinUNSPECIFIEDhttps://orcid.org/0000-0003-2076-4772UNSPECIFIED
Strobl, KlausUNSPECIFIEDhttps://orcid.org/0000-0001-8123-0606139008461
Triebel, RudolphUNSPECIFIEDhttps://orcid.org/0000-0002-7975-036XUNSPECIFIED
Albu-Schäffer, Alin OlimpiuUNSPECIFIEDhttps://orcid.org/0000-0001-5343-9074142115844
Date:December 2020
Journal or Publication Title:15th Asian Conference on Computer Vision, ACCV 2020
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In ISI Web of Science:No
Page Range:pp. 666-682
Publisher:Springer Nature Switzerland
Series Name:Lecture Notes in Computer Science (LNCS)
Keywords:6DoF Object Tracking, Pose estimation, Region-based, Sparse, Gaussian, Real-time, Newton optimization, Probabilistic, Monocular
Event Title:15th Asian Conference on Computer Vision, ACCV 2020
Event Location:Kyoto, Japan
Event Type:international Conference
Event Start Date:30 November 2020
Event End Date:4 December 2020
Organizer:Asian Federation of Computer Vision
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space System Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Space System Technology
DLR - Research theme (Project):R - Vorhaben Multisensorielle Weltmodellierung (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013)
Deposited By: Stoiber, Manuel
Deposited On:08 Dec 2020 14:51
Last Modified:24 Apr 2024 20:40

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.