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

DOT: Dynamic Object Tracking for Visual SLAM

Ballester Campos, Irene and Fontán Villacampa, Alejandro and Civera Sancho, Javier and Strobl, Klaus H. and Triebel, Rudolph (2021) DOT: Dynamic Object Tracking for Visual SLAM. In: 2021 IEEE International Conference on Robotics and Automation, ICRA 2021, pp. 11705-11711. IEEE. 2021 IEEE International Conference on Robotics and Automation (ICRA), 30 May - 05 June 2021, Xi'an, China. doi: 10.1109/ICRA48506.2021.9561452. ISBN 978-172819077-8. ISSN 1050-4729.

[img] PDF

Official URL: https://ieeexplore.ieee.org/abstract/document/9561452


In this paper we present DOT (Dynamic Object Tracking), a front-end that added to existing SLAM systems can significantly improve their robustness and accuracy in highly dynamic environments. DOT combines instance segmentation and multi-view geometry to generate masks for dynamic objects in order to allow SLAM systems based on rigid scene models to avoid such image areas in their optimizations.To determine which objects are actually moving, DOT segments first instances of potentially dynamic objects and then, with the estimated camera motion, tracks such objects by minimizing the photometric reprojection error. This short-term tracking improves the accuracy of the segmentation with respect to other approaches. In the end, only actually dynamicmasks are generated.We have evaluated DOT with ORB-SLAM 2 [1] in three public datasets. Our results show that our approach improves significantly the accuracy and robustness of ORB-SLAM2, especially in highly dynamic scenes.

Item URL in elib:https://elib.dlr.de/146127/
Document Type:Conference or Workshop Item (Speech)
Title:DOT: Dynamic Object Tracking for Visual SLAM
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Ballester Campos, Ireneiballester (at) cvl.tuwien.ac.athttps://orcid.org/0000-0002-0219-9063
Fontán Villacampa, AlejandroAlejandro.FontanVillacampa (at) dlr.dehttps://orcid.org/0000-0002-5909-8415
Civera Sancho, Javierjcivera (at) unizar.eshttps://orcid.org/0000-0003-1368-1151
Strobl, Klaus H.Klaus.Strobl (at) dlr.dehttps://orcid.org/0000-0001-8123-0606
Triebel, RudolphRudolph.Triebel (at) dlr.dehttps://orcid.org/0000-0002-7975-036X
Date:May 2021
Journal or Publication Title:2021 IEEE International Conference on Robotics and Automation, ICRA 2021
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
DOI :10.1109/ICRA48506.2021.9561452
Page Range:pp. 11705-11711
Keywords:slam; visual tracking; semantic segmentation
Event Title:2021 IEEE International Conference on Robotics and Automation (ICRA)
Event Location:Xi'an, China
Event Type:international Conference
Event Dates:30 May - 05 June 2021
Organizer:IEEE Robotics & Automation Society
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 - E3D: Algorithms and Application (RM) [RO]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Deposited By: Strobl, Klaus
Deposited On:26 Nov 2021 13:26
Last Modified:25 Mar 2022 10:32

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.