Zur Kurzanzeige

Visual Feature Track Dataset

dc.contributor.authorLuthardt, Stefan
dc.contributor.authorZiegler, Christoph
dc.date.accessioned2020-10-26T09:24:21Z
dc.date.available2020-10-26T09:24:21Z
dc.date.issued2019-10-27
dc.identifier.urihttps://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/2501
dc.description<style type="text/css"> <!-- .oof_tab { margin-left: 40px; } #oof_list ul { list-style-type: disc; list-style-position: outside; } #oof_list li { margin-left: 20px; } --> </style> <p>This dataset contains 282 visual feature tracks. A visual feature track is a sequence of feature observations of the same real 3D-landmark in consecutive image frames. These tracks are the output of a classical feature matching system, e.g. a Visual Odometry system or a system with Bundle Adjustment.</p> <p>The feature tracks were recorded at three different days in spring 2017 in a suburban area. The dataset provides each track as a sequence of square image patches which contain the surrounding of the observed feature. Since a stereo camera setup was used, there are two patches per feature observation. In total the dataset contains 3162 of these image patches.</p> <p>The dataset was created to investigate the task of long-term feature track matching, i.e. finding all tracks that belong to the same landmark. Therefore, the dataset also contains “ground truth” labels which of the tracks from the different days belong together. Furthermore, the distance to the feature is given for each observation.</p> <p>Like every real-world data, this dataset is not perfect. If you identify a major bug, please write an e-mail to <a class="link email" itemprop="email" href="mailto:christoph.ziegler@rmr.tu-darmstadt.de" title="mail to: christoph.ziegler@rmr.tu-darmstadt.de">christoph.ziegler@rmr.tu-…</a> with the track-ID and a description of the problem.</p> <p >If you use this dataset in your research please cite the associated publication:</p> <p><em>Stefan Luthardt, Christoph Ziegler, Volker Willert, and Jürgen Adamy: “How to Match Tracks of Visual Features for Automotive Long-Term SLAM”, IEEE 22nd International Conference on Intelligent Transportation Systems (ITSC), 2019.</em></p> <p><em><a href="https://tuprints.ulb.tu-darmstadt.de/9108/1/Luthardt_ITSC_2019_FeatureTracks.pdf" target="_blank">Download the Paper</a></em></p> <p>This paper also provides future explanations of the track matching task and describes possible approaches to solve this task.</p> <p><strong>BibTex:</strong></p> <p>@inproceedings{Luthardt.2019,<br/> <span class="oof_tab">author = {Luthardt, Stefan and Ziegler, Christoph and Willert, Volker and Adamy, Jürgen},</span><br/> <span class="oof_tab">title = {How to Match Tracks of Visual Features for Automotive Long-Term-{SLAM}},</span><br/> <span class="oof_tab">booktitle = {IEEE 22nd International Conference on Intelligent Transportation Systems (ITSC)},</span><br/> <span class="oof_tab">year = {2019}</span><br/> }</p> <p>Paper describing the associated SLAM algorithm:<br/><em><a href="http://tuprints.ulb.tu-darmstadt.de/8357/1/Luthardt_ITSC_2018_LLama.pdf" target="_blank">LLama-SLAM: Learning High-Quality Visual Landmarks for Long-Term Mapping and Localization.</a></em></p>en_US
dc.language.isoenen_US
dc.relationIsSupplementTo;DOI;10.1109/ITSC.2019.8916895
dc.rightsCreative Commons Attribution 4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectVisualizationen_US
dc.subjectFeature extractionen_US
dc.subjectoptimizationen_US
dc.subjectSimultaneous localization and mappingen_US
dc.subjectCamerasen_US
dc.subjectRobustnessen_US
dc.subjectimage matchingen_US
dc.subjectmobile robotsen_US
dc.subjectpose estimationen_US
dc.subjectrobot visionen_US
dc.subjectSLAMen_US
dc.subjectautomotive long-term SLAMen_US
dc.subjectvisual featuresen_US
dc.subjectautonomous driving functionsen_US
dc.subjectLLama-SLAMen_US
dc.subjectconsecutive image framesen_US
dc.subjectfeature tracken_US
dc.subjectvisual feature tracksen_US
dc.subject.classification4.43-04 Künstliche Intelligenz und Maschinelle Lernverfahren
dc.subject.classification4.41-04 Verkehrs- und Transportsysteme, Intelligenter und automatisierter Verkehr
dc.subject.classification4.43-05 Bild- und Sprachverarbeitung, Computergraphik und Visualisierung, Human Computer Interaction, Ubiquitous und Wearable Computing
dc.subject.ddc380
dc.subject.ddc004
dc.titleVisual Feature Track Dataseten_US
dc.typeDataseten_US
dc.typeTexten_US
dc.typeSoftwareen_US
dc.typeImageen_US
tud.history.classificationVersion=2016-2020;407-04 Verkehrs- und Transportsysteme, Logistik, Intelligenter und automatisierter Verkehr;409-05 Interaktive und intelligente Systeme, Bild- und Sprachverarbeitung, Computergraphik und Visualisierung;


Dateien zu dieser Ressource

Thumbnail
Name:
P4_VFTD_v1.zip
Größe:
9.329MB
Format:
application/zip
Anzahl der Dateien
Thumbnail
Name:
license_CC-BY-4.0.rdf
Größe:
7.877KB
Format:
application/rdf+xml
Anzahl der Dateien

Der Datensatz erscheint in:

Zur Kurzanzeige

Creative Commons Attribution 4.0
Solange nicht anders angezeigt, wird die Lizenz wie folgt beschrieben: Creative Commons Attribution 4.0