Show simple item record

dc.contributor.author
Xing, Chunwei
dc.contributor.author
Sun, Xinyu
dc.contributor.author
Cramariuc, Andrei
dc.contributor.author
Gull, Samuel
dc.contributor.author
Chung, Jen Jen
dc.contributor.author
Cadena, Cesar
dc.contributor.author
Siegwart, Roland
dc.contributor.author
Tschopp, Florian
dc.date.accessioned
2022-11-15T10:46:07Z
dc.date.available
2022-11-08T16:23:15Z
dc.date.available
2022-11-15T10:46:07Z
dc.date.issued
2022-09-14
dc.identifier.other
10.48550/ARXIV.2203.00567
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/580085
dc.description.abstract
Current descriptors for global localization often struggle under vast viewpoint or appearance changes. One possible improvement is the addition of topological information on semantic objects. However, handcrafted topological descriptors are hard to tune and not robust to environmental noise, drastic perspective changes, object occlusion or misdetections. To solve this problem, we formulate a learning-based approach by modelling semantically meaningful object constellations as graphs and using Deep Graph Convolution Networks to map a constellation to a descriptor. We demonstrate the effectiveness of our Deep Learned Constellation Descriptor (Descriptellation) on two real-world datasets. Although Descriptellation is trained on randomly generated simulation datasets, it shows good generalization abilities on real-world datasets. Descriptellation also outperforms state-of-the-art and handcrafted constellation descriptors for global localization, and is robust to different types of noise. The code is publicly available at https://github.com/ethz-asl/Descriptellation.
en_US
dc.language.iso
en
en_US
dc.publisher
Cornell University
en_US
dc.subject
Robotics (cs.RO)
en_US
dc.subject
Computer Vision and Pattern Recognition (cs.CV)
en_US
dc.subject
FOS: Computer and information sciences
en_US
dc.title
Descriptellation
en_US
dc.type
Working Paper
ethz.title.subtitle
Deep learned constellation descriptors
en_US
ethz.journal.title
arXiv
ethz.pages.start
2203.00567v2
en_US
ethz.size
7 p.
en_US
ethz.version.edition
v2
en_US
ethz.notes
PROMPT (MI Mobility Initiative Project)
en_US
ethz.identifier.arxiv
2203.00567
ethz.publication.place
Ithaca, NY
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02130 - Dep. Maschinenbau und Verfahrenstechnik / Dep. of Mechanical and Process Eng.::02620 - Inst. f. Robotik u. Intelligente Systeme / Inst. Robotics and Intelligent Systems::03737 - Siegwart, Roland Y. / Siegwart, Roland Y.
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02130 - Dep. Maschinenbau und Verfahrenstechnik / Dep. of Mechanical and Process Eng.::02261 - Center for Sustainable Future Mobility / Center for Sustainable Future Mobility
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02130 - Dep. Maschinenbau und Verfahrenstechnik / Dep. of Mechanical and Process Eng.::02620 - Inst. f. Robotik u. Intelligente Systeme / Inst. Robotics and Intelligent Systems::03737 - Siegwart, Roland Y. / Siegwart, Roland Y.
en_US
ethz.date.deposited
2022-11-08T16:23:16Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2022-11-15T10:46:08Z
ethz.rosetta.lastUpdated
2024-02-02T18:53:40Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Descriptellation&rft.jtitle=arXiv&rft.date=2022-09-14&rft.spage=2203.00567v2&rft.au=Xing,%20Chunwei&Sun,%20Xinyu&Cramariuc,%20Andrei&Gull,%20Samuel&Chung,%20Jen%20Jen&rft.genre=preprint&rft_id=info:doi/10.48550/ARXIV.2203.00567&
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record