Show simple item record

dc.contributor.author
Chen, Zetao
dc.contributor.author
Maffra, Fabiola
dc.contributor.author
Sa, Inkyu
dc.contributor.author
Chli, Margarita
dc.date.accessioned
2018-04-13T16:33:02Z
dc.date.available
2017-08-03T09:54:17Z
dc.date.available
2017-08-03T10:09:38Z
dc.date.available
2018-01-30T09:01:16Z
dc.date.available
2018-04-13T16:33:02Z
dc.date.issued
2017
dc.identifier.isbn
978-1-5386-2682-5
en_US
dc.identifier.isbn
978-1-5386-2681-8
en_US
dc.identifier.isbn
978-1-5386-2683-2
en_US
dc.identifier.other
10.1109/IROS.2017.8202131
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/174255
dc.identifier.doi
10.3929/ethz-b-000174255
dc.description.abstract
Recently, image representations derived from Convolutional Neural Networks (CNNs) have been demonstrated to achieve impressive performance on a wide variety of tasks, including place recognition. In this paper, we take a step deeper into the internal structure of CNNs and propose novel CNN-based image features for place recognition by identifying salient regions and creating their regional representations directly from the convolutional layer activations. A range of experiments is conducted on challenging datasets with varied conditions and viewpoints. These reveal superior precision-recall characteristics and robustness against both viewpoint and appearance variations for the proposed approach over the state of the art. By analyzing the feature encoding process of our approach, we provide insights into what makes an image presentation robust against external variations.
en_US
dc.format
application/pdf
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
Place Recognition
en_US
dc.subject
Convolutional Neural Network
en_US
dc.subject
Feature Encoding
en_US
dc.subject
Robot Localization
en_US
dc.title
Only look once, mining distinctive landmarks from ConvNet for visual place recognition
en_US
dc.type
Conference Paper
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2017-12-14
ethz.book.title
2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
en_US
ethz.pages.start
9
en_US
ethz.pages.end
16
en_US
ethz.version.deposit
submittedVersion
en_US
ethz.event
2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017)
en_US
ethz.event.location
Vancouver, Canada
en_US
ethz.event.date
September 24-28, 2017
en_US
ethz.grant
Collaborative Aerial Robotic Workers
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
Piscataway, NJ
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::09559 - Chli, Margarita (ehemalig) / Chli, Margarita (former)
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::09559 - Chli, Margarita (ehemalig) / Chli, Margarita (former)
en_US
ethz.grant.agreementno
644128
ethz.grant.fundername
SBFI
ethz.grant.funderDoi
10.13039/501100007352
ethz.grant.program
H2020
ethz.date.deposited
2017-08-03T09:54:18Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2018-01-30T09:01:21Z
ethz.rosetta.lastUpdated
2021-02-14T23:17:34Z
ethz.rosetta.exportRequired
true
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Only%20look%20once,%20mining%20distinctive%20landmarks%20from%20ConvNet%20for%20visual%20place%20recognition&rft.date=2017&rft.spage=9&rft.epage=16&rft.au=Chen,%20Zetao&Maffra,%20Fabiola&Sa,%20Inkyu&Chli,%20Margarita&rft.isbn=978-1-5386-2682-5&978-1-5386-2681-8&978-1-5386-2683-2&rft.genre=proceeding&rft_id=info:doi/10.1109/IROS.2017.8202131&rft.btitle=2017%20IEEE/RSJ%20International%20Conference%20on%20Intelligent%20Robots%20and%20Systems%20(IROS)
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record