Show simple item record

dc.contributor.author
Oertel, Amadeus
dc.contributor.author
Cieslewski, Titus
dc.contributor.author
Scaramuzza, Davide
dc.date.accessioned
2020-09-11T05:57:29Z
dc.date.available
2020-09-11T02:57:33Z
dc.date.available
2020-09-11T05:57:29Z
dc.date.issued
2020-10
dc.identifier.issn
2377-3766
dc.identifier.other
10.1109/LRA.2020.3009077
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/439890
dc.description.abstract
In this letter, we propose to augment image-based place recognition with structural cues. Specifically, these structural cues are obtained using structure-from-motion, such that no additional sensors are needed for place recognition. This is achieved by augmenting the 2D convolutional neural network (CNN) typically used for image-based place recognition with a 3D CNN that takes as input a voxel grid derived from the structure-from-motion point cloud. We evaluate different methods for fusing the 2D and 3D features and obtain best performance with global average pooling and simple concatenation. On the Oxford RobotCar dataset, the resulting descriptor exhibits superior recognition performance compared to descriptors extracted from only one of the input modalities, including state-of-The-Art image-based descriptors. Especially at low descriptor dimensionalities, we outperform state-of-The-Art descriptors by up to 90%. © 2016 IEEE.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.subject
Recognition
en_US
dc.subject
localization
en_US
dc.title
Augmenting visual place recognition with structural cues
en_US
dc.type
Journal Article
dc.date.published
2020-07-14
ethz.journal.title
IEEE Robotics and Automation Letters
ethz.journal.volume
5
en_US
ethz.journal.issue
4
en_US
ethz.pages.start
5534
en_US
ethz.pages.end
5541
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
New York, NY
en_US
ethz.publication.status
published
en_US
ethz.date.deposited
2020-09-11T02:57:43Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2020-09-11T05:57:43Z
ethz.rosetta.lastUpdated
2021-02-15T17:10:02Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Augmenting%20visual%20place%20recognition%20with%20structural%20cues&rft.jtitle=IEEE%20Robotics%20and%20Automation%20Letters&rft.date=2020-10&rft.volume=5&rft.issue=4&rft.spage=5534&rft.epage=5541&rft.issn=2377-3766&rft.au=Oertel,%20Amadeus&Cieslewski,%20Titus&Scaramuzza,%20Davide&rft.genre=article&rft_id=info:doi/10.1109/LRA.2020.3009077&
 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