Show simple item record

dc.contributor.author
Taubner, Felix
dc.contributor.author
Tschopp, Florian
dc.contributor.author
Novkovic, Tonci
dc.contributor.author
Siegwart, Roland
dc.contributor.author
Furrer, Fadri
dc.date.accessioned
2021-03-18T07:57:51Z
dc.date.available
2021-03-13T04:29:19Z
dc.date.available
2021-03-18T07:57:51Z
dc.date.issued
2020
dc.identifier.isbn
978-1-7281-8128-8
en_US
dc.identifier.isbn
978-1-7281-8129-5
en_US
dc.identifier.other
10.1109/3DV50981.2020.00101
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/474211
dc.description.abstract
Current research on visual place recognition mostly focuses on aggregating local visual features of an image into a single vector representation. Therefore, high-level information such as the geometric arrangement of the features is typically lost. In this paper, we introduce a novel learning-based approach to place recognition, using RGB-D cameras and line clusters as visual and geometric features. We state the place recognition problem as a problem of recognizing clusters of lines instead of individual patches, thus maintaining structural information. In our work, line clusters are defined as lines that make up individual objects, hence our place recognition approach can be understood as object recognition. 3D line segments are detected in RGB-D images using state-of-the-art techniques. We present a neural network architecture based on the attention mechanism for frame-wise line clustering. A similar neural network is used for the description of these clusters with a compact embedding of 128 floating point numbers, trained with triplet loss on training data obtained from the InteriorNet dataset. We show experiments on a large number of indoor scenes and compare our method with the bag-of-words image-retrieval approach using SIFT and SuperPoint features and the global descriptor NetVLAD. Trained only on synthetic data, our approach generalizes well to real-world data captured with Kinect sensors, while also providing information about the geometric arrangement of instances. © 2020 IEEE
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.title
LCD – Line Clustering and Description for Place Recognition
en_US
dc.type
Conference Paper
dc.date.published
2021-01-19
ethz.book.title
2020 International Conference on 3D Vision (3DV)
en_US
ethz.pages.start
908
en_US
ethz.pages.end
917
en_US
ethz.event
8th International Conference on 3D Vision (3DV 2020) (virtual)
en_US
ethz.event.location
Fukuoka, Japan
en_US
ethz.event.date
November 25-28, 2020
en_US
ethz.notes
Due to the Coronavirus (COVID-19) the conference was conducted virtually.
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
Piscataway, NJ
en_US
ethz.publication.status
published
en_US
ethz.date.deposited
2021-03-13T04:29:33Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-03-18T07:58:04Z
ethz.rosetta.lastUpdated
2022-03-29T05:51:21Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=LCD%20%E2%80%93%20Line%20Clustering%20and%20Description%20for%20Place%20Recognition&rft.date=2020&rft.spage=908&rft.epage=917&rft.au=Taubner,%20Felix&Tschopp,%20Florian&Novkovic,%20Tonci&Siegwart,%20Roland&Furrer,%20Fadri&rft.isbn=978-1-7281-8128-8&978-1-7281-8129-5&rft.genre=proceeding&rft_id=info:doi/10.1109/3DV50981.2020.00101&rft.btitle=2020%20International%20Conference%20on%203D%20Vision%20(3DV)
 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