Show simple item record

dc.contributor.author
Mascaro, Ruben
dc.contributor.author
Pinto Teixeira, Lucas
dc.contributor.author
Chli, Margarita
dc.date.accessioned
2022-03-23T08:25:24Z
dc.date.available
2022-03-23T08:11:07Z
dc.date.available
2022-03-23T08:25:24Z
dc.date.issued
2022-04
dc.identifier.issn
2377-3766
dc.identifier.other
10.1109/LRA.2022.3146502
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/538641
dc.identifier.doi
10.3929/ethz-b-000527844
dc.description.abstract
Robots operating in real-world settings often need to plan interactions with surrounding scene elements and therefore, it is crucial for them to understand their workspace at the level of individual objects. In this spirit, this work presents a novel approach to progressively build instance-level, dense 3D maps from color and depth cues acquired by either a moving RGB-D sensor or a camera-LiDAR setup, whose pose is being tracked. The proposed framework processes each input RGB image with a semantic instance segmentation neural network and uses depth information to extract a set of per-frame, semantically labeled 3D instance segments, which then get matched to object instances already identified in previous views. Following integration of these newly detected instance segments in a global volumetric map, an efficient label diffusion scheme that considers multi-view instance predictions together with the reconstructed scene geometry is used to refine 3D segmentation boundaries. Experiments on indoor benchmarking RGB-D sequences show that the proposed system achieves state-of-the-art performance in terms of 3D segmentation accuracy, while reducing the computational processing cost required at each frame. Furthermore, the applicability of the system to challenging domains outside the traditional office scenes is demonstrated by testing it on a robotic excavator equipped with a calibrated camera-LiDAR setup, with the goal of segmenting individual boulders in a highly cluttered construction scenario.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
Object Detection and Segmentation
en_US
dc.subject
RGB-D Perception
en_US
dc.subject
Mapping
en_US
dc.title
Volumetric Instance-Level Semantic Mapping Via Multi-View 2D-to-3D Label Diffusion
en_US
dc.type
Journal Article
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2022-01-27
ethz.journal.title
IEEE Robotics and Automation Letters
ethz.journal.volume
7
en_US
ethz.journal.issue
2
en_US
ethz.pages.start
3531
en_US
ethz.pages.end
3538
en_US
ethz.size
8 p.
en_US
ethz.version.deposit
acceptedVersion
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
New York, 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::09559 - Chli, Margarita (ehemalig) / Chli, Margarita (former)
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02100 - Dep. Architektur / Dep. of Architecture::02284 - NFS Digitale Fabrikation / NCCR Digital Fabrication
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.date.deposited
2022-01-24T11:47:07Z
ethz.source
FORM
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2022-03-23T08:25:47Z
ethz.rosetta.lastUpdated
2022-03-29T20:44:13Z
ethz.rosetta.exportRequired
true
ethz.rosetta.versionExported
true
dc.identifier.olduri
http://hdl.handle.net/20.500.11850/527844
dc.identifier.olduri
http://hdl.handle.net/20.500.11850/534163
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Volumetric%20Instance-Level%20Semantic%20Mapping%20Via%20Multi-View%202D-to-3D%20Label%20Diffusion&rft.jtitle=IEEE%20Robotics%20and%20Automation%20Letters&rft.date=2022-04&rft.volume=7&rft.issue=2&rft.spage=3531&rft.epage=3538&rft.issn=2377-3766&rft.au=Mascaro,%20Ruben&Pinto%20Teixeira,%20Lucas&Chli,%20Margarita&rft.genre=article&rft_id=info:doi/10.1109/LRA.2022.3146502&
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record