oru.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Compressed Voxel-Based Mapping Using Unsupervised Learning
Örebro universitet, Institutionen för naturvetenskap och teknik. (Center for Autonomous Applied Sensor Systems (AASS))ORCID-id: 0000-0001-7035-5710
Örebro universitet, Institutionen för naturvetenskap och teknik. (Center for Autonomous Applied Sensor Systems (AASS))ORCID-id: 0000-0003-4026-7490
Örebro universitet, Institutionen för naturvetenskap och teknik. (Center for Autonomous Applied Sensor Systems (AASS))ORCID-id: 0000-0002-6013-4874
Örebro universitet, Institutionen för naturvetenskap och teknik. (Center for Autonomous Applied Sensor Systems (AASS))ORCID-id: 0000-0003-0217-9326
Vise andre og tillknytning
2017 (engelsk)Inngår i: Robotics, E-ISSN 2218-6581, Vol. 6, nr 3, artikkel-id 15Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

In order to deal with the scaling problem of volumetric map representations, we propose spatially local methods for high-ratio compression of 3D maps, represented as truncated signed distance fields. We show that these compressed maps can be used as meaningful descriptors for selective decompression in scenarios relevant to robotic applications. As compression methods, we compare using PCA-derived low-dimensional bases to nonlinear auto-encoder networks. Selecting two application-oriented performance metrics, we evaluate the impact of different compression rates on reconstruction fidelity as well as to the task of map-aided ego-motion estimation. It is demonstrated that lossily reconstructed distance fields used as cost functions for ego-motion estimation can outperform the original maps in challenging scenarios from standard RGB-D (color plus depth) data sets due to the rejection of high-frequency noise content.

sted, utgiver, år, opplag, sider
Basel, Switzerland: MDPI AG , 2017. Vol. 6, nr 3, artikkel-id 15
Emneord [en]
3D mapping, TSDF, compression, dictionary learning, auto-encoder, denoising
HSV kategori
Identifikatorer
URN: urn:nbn:se:oru:diva-64420DOI: 10.3390/robotics6030015ISI: 000419218300002Scopus ID: 2-s2.0-85030989493OAI: oai:DiVA.org:oru-64420DiVA, id: diva2:1175909
Merknad

Funding Agencies:

European Commission  FP7-ICT-270350 

H-ICT  732737 

Tilgjengelig fra: 2018-01-19 Laget: 2018-01-19 Sist oppdatert: 2018-01-19bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Canelhas, Daniel R.Schaffernicht, ErikStoyanov, TodorLilienthal, Achim

Søk i DiVA

Av forfatter/redaktør
Canelhas, Daniel R.Schaffernicht, ErikStoyanov, TodorLilienthal, Achim
Av organisasjonen
I samme tidsskrift
Robotics

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 202 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf