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
Extracting essential local object characteristics for 3D object categorization
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP. KTH, Skolan för datavetenskap och kommunikation (CSC), Centra, Centrum för Autonoma System, CAS.
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP. KTH, Skolan för datavetenskap och kommunikation (CSC), Centra, Centrum för Autonoma System, CAS.
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP. KTH, Skolan för datavetenskap och kommunikation (CSC), Centra, Centrum för Autonoma System, CAS.
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP. KTH, Skolan för datavetenskap och kommunikation (CSC), Centra, Centrum för Autonoma System, CAS.
Vise andre og tillknytning
2013 (engelsk)Inngår i: 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE conference proceedings, 2013, s. 2240-2247Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Most object classes share a considerable amount of local appearance and often only a small number of features are discriminative. The traditional approach to represent an object is based on a summarization of the local characteristics by counting the number of feature occurrences. In this paper we propose the use of a recently developed technique for summarizations that, rather than looking into the quantity of features, encodes their quality to learn a description of an object. Our approach is based on extracting and aggregating only the essential characteristics of an object class for a task. We show how the proposed method significantly improves on previous work in 3D object categorization. We discuss the benefits of the method in other scenarios such as robot grasping. We provide extensive quantitative and qualitative experiments comparing our approach to the state of the art to justify the described approach.

sted, utgiver, år, opplag, sider
IEEE conference proceedings, 2013. s. 2240-2247
Serie
IEEE International Conference on Intelligent Robots and Systems. Proceedings, ISSN 2153-0858
Emneord [en]
computer vision, robotics, 3D vision, object recognition
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-136370DOI: 10.1109/IROS.2013.6696670ISI: 000331367402060Scopus ID: 2-s2.0-84893753374ISBN: 978-146736358-7 (tryckt)OAI: oai:DiVA.org:kth-136370DiVA, id: diva2:675929
Konferanse
2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013; Tokyo; Japan; 3 November 2013 through 8 November 2013
Forskningsfinansiär
EU, FP7, Seventh Framework Programme, IST-FP7-270436EU, FP7, Seventh Framework Programme, FP7- ICT-288533Swedish Foundation for Strategic Research Swedish Research Council
Merknad

QC 20131216

Tilgjengelig fra: 2013-12-04 Laget: 2013-12-04 Sist oppdatert: 2018-01-11bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Kragic, Danica

Søk i DiVA

Av forfatter/redaktør
Madry, MariannaMaboudi Afkham, HeydarEk, Carl HenrikCarlsson, StefanKragic, Danica
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 140 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