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
Detecting, segmenting and tracking unknown objects using multi-label MRF inference
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP. KTH, Skolan för datavetenskap och kommunikation (CSC), Centra, Centrum för Autonoma System, CAS.ORCID-id: 0000-0003-0579-3372
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.ORCID-id: 0000-0003-2965-2953
2014 (engelsk)Inngår i: Computer Vision and Image Understanding, ISSN 1077-3142, E-ISSN 1090-235X, Vol. 118, s. 111-127Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

This article presents a unified framework for detecting, segmenting and tracking unknown objects in everyday scenes, allowing for inspection of object hypotheses during interaction over time. A heterogeneous scene representation is proposed, with background regions modeled as a combinations of planar surfaces and uniform clutter, and foreground objects as 3D ellipsoids. Recent energy minimization methods based on loopy belief propagation, tree-reweighted message passing and graph cuts are studied for the purpose of multi-object segmentation and benchmarked in terms of segmentation quality, as well as computational speed and how easily methods can be adapted for parallel processing. One conclusion is that the choice of energy minimization method is less important than the way scenes are modeled. Proximities are more valuable for segmentation than similarity in colors, while the benefit of 3D information is limited. It is also shown through practical experiments that, with implementations on GPUs, multi-object segmentation and tracking using state-of-art MRF inference methods is feasible, despite the computational costs typically associated with such methods.

sted, utgiver, år, opplag, sider
Elsevier, 2014. Vol. 118, s. 111-127
Emneord [en]
Figure-ground segmentation, Active perception, MRF, Multi-object tracking, Object detection, GPU acceleration
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-133215DOI: 10.1016/j.cviu.2013.10.007ISI: 000328591500011Scopus ID: 2-s2.0-84890998700OAI: oai:DiVA.org:kth-133215DiVA, id: diva2:659983
Merknad

QC 20140122. Updated from accepted to published.

Tilgjengelig fra: 2013-10-28 Laget: 2013-10-28 Sist oppdatert: 2018-01-11bibliografisk kontrollert

Open Access i DiVA

2011_CVIU_bbk(2533 kB)617 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 2533 kBChecksum SHA-512
099f96787c96f7113b1497e57e134823744a15b41ab0ab9c031236fdd17ac6fd9bdc47d042d47d1e1ea4e4d1d84820b6de889fa437132b7de2084c2289d70e81
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Björkman, MårtenKragic, Danica

Søk i DiVA

Av forfatter/redaktør
Björkman, MårtenBergström, NiklasKragic, Danica
Av organisasjonen
I samme tidsskrift
Computer Vision and Image Understanding

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 617 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 607 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