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
3D pictorial structures for multiple view articulated pose estimation
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
2013 (engelsk)Inngår i: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, 2013, s. 3618-3625Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

We consider the problem of automatically estimating the 3D pose of humans from images, taken from multiple calibrated views. We show that it is possible and tractable to extend the pictorial structures framework, popular for 2D pose estimation, to 3D. We discuss how to use this framework to impose view, skeleton, joint angle and intersection constraints in 3D. The 3D pictorial structures are evaluated on multiple view data from a professional football game. The evaluation is focused on computational tractability, but we also demonstrate how a simple 2D part detector can be plugged into the framework.

sted, utgiver, år, opplag, sider
IEEE Computer Society, 2013. s. 3618-3625
Serie
IEEE Conference on Computer Vision and Pattern Recognition. Proceedings, ISSN 1063-6919
Emneord [en]
human pose estimation, motion capture, multiple view 3D reconstruction, part-based models, pictorial structures
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-129706DOI: 10.1109/CVPR.2013.464ISI: 000331094303088Scopus ID: 2-s2.0-84887329445OAI: oai:DiVA.org:kth-129706DiVA, id: diva2:653207
Konferanse
26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013; Portland, OR; United States; 23 June 2013 through 28 June 2013
Merknad

QC 20131007

Tilgjengelig fra: 2013-10-03 Laget: 2013-10-03 Sist oppdatert: 2014-03-24bibliografisk kontrollert
Inngår i avhandling
1. Human 3D Pose Estimation in the Wild: using Geometrical Models and Pictorial Structures
Åpne denne publikasjonen i ny fane eller vindu >>Human 3D Pose Estimation in the Wild: using Geometrical Models and Pictorial Structures
2013 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
sted, utgiver, år, opplag, sider
Stockholm: KTH Royal Institute of Technology, 2013. s. viii, 178
Serie
Trita-CSC-A, ISSN 1653-5723 ; 2013:15
HSV kategori
Identifikatorer
urn:nbn:se:kth:diva-138136 (URN)978-91-7501-980-2 (ISBN)
Disputas
2014-01-21, F3, KTH, Lindstedtsvägen 26, Stockholm, 13:00
Opponent
Veileder
Merknad

QC 20131218

Tilgjengelig fra: 2013-12-18 Laget: 2013-12-18 Sist oppdatert: 2018-01-11bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Søk i DiVA

Av forfatter/redaktør
Burenius, MagnusSullivan, JosephineCarlsson, Stefan
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 195 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