liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Accurate Interpolation in Appearance-Based Pose Estimation
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.ORCID iD: 0000-0002-6096-3648
2007 (English)In: Image Analysis: 15th Scandinavian Conference, SCIA 2007, Aalborg, Denmark, June 10-14, 2007 / [ed] Bjarne Kjær Ersbøll and Kim Steenstrup Pedersen, Springer Berlin/Heidelberg, 2007, 1-10 p.Conference paper, Published paper (Refereed)
Abstract [en]

One problem in appearance-based pose estimation is the need for many training examples, i.e. images of the object in a large number of known poses. Some invariance can be obtained by considering translations, rotations and scale changes in the image plane, but the remaining degrees of freedom are often handled simply by sampling the pose space densely enough. This work presents a method for accurate interpolation between training views using local linear models. As a view representation local soft orientation histograms are used. The derivative of this representation with respect to the image plane transformations is computed, and a Gauss-Newton optimization is used to optimize all pose parameters simultaneously, resulting in an accurate estimate.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2007. 1-10 p.
Series
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 4522
National Category
Computer Science
Identifiers
URN: urn:nbn:se:liu:diva-38253DOI: 10.1007/978-3-540-73040-8_1ISI: 000247364000001Local ID: 43285ISBN: 978-3-540-73039-2 (print)ISBN: 978-3-540-73040-8 (print)OAI: oai:DiVA.org:liu-38253DiVA: diva2:259102
Conference
15th Scandinavian Conference, SCIA 2007, Aalborg, Denmark, June 10-14, 2007
Available from: 2009-10-10 Created: 2009-10-10 Last updated: 2016-05-04Bibliographically approved

Open Access in DiVA

fulltext(231 kB)311 downloads
File information
File name FULLTEXT01.pdfFile size 231 kBChecksum SHA-512
9377b08e3feaa15f03475df4f9101c8f4cbb5291bb8fe4633769ceb2ccd389df3d5bd298e9676a4d666d7ea4256f24d59bcf6007a71220a4025ead88a7ac9620
Type fulltextMimetype application/pdf

Other links

Publisher's full textfind book at a swedish library/hitta boken i ett svenskt bibliotek

Authority records BETA

Jonsson, ErikFelsberg, Michael

Search in DiVA

By author/editor
Jonsson, ErikFelsberg, Michael
By organisation
Computer VisionThe Institute of Technology
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 311 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 396 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf