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
Weighted Update and Comparison for Channel-Based Distribution Field Tracking
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology. (Linköping University, Department of Electrical Engineering, Computer Vision)
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology. Linköping University, Center for Medical Image Science and Visualization (CMIV). (Linköping University, Department of Electrical Engineering, Computer Vision)ORCID iD: 0000-0002-6096-3648
2015 (English)In: COMPUTER VISION - ECCV 2014 WORKSHOPS, PT II, Springer, 2015, Vol. 8926, 218-231 p.Conference paper, Published paper (Refereed)
Abstract [en]

There are three major issues for visual object trackers: modelrepresentation, search and model update. In this paper we address thelast two issues for a specic model representation, grid based distributionmodels by means of channel-based distribution elds. Particularly weaddress the comparison part of searching. Previous work in the areahas used standard methods for comparison and update, not exploitingall the possibilities of the representation. In this work we propose twocomparison schemes and one update scheme adapted to the distributionmodel. The proposed schemes signicantly improve the accuracy androbustness on the Visual Object Tracking (VOT) 2014 Challenge dataset.

Place, publisher, year, edition, pages
Springer, 2015. Vol. 8926, 218-231 p.
Series
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 8926
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-114116DOI: 10.1007/978-3-319-16181-5_15ISI: 000362495500015ISBN: 978-3-319-16181-5 (print)OAI: oai:DiVA.org:liu-114116DiVA: diva2:787563
Conference
13th European Conference on Computer Vision (ECCV)
Available from: 2015-02-10 Created: 2015-02-09 Last updated: 2016-05-04

Open Access in DiVA

fulltext(1255 kB)120 downloads
File information
File name FULLTEXT01.pdfFile size 1255 kBChecksum SHA-512
996a97051842e8f3b061e8d00a84f3c57f9c95946667c8c00fab7232b2dfb991d37a5e7f30169600a71e0bfd18a5f9ad2dba9d067c4a71fa1eb174dbae31c2eb
Type fulltextMimetype application/pdf

Other links

Publisher's full texthttp://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/ECCV_2014/workshops/w09/W9-03.pdf

Authority records BETA

Öfjäll, KristofferFelsberg, Michael

Search in DiVA

By author/editor
Öfjäll, KristofferFelsberg, Michael
By organisation
Computer VisionThe Institute of TechnologyCenter for Medical Image Science and Visualization (CMIV)
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 120 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: 1308 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