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

Direct link
Cite
Citation style
  • apa
  • 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
BASE: Probably a Better Approach to Visual Multi-Object Tracking
FFI, Norwegian Defence Research Establishment, Norway.ORCID iD: 0000-0002-3008-7712
FFI, Norwegian Defence Research Establishment, Norway.ORCID iD: 0009-0004-6118-8593
FFI, Norwegian Defence Research Establishment, Norway.ORCID iD: 0009-0001-6351-8128
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. University of Oslo, Norway.ORCID iD: 0000-0002-6763-5487
Show others and affiliations
2024 (English)In: Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Rome, Italy, 2024, SciTePress, 2024, p. 110-121Conference paper, Published paper (Refereed)
Abstract [en]

The field of visual object tracking is dominated by methods that combine simple tracking algorithms and ad hoc schemes. Probabilistic tracking algorithms, which are leading in other fields, are surprisingly absent from the leaderboards. We found that accounting for distance in target kinematics, exploiting detector confidence and modelling non-uniform clutter characteristics is critical for a probabilistic tracker to work in visual tracking. Previous probabilistic methods fail to address most or all these aspects, which we believe is why they fall so far behind current state-of-the-art (SOTA) methods (there are no probabilistic trackers in the MOT17 top 100). To rekindle progress among probabilistic approaches, we propose a set of pragmatic models addressing these challenges, and demonstrate how they can be incorporated into a probabilistic framework. We present BASE (Bayesian Approximation Single-hypothesis Estimator), a simple, performant and easily extendible visual tracker, achieving state-of-the-art (SOTA) on MOT17 and MOT20, without using Re-Id. Code available at https://github.com/ffi-no/paper-base-visapp-2024.

Place, publisher, year, edition, pages
SciTePress, 2024. p. 110-121
Series
VISIGRAPP, ISSN 2184-4321
Keywords [en]
Visual Multi-Object Tracking, Probabilistic Tracking, Distance-Aware, Association-Less Track Management
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-201409DOI: 10.5220/0012386600003660OAI: oai:DiVA.org:liu-201409DiVA, id: diva2:1843135
Conference
International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - VISAPP
Available from: 2024-03-07 Created: 2024-03-07 Last updated: 2024-03-07

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Authority records

Ahlberg, Jörgen

Search in DiVA

By author/editor
Larsen, MartinRolfsfjord, SigmundGusland, DanielAhlberg, JörgenMathiassen, Kim
By organisation
Computer VisionFaculty of Science & Engineering
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 58 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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