liu.seSök publikationer i DiVA
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
ATOM: Accurate tracking by overlap maximization
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.ORCID-id: 0000-0002-6096-3648
2019 (Engelska)Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

While recent years have witnessed astonishing improvements in visual tracking robustness, the advancements in tracking accuracy have been limited. As the focus has been directed towards the development of powerful classifiers, the problem of accurate target state estimation has been largely overlooked. In fact, most trackers resort to a simple multi-scale search in order to estimate the target bounding box. We argue that this approach is fundamentally limited since target estimation is a complex task, requiring highlevel knowledge about the object. We address this problem by proposing a novel tracking architecture, consisting of dedicated target estimation and classification components. High level knowledge is incorporated into the target estimation through extensive offline learning. Our target estimation component is trained to predict the overlap between the target object and an estimated bounding box. By carefully integrating targetspecific information, our approach achieves previously unseen bounding box accuracy. We further introduce a classification component that is trained online to guarantee high discriminative power in the presence of distractors. Our final tracking framework sets a new state-of-the-art on five challenging benchmarks. On the new large-scale TrackingNet dataset, our tracker ATOM achieves a relative gain of 15% over the previous best approach, while running at over 30 FPS. Code and models are available at https://github.com/visionml/pytracking.

Ort, förlag, år, upplaga, sidor
2019.
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Identifikatorer
URN: urn:nbn:se:liu:diva-163194OAI: oai:DiVA.org:liu-163194DiVA, id: diva2:1387537
Konferens
IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, June 16th - June 20th, 2019
Tillgänglig från: 2020-01-22 Skapad: 2020-01-22 Senast uppdaterad: 2020-02-06Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Personposter BETA

Danelljan, MartinBhat, GoutamKhan, Fahad ShahbazFelsberg, Michael

Sök vidare i DiVA

Av författaren/redaktören
Danelljan, MartinBhat, GoutamKhan, Fahad ShahbazFelsberg, Michael
Av organisationen
DatorseendeTekniska fakulteten
Datorseende och robotik (autonoma system)

Sök vidare utanför DiVA

GoogleGoogle Scholar

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 10 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf