liu.seSearch for publications in DiVA
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Accurate Scale Estimation for Robust Visual Tracking
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.ORCID-id: 0000-0002-6096-3648
2014 (engelsk)Inngår i: Proceedings of the British Machine Vision Conference 2014 / [ed] Michel Valstar, Andrew French and Tony Pridmore, BMVA Press , 2014Konferansepaper, Poster (with or without abstract) (Fagfellevurdert)
Abstract [en]

Robust scale estimation is a challenging problem in visual object tracking. Most existing methods fail to handle large scale variations in complex image sequences. This paper presents a novel approach for robust scale estimation in a tracking-by-detection framework. The proposed approach works by learning discriminative correlation filters based on a scale pyramid representation. We learn separate filters for translation and scale estimation, and show that this improves the performance compared to an exhaustive scale search. Our scale estimation approach is generic as it can be incorporated into any tracking method with no inherent scale estimation.

Experiments are performed on 28 benchmark sequences with significant scale variations. Our results show that the proposed approach significantly improves the performance by 18.8 % in median distance precision compared to our baseline. Finally, we provide both quantitative and qualitative comparison of our approach with state-of-the-art trackers in literature. The proposed method is shown to outperform the best existing tracker by 16.6 % in median distance precision, while operating at real-time.

sted, utgiver, år, opplag, sider
BMVA Press , 2014.
HSV kategori
Identifikatorer
URN: urn:nbn:se:liu:diva-113948DOI: 10.5244/C.28.65ISBN: 1901725529 (tryckt)OAI: oai:DiVA.org:liu-113948DiVA, id: diva2:785778
Konferanse
British Machine Vision Conference, Nottingham, September 1-5, 2014
Tilgjengelig fra: 2015-02-03 Laget: 2015-02-03 Sist oppdatert: 2019-11-11bibliografisk kontrollert

Open Access i DiVA

fulltext(2490 kB)10628 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 2490 kBChecksum SHA-512
55515ae8d41c6954635a6c3aca4316911c99f73aceff4011f5146ce5dd8c2353f15aca51810787f57dcac43d46ecf68dba0cc083628e99d9b5c65e5f5f172d82
Type fulltextMimetype application/pdf
Extended Abstract(779 kB)333 nedlastinger
Filinformasjon
Fil ATTACHMENT01.pdfFilstørrelse 779 kBChecksum SHA-512
065ae4f37692c55f3fe8c268a8d6465b40425ff8f2fa58da854ae811ef6db01751f7577991bff6ea06c626a4e4d1559a82fa4bfe87b2acb9040f27aa09b9783d
Type attachmentMimetype application/pdf

Andre lenker

Forlagets fulltekst

Personposter BETA

Danelljan, MartinHäger, GustavKhan, FahadFelsberg, Michael

Søk i DiVA

Av forfatter/redaktør
Danelljan, MartinHäger, GustavKhan, FahadFelsberg, Michael
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 10628 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 19881 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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