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
Improving Discriminative Correlation Filters for Visual Tracking
Linköping University, Department of Electrical Engineering, Computer Vision.
2015 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Förbättring av korrelationsfilter för visuell följning (Swedish)
Abstract [en]

Generic visual tracking is one of the classical problems in computer vision. In this problem, no prior knowledge of the target is available aside from a bounding box in the initial frame of the sequence. The generic visual tracking is a difficult task due to a number of factors such as momentary occlusions, target rotations, changes in target illumination and variations in the target size. In recent years, discriminative correlation filter (DCF) based trackers have shown promising results for visual tracking. These DCF based methods use the Fourier transform to efficiently calculate detection and model updates, allowing significantly higher frame rates than competing methods. However, existing DCF based methods only estimate translation of the object while ignoring changes in size.This thesis investigates the problem of accurately estimating the scale variations within a DCF based framework. A novel scale estimation method is proposed by explicitly constructing translation and scale filters. The proposed scale estimation technique is robust and significantly improve the tracking performance, while operating at real-time. In addition, a comprehensive evaluation of feature representations in a DCF framework is performed. Experiments are performed on the benchmark OTB-2015 dataset, as well as the VOT 2014 dataset. The proposed methods are shown to significantly improve the performance of existing DCF based trackers.

Abstract [sv]

Allmän visuell följning är ett klassiskt problem inom datorseende. I den vanliga formuleringen antas ingen förkunskap om objektet som skall följas, utöver en initial rektangel i en videosekvens första bild.Detta är ett mycket svårt problem att lösa allmänt på grund av occlusioner, rotationer, belysningsförändringar och variationer i objektets uppfattde storlek. På senare år har följningsmetoder baserade på diskriminativea korrelationsfilter gett lovande resultat inom området. Dessa metoder är baserade på att med hjälp av Fourertransformen effektivt beräkna detektioner och modellupdateringar, samtidigt som de har mycket bra prestanda och klarar av många hundra bilder per sekund. De nuvarande metoderna uppskattar dock bara translationen hos det följda objektet, medans skalförändringar ignoreras. Detta examensarbete utvärderar ett antal metoder för att göra skaluppskattningar inom ett korrelationsfilterramverk. En innovativ metod baserad på att konstruera separata skal och translationsfilter. Den föreslagna metoden är robust och har signifikant bättre följningsprestanda, samtidigt som den kan användas i realtid. Det utförs också en utvärdering av olika särdragsrepresentationer på två stora benchmarking dataset för följning.

Place, publisher, year, edition, pages
2015. , 47 p.
Keyword [en]
Tracking, Computer vision
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-125963ISRN: LiTH-ISY-EX-15/4919--SEOAI: oai:DiVA.org:liu-125963DiVA: diva2:910736
Subject / course
Computer Vision Laboratory
Presentation
2015-12-21, 08:51 (English)
Supervisors
Examiners
Available from: 2016-03-14 Created: 2016-03-10 Last updated: 2016-03-14Bibliographically approved

Open Access in DiVA

fulltext(11887 kB)314 downloads
File information
File name FULLTEXT01.pdfFile size 11887 kBChecksum SHA-512
7e0a3735bc4ce57cfe084d9a87a4013362557682eb3326cfe0c9a2b4c5bda1c4df0b76ad91960e5b3749f24d18993431e44b0e19556947a7b437d6ece305e7f7
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Häger, Gustav
By organisation
Computer Vision
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 314 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

urn-nbn

Altmetric score

urn-nbn
Total: 563 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