Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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
Dense scale selection over space, time and space-time
KTH, Skolan för elektroteknik och datavetenskap (EECS), Beräkningsvetenskap och beräkningsteknik (CST). (Computational Brain Science Lab)ORCID-id: 0000-0002-9081-2170
2018 (engelsk)Inngår i: SIAM Journal on Imaging Sciences, ISSN 1936-4954, E-ISSN 1936-4954, Vol. 11, nr 1, s. 407-441Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Scale selection methods based on local extrema over scale of scale-normalized derivatives have been primarily developed to be applied sparsely---at image points where the magnitude of a scale-normalized differential expression additionally assumes local extrema over the domain where the data are defined. This paper presents a methodology for performing dense scale selection, so that hypotheses about local characteristic scales in images, temporal signals, and video can be computed at every image point and every time moment. A critical problem when designing mechanisms for dense scale selection is that the scale at which scale-normalized differential entities assume local extrema over scale can be strongly dependent on the local order of the locally dominant differential structure. To address this problem, we propose a methodology where local extrema over scale are detected of a quasi quadrature measure involving scale-space derivatives up to order two and propose two independent mechanisms to reduce the phase dependency of the local scale estimates by (i) introducing a second layer of postsmoothing prior to the detection of local extrema over scale, and (ii) performing local phase compensation based on a model of the phase dependency of the local scale estimates depending on the relative strengths between first- and second-order differential structures. This general methodology is applied over three types of domains: (i) spatial images, (ii) temporal signals, and (iii) spatio-temporal video. Experiments demonstrate that the proposed methodology leads to intuitively reasonable results with local scale estimates that reflect variations in the characteristic scales of locally dominant structures over space and time.

sted, utgiver, år, opplag, sider
Society for Industrial and Applied Mathematics, 2018. Vol. 11, nr 1, s. 407-441
Emneord [en]
scale, scale selection, spatial, temporal, spatio-temporal, scale invariance, scale space, feature detection, differential invariant, video analysis, image analysis, computer vision
HSV kategori
Forskningsprogram
Datalogi
Identifikatorer
URN: urn:nbn:se:kth:diva-218340DOI: 10.1137/17M114892XISI: 000428946200014Scopus ID: 2-s2.0-85045692496OAI: oai:DiVA.org:kth-218340DiVA, id: diva2:1160646
Prosjekter
Scale-space theory for invariant and covariant visual receptive fields
Forskningsfinansiär
Swedish Research Council, 2014-4083
Merknad

QC 20180227

Tilgjengelig fra: 2017-11-27 Laget: 2017-11-27 Sist oppdatert: 2019-09-23bibliografisk kontrollert

Open Access i DiVA

fulltext(2464 kB)158 nedlastinger
Filinformasjon
Fil FULLTEXT02.pdfFilstørrelse 2464 kBChecksum SHA-512
8c5d4f4ed833120c812da1a5c304f7fd9a522c4f6b485af596e4b63dd423695894cbba70a754a024c7e9bc2de464ff8207367c78e9f82d01bb4cd623530f9721
Type fulltextMimetype application/pdf
fulltext(1174 kB)42 nedlastinger
Filinformasjon
Fil FULLTEXT03.pdfFilstørrelse 1174 kBChecksum SHA-512
a618c37ac1a8cd3e1d38727a0e35ac2e5e8d2e196c34b15889d8ebbfdf3f205575eda351981e515b20fc43077de5a3498736a6431ace4c33da29001969989f1a
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Søk i DiVA

Av forfatter/redaktør
Lindeberg, Tony
Av organisasjonen
I samme tidsskrift
SIAM Journal on Imaging Sciences

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 200 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 1104 treff
RefereraExporteraLink to record
Permanent link

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