Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • 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
Spatio-temporal scale selection in video data
KTH, Skolan för datavetenskap och kommunikation (CSC), Beräkningsvetenskap och beräkningsteknik (CST). (Computational Brain Science Lab)ORCID-id: 0000-0002-9081-2170
2018 (engelsk)Inngår i: Journal of Mathematical Imaging and Vision, ISSN 0924-9907, E-ISSN 1573-7683, Vol. 60, nr 4, s. 525-562Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

This work presents a theory and methodology for simultaneous detection of local spatial and temporal scales in video data. The underlying idea is that if we process video data by spatio-temporal receptive fields at multiple spatial and temporal scales, we would like to generate hypotheses about the spatial extent and the temporal duration of the underlying spatio-temporal image structures that gave rise to the feature responses.

For two types of spatio-temporal scale-space representations, (i) a non-causal Gaussian spatio-temporal scale space for offline analysis of pre-recorded video sequences and (ii) a time-causal and time-recursive spatio-temporal scale space for online analysis of real-time video streams, we express sufficient conditions for spatio-temporal feature detectors in terms of spatio-temporal receptive fields to deliver scale covariant and scale invariant feature responses.

We present an in-depth theoretical analysis of the scale selection properties of eight types of spatio-temporal interest point detectors in terms of either: (i)-(ii) the spatial Laplacian applied to the first- and second-order temporal derivatives, (iii)-(iv) the determinant of the spatial Hessian applied to the first- and second-order temporal derivatives, (v) the determinant of the spatio-temporal Hessian matrix, (vi) the spatio-temporal Laplacian and (vii)-(viii) the first- and second-order temporal derivatives of the determinant of the spatial Hessian matrix. It is shown that seven of these spatio-temporal feature detectors allow for provable scale covariance and scale invariance. Then, we describe a time-causal and time-recursive algorithm for detecting sparse spatio-temporal interest points from video streams and show that it leads to intuitively reasonable results.

An experimental quantification of the accuracy of the spatio-temporal scale estimates and the amount of temporal delay obtained these spatio-temporal interest point detectors is given showing that: (i) the spatial and temporal scale selection properties predicted by the continuous theory are well preserved in the discrete implementation and (ii) the spatial Laplacian or the determinant of the spatial Hessian applied to the first- and second-order temporal derivatives lead to much shorter temporal delays in a time-causal implementation compared to the determinant of the spatio-temporal Hessian or the first- and second-order temporal derivatives of the determinant of the spatial Hessian matrix.

sted, utgiver, år, opplag, sider
Springer Science+Business Media B.V., 2018. Vol. 60, nr 4, s. 525-562
Emneord [en]
Scale selection, Scale, Scale space, Spatial, Temporal, Spatio-temporal, Scale invariance, Scale covariance, Feature detection, Differential invariant, Interest point, Video analysis, Computer vision
HSV kategori
Forskningsprogram
Datalogi
Identifikatorer
URN: urn:nbn:se:kth:diva-214932DOI: 10.1007/s10851-017-0766-9ISI: 000428612400004Scopus ID: 2-s2.0-85032330463OAI: oai:DiVA.org:kth-214932DiVA, id: diva2:1144192
Prosjekter
Scale-space theory for invariant and covariant visual receptive fieldsTime-causal receptive fields for computer vision and computational modelling of biological vision
Forskningsfinansiär
Swedish Research Council, 2014-4083Stiftelsen Olle Engkvist Byggmästare, 2015/465
Merknad

QC 20171129

Tilgjengelig fra: 2017-09-25 Laget: 2017-09-25 Sist oppdatert: 2018-12-06bibliografisk kontrollert

Open Access i DiVA

fulltext(7775 kB)66 nedlastinger
Filinformasjon
Fil FULLTEXT02.pdfFilstørrelse 7775 kBChecksum SHA-512
9b63eff807b0c0c65ac558f7e0ea155c84723ee6dad0e73084045446f7091d705541a759b19f566f3ab4b5f04691eea525893cca88c83ca6609e66bca97f2814
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Søk i DiVA

Av forfatter/redaktør
Lindeberg, Tony
Av organisasjonen
I samme tidsskrift
Journal of Mathematical Imaging and Vision

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 68 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: 717 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • 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