Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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
Spatio-temporal scale selection in video data
KTH, School of Computer Science and Communication (CSC), Computational Science and Technology (CST). (Computational Brain Science Lab)ORCID iD: 0000-0002-9081-2170
2017 (English)In: Scale Space and Variational Methods in Computer Vision, Springer-Verlag Tokyo Inc., 2017, Vol. 10302, p. 3-15Conference paper, Published paper (Refereed)
Abstract [en]

We present a theory and a method 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.

A theoretical analysis is given of the scale selection properties of six types of spatio-temporal interest point detectors, showing that five of them 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.

Place, publisher, year, edition, pages
Springer-Verlag Tokyo Inc., 2017. Vol. 10302, p. 3-15
Series
Springer Lecture Notes in Computer Science, ISSN 0302-9743 ; 10302
Keywords [en]
scale space, scale, scale selection, spatial, temporal, spatio-temporal, scale invariance, feature detection, differential invariant, video analysis, computer vision
National Category
Computer Vision and Robotics (Autonomous Systems) Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-202415DOI: 10.1007/978-3-319-58771-4_1ISI: 000432210900001Scopus ID: 2-s2.0-85019743724ISBN: 978-3-319-58771-4 (print)OAI: oai:DiVA.org:kth-202415DiVA, id: diva2:1076848
Conference
SSVM 2017: 6th International Conference on Scale Space and Variational Methods in Computer Vision, Kolding, Denmark, June 4-8, 2017
Projects
Scale-space theory for invariant and covariant visual receptive fieldsTime-causal receptive fields for computer vision and modelling of biological vision
Funder
Swedish Research Council, 2014-4083Stiftelsen Olle Engkvist Byggmästare, 2015/465
Note

QC 20170308

Available from: 2017-02-24 Created: 2017-02-24 Last updated: 2018-06-19Bibliographically approved

Open Access in DiVA

fulltext(27070 kB)56 downloads
File information
File name FULLTEXT01.pdfFile size 27070 kBChecksum SHA-512
f7485d40e076f859ff7cbd20e3133b88942484416f4e6fa3e0a13b58976ad92f0dc9fd0ed397f6f415515b2fcb84388668d8d4e822e5b23ce17edaf62893292b
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopushttp://ssvm2017.compute.dtu.dk/

Search in DiVA

By author/editor
Lindeberg, Tony
By organisation
Computational Science and Technology (CST)
Computer Vision and Robotics (Autonomous Systems)Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 56 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

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 1123 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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