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
Real-time scale selection in hybrid multi-scale representations
KTH, Skolan för datavetenskap och kommunikation (CSC), Beräkningsbiologi, CB.ORCID-id: 0000-0002-9081-2170
KTH, Tidigare Institutioner, Numerisk analys och datalogi, NADA.
2003 (engelsk)Inngår i: Proc. Scale-Space’03, Springer Berlin/Heidelberg, 2003, Vol. 2695, s. 148-163Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Local scale information extracted from visual data in a bottom-up manner constitutes an important cue for a large number of visual tasks. This article presents a framework for how the computation of such scale descriptors can be performed in real time on a standard computer.

The proposed scale selection framework is expressed within a novel type of multi-scale representation, referred to as hybrid multi-scale representation, which aims at integrating and providing variable trade-offs between the relative advantages of pyramids and scale-space representation, in terms of computational efficiency and computational accuracy. Starting from binomial scale-space kernels of different widths, we describe a family pyramid representations, in which the regular pyramid concept and the regular scale-space representation constitute limiting cases. In particular, the steepness of the pyramid as well as the sampling density in the scale direction can be varied.

It is shown how the definition of gamma-normalized derivative operators underlying the automatic scale selection mechanism can be transferred from a regular scale-space to a hybrid pyramid, and two alternative definitions are studied in detail, referred to as variance normalization and l(p)-normalization. The computational accuracy of these two schemes is evaluated, and it is shown how the choice of sub-sampling rate provides a trade-off between the computational efficiency and the accuracy of the scale descriptors. Experimental evaluations are presented for both synthetic and real data. In a simplified form, this scale selection mechanism has been running for two years, in a real-time computer vision system.

sted, utgiver, år, opplag, sider
Springer Berlin/Heidelberg, 2003. Vol. 2695, s. 148-163
Serie
Lecture Notes in Computer Science, ISSN 0302-9743 ; 2695
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-40242DOI: 10.1007/3-540-44935-3_11ISI: 000185043200011ISBN: 3-540-40368-X (tryckt)OAI: oai:DiVA.org:kth-40242DiVA, id: diva2:440700
Konferanse
4th International Conference on Scale Space Methods in Computer Vision Location: ISLE SKYE, SCOTLAND Date: JUN 10-12, 2003
Merknad

QC 20110913

Tilgjengelig fra: 2013-04-19 Laget: 2011-09-13 Sist oppdatert: 2018-01-12bibliografisk kontrollert

Open Access i DiVA

fulltext(214 kB)1212 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 214 kBChecksum SHA-512
eec6216c40661a08da57333fb59927e1f54839f781c7c3f13cd937b3d1fd8bef06fb19c04ad6bd1f37aca14c20a578ea7fd30506318f8597bc1225fc6a1aaf2a
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstAt authors' home pageThe final publication is available at www.springerlink.com

Personposter BETA

Lindeberg, Tony

Søk i DiVA

Av forfatter/redaktør
Lindeberg, TonyBretzner, Lars
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 1212 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: 478 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