Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Distances and Means of Direct Similarities
Toshiba Research Europe Ltd..
Toshiba Research Europe Ltd..
Toshiba Research Europe Ltd..
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.ORCID-id: 0000-0002-4266-6746
Visa övriga samt affilieringar
2014 (Engelska)Ingår i: International Journal of Computer Vision, ISSN 0920-5691, E-ISSN 1573-1405, Vol. 112, nr 3, s. 285-306Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

The non-Euclidean nature of direct isometries in a Euclidean space, i.e. transformations consisting of a rotation and a translation, creates difficulties when computing distances, means and distributions over them, which have been well studied in the literature. Direct similarities, transformations consisting of a direct isometry and a positive uniform scaling, present even more of a challenge—one which we demonstrate and address here. In this article, we investigate divergences (a superset of distances without constraints on symmetry and sub-additivity) for comparing direct similarities, and means induced by them via minimizing a sum of squared divergences. We analyze several standard divergences: the Euclidean distance using the matrix representation of direct similarities, a divergence from Lie group theory, and the family of all left-invariant distances derived from Riemannian geometry. We derive their properties and those of their induced means, highlighting several shortcomings. In addition, we introduce a novel family of left-invariant divergences, called SRT divergences, which resolve several issues associated with the standard divergences. In our evaluation we empirically demonstrate the derived properties of the divergences and means, both qualitatively and quantitatively, on synthetic data. Finally, we compare the divergences in a real-world application: vote-based, scale-invariant object recognition. Our results show that the new divergences presented here, and their means, are both more effective and faster to compute for this task.

Ort, förlag, år, upplaga, sidor
Springer-Verlag New York, 2014. Vol. 112, nr 3, s. 285-306
Nyckelord [en]
Direct similarity, Distance, Mean, Object recognition, Registration
Nationell ämneskategori
Datorseende och robotik (autonoma system)
Identifikatorer
URN: urn:nbn:se:kth:diva-158118DOI: 10.1007/s11263-014-0762-0ISI: 000353159600002OAI: oai:DiVA.org:kth-158118DiVA, id: diva2:774379
Anmärkning

QC 20150507

Tillgänglig från: 2014-12-22 Skapad: 2014-12-22 Senast uppdaterad: 2018-01-11Bibliografiskt granskad

Open Access i DiVA

fulltext(1303 kB)147 nedladdningar
Filinformation
Filnamn FULLTEXT02.pdfFilstorlek 1303 kBChecksumma SHA-512
5b1b88f60878d30e81e0fa7006b1f88543487fcf6b496c23ba555393044718aacf0b0754ccd4258e25cb24c3c27dae24d9d88067029cd0ab6aafe89b8d3f6dca
Typ fulltextMimetyp application/pdf

Övriga länkar

Förlagets fulltextThe final publication is available at www.springerlink.com

Personposter BETA

Maki, Atsuto

Sök vidare i DiVA

Av författaren/redaktören
Maki, Atsuto
Av organisationen
Datorseende och robotik, CVAP
I samma tidskrift
International Journal of Computer Vision
Datorseende och robotik (autonoma system)

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 147 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 150 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf