SwePub
Sök i LIBRIS databas

  Utökad sökning

WFRF:(Maki M)
 

Sökning: WFRF:(Maki M) > Distances and Means...

Distances and Means of Direct Similarities

Pham, M.-T. (författare)
Toshiba Research Europe Ltd.
Woodford, O. J. (författare)
Toshiba Research Europe Ltd.
Perbet, F. (författare)
Toshiba Research Europe Ltd.
visa fler...
Maki, Atsuto (författare)
KTH,Datorseende och robotik, CVAP
Gherardi, R. (författare)
Toshiba Research Europe Ltd.
Stenger, B. (författare)
Toshiba Research Europe Ltd.
Cipolla, R. (författare)
University of Cambridge
visa färre...
Toshiba Research Europe Ltd Datorseende och robotik, CVAP (creator_code:org_t)
2014-09-20
2014
Engelska.
Ingår i: International Journal of Computer Vision. - : Springer-Verlag New York. - 0920-5691 .- 1573-1405. ; 112:3, s. 285-306
Relaterad länk:
http://link.springer...
visa fler...
https://kth.diva-por... (primary) (Raw object)
http://kth.diva-port...
https://urn.kb.se/re...
https://doi.org/10.1...
visa färre...
  • Tidskriftsartikel (refereegranskat)
Abstract Ämnesord
Stäng  
  • 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.

Ämnesord

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)

Nyckelord

Direct similarity
Distance
Mean
Object recognition
Registration

Publikations- och innehållstyp

ref (ämneskategori)
art (ämneskategori)

Hitta via bibliotek

Till lärosätets databas

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy