How to put probabilities on homographies

Evgeni Begelfor*, Michael Werman

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

32 Scopus citations

Abstract

We present a family of "normal" distributions over a matrix group together with a simple method for estimating its parameters. In particular, the mean of a set of elements can be calculated. The approach is applied to planar projective homographies, showing that using priors defined in this way improves object recognition.

Original languageAmerican English
Pages (from-to)1666-1670
Number of pages5
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume27
Issue number10
DOIs
StatePublished - Oct 2005

Keywords

  • Bayesian statistics
  • Geodesics
  • Homography
  • Lie groups
  • Normal distribution

Fingerprint

Dive into the research topics of 'How to put probabilities on homographies'. Together they form a unique fingerprint.

Cite this