Bayesian structure from motion

D. A. Forsyth, S. Ioffe, J. Haddon

Research output: Contribution to conferencePaperpeer-review

Abstract

We formulate structure from motion as a Bayesian inference problem, and use a Markov chain Monte Carlo sampler to sample the posterior on this problem. This results in a method that can identify both small and large tracker errors, and yields reconstructions that are stable in the presence of these errors. Furthermore, the method gives detailed information on the range of ambiguities in structure given a particular dataset, and requires no special geometric formulation to cope with degenerate situations. Motion segmentation is obtained by a layer of discrete variables associating a point with an object. We demonstrate a sampler that successfully samples an approximation to the marginal on this domain, producing a relatively unambiguous segmentation.

Original languageEnglish (US)
Pages660-665
Number of pages6
StatePublished - 1999
Externally publishedYes
EventProceedings of the 1999 7th IEEE International Conference on Computer Vision (ICCV'99) - Kerkyra, Greece
Duration: Sep 20 1999Sep 27 1999

Other

OtherProceedings of the 1999 7th IEEE International Conference on Computer Vision (ICCV'99)
CityKerkyra, Greece
Period9/20/999/27/99

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Bayesian structure from motion'. Together they form a unique fingerprint.

Cite this