• DocumentCode
    1451310
  • Title

    Empirical Bayesian motion segmentation

  • Author

    Vasconcelos, Nuno ; Lippman, Andrew

  • Author_Institution
    Compaq Comput. Corp., Cambridge, MA, USA
  • Volume
    23
  • Issue
    2
  • fYear
    2001
  • fDate
    2/1/2001 12:00:00 AM
  • Firstpage
    217
  • Lastpage
    221
  • Abstract
    We introduce an empirical Bayesian procedure for the simultaneous segmentation of an observed motion field and estimation of the hyperparameters of a Markov random field prior. The new approach exhibits the Bayesian appeal of incorporating prior beliefs, but requires only a qualitative description of the prior, avoiding the requirement for a quantitative specification of its parameters. This eliminates the need for trial-and-error strategies for the determination of these parameters and leads to better segmentations
  • Keywords
    Bayes methods; Markov processes; image motion analysis; image segmentation; parameter estimation; Markov random field prior; empirical Bayesian motion segmentation; hyperparameter estimation; observed motion field; parameter estimation; prior beliefs; Bayesian methods; Computer vision; Image segmentation; Layout; Markov random fields; Motion estimation; Motion segmentation; Random variables; Shape control; Statistical learning;
  • fLanguage
    English
  • Journal_Title
    Pattern Analysis and Machine Intelligence, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0162-8828
  • Type

    jour

  • DOI
    10.1109/34.908972
  • Filename
    908972