Estimation of Motion Vector Fields

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearch

    353 Downloads (Pure)

    Abstract

    This paper presents an approach to the estimation of 2-D motion vector fields from time varying image sequences. We use a piecewise smooth model based on coupled vector/binary Markov random fields. We find the maximum a posteriori solution by simulated annealing. The algorithm generate sample fields by means of stochastic relaxation implemented via the Gibbs sampler.
    Original languageEnglish
    Title of host publicationProceedings of the 2nd Danish Conference on Pattern Recognition and Image Analysis (DANKOMB, DSAGM yearly meeting), Aug. 25-26
    EditorsPeter Johansen
    PublisherDepartment of Computer Science, University of Copenhagen (DIKU)
    Publication date1993
    Pages37-42
    Publication statusPublished - 1993
    EventProceedings of the 2nd Danish Conference on Pattern Recognition and Image Analysis (DANKOMB, DSAGM yearly meeting), Aug. 25-26 -
    Duration: 1 Jan 1993 → …

    Conference

    ConferenceProceedings of the 2nd Danish Conference on Pattern Recognition and Image Analysis (DANKOMB, DSAGM yearly meeting), Aug. 25-26
    Period01/01/1993 → …

    Keywords

    • Markov random fields
    • optical flow

    Fingerprint Dive into the research topics of 'Estimation of Motion Vector Fields'. Together they form a unique fingerprint.

    Cite this