Integrating prior knowledge and structure from motion

Nicolas Guilbert, Henrik Aanæs, Rasmus Larsen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    37 Downloads (Pure)

    Abstract

    A new approach for formulating prior knowledge in structure form motion is presented, where the structure is viewed as a 3D stochastic variable, hereby priors are more naturally expressed. It is demonstrated that this formulation is efficient for regularizing structure reconstruction via prior knowledge. Specifically algorithms for imposing priors in the proposed formulation are presented.
    Original languageEnglish
    Title of host publicationProceedings of the Scandinavian Image Analysis - SCIA'01
    EditorsIvar Austvoll
    Publication date2001
    Pages477-481
    Publication statusPublished - 2001
    Event12th Scandinavian Conference on Image Analysis - Bergen, Norway
    Duration: 11 Jun 200114 Jun 2001
    Conference number: 12

    Conference

    Conference12th Scandinavian Conference on Image Analysis
    Number12
    Country/TerritoryNorway
    CityBergen
    Period11/06/200114/06/2001

    Fingerprint

    Dive into the research topics of 'Integrating prior knowledge and structure from motion'. Together they form a unique fingerprint.

    Cite this