View Item 
        •   Utrecht University Student Theses Repository Home
        • UU Theses Repository
        • Theses
        • View Item
        •   Utrecht University Student Theses Repository Home
        • UU Theses Repository
        • Theses
        • View Item
        JavaScript is disabled for your browser. Some features of this site may not work without it.

        Browse

        All of UU Student Theses RepositoryBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

        Detecting missing frames in videos

        Thumbnail
        View/Open
        3344959-MarcVaarties-thesis.pdf (8.478Mb)
        Publication date
        2014
        Author
        Vaarties, M.R.
        Metadata
        Show full item record
        Summary
        Although there are many video completion algorithms, ranging from object removal to reconstructing missing frames, little work has been done in the field of automatically detecting missing frames to begin with. This means manual work, thus we seek to propose a method that detects the locations of missing frames automatically. Our proposed method is based on the Edge Change Ratio algorithm, which was originally developed to detect scene breaks. We look at a number of factors and how they influence the algorithm, and adapt it to our needs. Results indicate that our method works fairly well, and with some more work, can automatically and reliably detect missing frames regardless of resolution, framerate, or the actual content of the video.
        URI
        https://studenttheses.uu.nl/handle/20.500.12932/17613
        Collections
        • Theses
        Utrecht university logo