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

        Monitoring Interactions

        Thumbnail
        View/Open
        MonitoringInteractions.pdf (4.223Mb)
        Publication date
        2016
        Author
        Meißner, F.N.
        Metadata
        Show full item record
        Summary
        This work proposes a human interaction recognition based approach to video indexing that represents a video by showing when and with whom was interacted throughout the video. In order to visualize the length of an interaction, it is required to recognize individuals that have been detected in earlier parts of the video. To solve this problem, an approach to photo-clustering is extended to video material by tracking detected faces and using the information from tracking to improve the recognition of human beings. The results of the tracking based approach show a considerable decrease of false cluster assignments compared to the original method. Further, it is demonstrated that the proposed method is able to correctly recognize the appearance of five out of the six individuals correctly.
        URI
        https://studenttheses.uu.nl/handle/20.500.12932/22175
        Collections
        • Theses
        Utrecht university logo