Tracking with active contours using dynamically updated shape information

J. Chiverton, X. Xie, M. Mirmehdi

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    125 Downloads (Pure)

    Abstract

    An active contour based tracking framework is described that generates and integrates dynamic shape information without having to learn a priori shape constraints. This dynamic shape information is combined with dynamic photometric foreground model matching and background mismatching. Boundary based optical flow is also used to estimate the location of the object in each new frame, incorporating Procrustes shape alignment. Promising results under complex deformations of shape, varied levels of noise, and close-to-complete occlusion in complex textured backgrounds are presented.
    Original languageEnglish
    Title of host publicationProceedings of the British Machine Vision Conference 2008 (Leeds, September 2008)
    EditorsMark Everingham, Chris James Needham, Roberto Fraile
    PublisherBritish Machine Vision Association
    Pages1-10
    ISBN (Print)9781901725360
    Publication statusPublished - 2008

    Fingerprint

    Dive into the research topics of 'Tracking with active contours using dynamically updated shape information'. Together they form a unique fingerprint.

    Cite this