View-based adaptive affine tracking

Fernando de la Torre (Lead / Corresponding author), Shaogang Gong (Lead / Corresponding author), Stephen McKenna (Lead / Corresponding author)

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

    14 Citations (Scopus)

    Abstract

    We propose a model for view-based adaptive affine tracking of moving objects. We avoid the need for feature-based matching in establishing correspondences through learning landmarks. We use an effective bootstrapping process based on colour segmentation and selective attention. We recover affine parameters with dynamic updates to the eigenspace using most recent history and perform predictions in parameter space. Experimental results are given to illustrate our approach.
    Original languageEnglish
    Title of host publicationComputer Vision — ECCV'98
    Subtitle of host publication5th European Conference on Computer Vision Freiburg, Germany, June, 2–6, 1998 Proceedings
    EditorsHans Burkhardt, Bernd Neumann
    Place of PublicationBerlin
    PublisherSpringer
    Pages828-842
    Number of pages15
    Volume1
    ISBN (Electronic)9783540693543
    ISBN (Print)9783540645696
    DOIs
    Publication statusPublished - 1998
    Event5th European Conference on Computer Vision - Freiburg, Germany
    Duration: 2 Jun 19986 Jun 1998

    Publication series

    NameLecture notes in computer science
    PublisherSpringer
    Volume1406
    ISSN (Print)0302-9743

    Conference

    Conference5th European Conference on Computer Vision
    Abbreviated titleECCV'98
    CountryGermany
    CityFreiburg
    Period2/06/986/06/98

      Fingerprint

    Cite this

    de la Torre, F., Gong, S., & McKenna, S. (1998). View-based adaptive affine tracking. In H. Burkhardt, & B. Neumann (Eds.), Computer Vision — ECCV'98: 5th European Conference on Computer Vision Freiburg, Germany, June, 2–6, 1998 Proceedings (Vol. 1, pp. 828-842). (Lecture notes in computer science; Vol. 1406). Springer . https://doi.org/10.1007/BFb0055707