Better features to track by estimating the tracking convergence region

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    45 Downloads (Pure)

    Abstract

    Reliably tracking key points and textured patches from frame to frame is the basic requirement for many bottomup computer vision algorithms. The problem of selecting the features that can be tracked well is addressed here. The Lucas-Kanade tracking procedure is commonly used. We propose a method to estimate the size of the tracking procedure convergence region for each feature. The features that have a wider convergence region around them should be tracked better by the tracker. The size of the convergence region as a new feature goodness measure is compared with the widely accepted Shi-Tomasi feature selection criteria.
    Original languageEnglish
    Title of host publicationProceedings of the Eighth Annual Conference of the Advanced School for Computing and imaging, ASCI 2002
    EditorsE.F. Deprettere, A. Belloum, J.W.J. Heijnsdijk, F. van der Stappen
    Place of PublicationDelft, The Netherlands
    PublisherAdvanced School for Computing and Imaging (ASCI)
    Pages284-287
    Number of pages4
    ISBN (Print)90-803086-7-6
    Publication statusPublished - 19 Jun 2002
    EventEighth Annual Conference of the Advanced School for Computing and imaging, ASCI 2002 - Lochem
    Duration: 19 Jun 200221 Jun 2002

    Conference

    ConferenceEighth Annual Conference of the Advanced School for Computing and imaging, ASCI 2002
    CityLochem
    Period19/06/0221/06/02

    Fingerprint Dive into the research topics of 'Better features to track by estimating the tracking convergence region'. Together they form a unique fingerprint.

  • Cite this

    Zivkovic, Z., & van der Heijden, F. (2002). Better features to track by estimating the tracking convergence region. In E. F. Deprettere, A. Belloum, J. W. J. Heijnsdijk, & F. van der Stappen (Eds.), Proceedings of the Eighth Annual Conference of the Advanced School for Computing and imaging, ASCI 2002 (pp. 284-287). Delft, The Netherlands: Advanced School for Computing and Imaging (ASCI).