Research

An anchor patch based optimisation framework for reducing optical flow drift in long image sequences


Reference:

Li, W., Cosker, D. and Brown, M., 2013. An anchor patch based optimisation framework for reducing optical flow drift in long image sequences. In: Lee, K. M., Matsushita, Y., Rehg, J. M. and Hu, Z., eds. 11th Asian Conference on Computer Vision (ACCV), 2012-11-07. Berlin: Springer, pp. 112-125. (Lecture Notes in Computer Science; 7726)

Related documents:

[img]
Preview
PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (6MB) | Preview

    Official URL:

    http://www.accv2012.org/

    Related URLs:

    Abstract

    Tracking through long image sequences is a fundamental research issue in computer vision. This task relies on estimating correspondences between image pairs over time where error accumulation in tracking can result in drift. In this paper, we propose an optimization framework that utilises a novel Anchor Patch algorithm which significantly reduces overall tracking errors given long sequences containing highly deformable objects. The framework may be applied to any tracking algorithm that calculates dense correspondences between images, e.g. optical flow. We demonstrate the success of our approach by showing significant tracking error reduction using 6 existing optical flow algorithms applied to a range of benchmark ground truth sequences. We also provide quantitative analysis of our approach given synthetic occlusions and image noise.

    Details

    Item Type Conference or Workshop Items (UNSPECIFIED)
    CreatorsLi, W., Cosker, D. and Brown, M.
    EditorsLee, K. M., Matsushita, Y., Rehg, J. M. and Hu, Z.
    Related URLs
    URLURL Type
    http://www.scopus.com/inward/record.url?scp=84875878089&partnerID=8YFLogxKUNSPECIFIED
    DepartmentsFaculty of Science > Computer Science
    Research CentresMedia Technology Research Centre
    Publisher StatementanchorPatch_final_v2.pdf: The final publication is available at link.springer.com
    StatusPublished
    ID Code32333

    Export

    Actions (login required)

    View Item

    Document Downloads

    More statistics for this item...