BIROn - Birkbeck Institutional Research Online

    Dual L1-normalized context aware tensor power iteration and its applications to multi-object tracking and multi-graph matching

    Hu, W. and Shi, X. and Zhou, Z. and Xing, J. and Ling, H. and Maybank, Stephen J. (2020) Dual L1-normalized context aware tensor power iteration and its applications to multi-object tracking and multi-graph matching. International Journal of Computer Vision 128 , pp. 360-392. ISSN 0920-5691.

    [img] Text
    Dual L1 Normalized.pdf - Author's Accepted Manuscript
    Restricted to Repository staff only

    Download (2MB) | Request a copy
    29559.pdf - Published Version of Record
    Available under License Creative Commons Attribution.

    Download (6MB) | Preview


    The multi-dimensional assignment problem is universal for data association analysis such as data association-based visual multi-object tracking and multi-graph matching. In this paper, multi-dimensional assignment is formulated as a rank-1 tensor approximation problem. A dual 1-normalized context/hyper-context aware tensor power iteration optimization method is proposed. The method is applied to multi-object tracking and multi-graph matching. In the optimization method, tensor power iteration with the dual unit norm enables the capture of information across multiple sample sets. Interactions between sample associations are modeled as contexts or hyper-contexts which are combined with the global affinity into a unified optimization. The optimization is flexible for accommodating various types of contextual models. In multi-object tracking, the global affinity is defined according to the appearance similarity between objects detected in different frames. Interactions between objects are modeled as motion contexts which are encoded into the global association optimization. The tracking method integrates high order motion information and high order appearance variation. The multi-graph matching method carries out matching over graph vertices and structure matching over graph edges simultaneously. The matching consistency across multi-graphs is based on the high-order tensor optimization. Various types of vertext affinites and edge/hyper-edge affinities are flexibly integrated. Experiments on several public datasets, such as the MOT16 challenge benchmark, validate the effectiveness of the proposed methods.


    Item Type: Article
    Keyword(s) / Subject(s): Multi-dimensional assignment, Context/hyper-context aware tensor power iteration, multi-object tracking, Multi-graph matching
    School: Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences
    Depositing User: Stephen Maybank
    Date Deposited: 21 Oct 2019 13:29
    Last Modified: 09 Aug 2023 12:47


    Activity Overview
    6 month trend
    6 month trend

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item