Adaptive Multiple Component Metric Learning for Robust Visual Tracking

Roland GOECKE, Behzad BOZORGTABAR

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    Abstract

    In this paper, we present a new robust visual tracking approach that incorporates an adaptive metric learning in a multiple components framework. Using a similar overall approach to other state-of-the-art tracking methods, which pose object tracking as a binary classification problem, we firstly employ a new feature selection mechanism based on adaptive metric learning for constructing a discriminative target appearance model and then propose a scheme to update the appearance model in a Multiple Component Learning boosting manner, which automatically learns individual component classifiers and combines these into an overall classifier. Experiments on several challenging benchmark video sequences demonstrate the effectiveness and robustness of our proposed method.
    Original languageEnglish
    Title of host publicationNeural Information Processing - Lecture Notes of Computer Science
    EditorsMinho Lee, Akira Hirose, Zeng-Guang Hou, Rhee Man Kil
    Place of PublicationGermany
    PublisherSpringer
    Pages566-575
    Number of pages10
    Volume8228
    ISBN (Print)9783642420504
    DOIs
    Publication statusPublished - 2013
    Event20th International Conference on Neural Information Processing (ICONIP 2013) - Daegu, Daegu, Korea, Republic of
    Duration: 3 Nov 20137 Nov 2013

    Conference

    Conference20th International Conference on Neural Information Processing (ICONIP 2013)
    Abbreviated titleICONIP 2013
    CountryKorea, Republic of
    CityDaegu
    Period3/11/137/11/13

    Fingerprint

    Classifiers
    Feature extraction
    Experiments

    Cite this

    GOECKE, R., & BOZORGTABAR, B. (2013). Adaptive Multiple Component Metric Learning for Robust Visual Tracking. In M. Lee, A. Hirose, Z-G. Hou, & R. M. Kil (Eds.), Neural Information Processing - Lecture Notes of Computer Science (Vol. 8228, pp. 566-575). Germany: Springer. https://doi.org/10.1007/978-3-642-42051-1_70
    GOECKE, Roland ; BOZORGTABAR, Behzad. / Adaptive Multiple Component Metric Learning for Robust Visual Tracking. Neural Information Processing - Lecture Notes of Computer Science. editor / Minho Lee ; Akira Hirose ; Zeng-Guang Hou ; Rhee Man Kil. Vol. 8228 Germany : Springer, 2013. pp. 566-575
    @inproceedings{03499aa5738a48069f09e2fe0e1135e6,
    title = "Adaptive Multiple Component Metric Learning for Robust Visual Tracking",
    abstract = "In this paper, we present a new robust visual tracking approach that incorporates an adaptive metric learning in a multiple components framework. Using a similar overall approach to other state-of-the-art tracking methods, which pose object tracking as a binary classification problem, we firstly employ a new feature selection mechanism based on adaptive metric learning for constructing a discriminative target appearance model and then propose a scheme to update the appearance model in a Multiple Component Learning boosting manner, which automatically learns individual component classifiers and combines these into an overall classifier. Experiments on several challenging benchmark video sequences demonstrate the effectiveness and robustness of our proposed method.",
    keywords = "Visual tracking, Adaptive metric learning, Multi Component Learning",
    author = "Roland GOECKE and Behzad BOZORGTABAR",
    year = "2013",
    doi = "10.1007/978-3-642-42051-1_70",
    language = "English",
    isbn = "9783642420504",
    volume = "8228",
    pages = "566--575",
    editor = "Minho Lee and Akira Hirose and Zeng-Guang Hou and Kil, {Rhee Man}",
    booktitle = "Neural Information Processing - Lecture Notes of Computer Science",
    publisher = "Springer",
    address = "Netherlands",

    }

    GOECKE, R & BOZORGTABAR, B 2013, Adaptive Multiple Component Metric Learning for Robust Visual Tracking. in M Lee, A Hirose, Z-G Hou & RM Kil (eds), Neural Information Processing - Lecture Notes of Computer Science. vol. 8228, Springer, Germany, pp. 566-575, 20th International Conference on Neural Information Processing (ICONIP 2013), Daegu, Korea, Republic of, 3/11/13. https://doi.org/10.1007/978-3-642-42051-1_70

    Adaptive Multiple Component Metric Learning for Robust Visual Tracking. / GOECKE, Roland; BOZORGTABAR, Behzad.

    Neural Information Processing - Lecture Notes of Computer Science. ed. / Minho Lee; Akira Hirose; Zeng-Guang Hou; Rhee Man Kil. Vol. 8228 Germany : Springer, 2013. p. 566-575.

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    TY - GEN

    T1 - Adaptive Multiple Component Metric Learning for Robust Visual Tracking

    AU - GOECKE, Roland

    AU - BOZORGTABAR, Behzad

    PY - 2013

    Y1 - 2013

    N2 - In this paper, we present a new robust visual tracking approach that incorporates an adaptive metric learning in a multiple components framework. Using a similar overall approach to other state-of-the-art tracking methods, which pose object tracking as a binary classification problem, we firstly employ a new feature selection mechanism based on adaptive metric learning for constructing a discriminative target appearance model and then propose a scheme to update the appearance model in a Multiple Component Learning boosting manner, which automatically learns individual component classifiers and combines these into an overall classifier. Experiments on several challenging benchmark video sequences demonstrate the effectiveness and robustness of our proposed method.

    AB - In this paper, we present a new robust visual tracking approach that incorporates an adaptive metric learning in a multiple components framework. Using a similar overall approach to other state-of-the-art tracking methods, which pose object tracking as a binary classification problem, we firstly employ a new feature selection mechanism based on adaptive metric learning for constructing a discriminative target appearance model and then propose a scheme to update the appearance model in a Multiple Component Learning boosting manner, which automatically learns individual component classifiers and combines these into an overall classifier. Experiments on several challenging benchmark video sequences demonstrate the effectiveness and robustness of our proposed method.

    KW - Visual tracking

    KW - Adaptive metric learning

    KW - Multi Component Learning

    U2 - 10.1007/978-3-642-42051-1_70

    DO - 10.1007/978-3-642-42051-1_70

    M3 - Conference contribution

    SN - 9783642420504

    VL - 8228

    SP - 566

    EP - 575

    BT - Neural Information Processing - Lecture Notes of Computer Science

    A2 - Lee, Minho

    A2 - Hirose, Akira

    A2 - Hou, Zeng-Guang

    A2 - Kil, Rhee Man

    PB - Springer

    CY - Germany

    ER -

    GOECKE R, BOZORGTABAR B. Adaptive Multiple Component Metric Learning for Robust Visual Tracking. In Lee M, Hirose A, Hou Z-G, Kil RM, editors, Neural Information Processing - Lecture Notes of Computer Science. Vol. 8228. Germany: Springer. 2013. p. 566-575 https://doi.org/10.1007/978-3-642-42051-1_70