3D Human Action Recognition

    Research output: ThesisDoctoral Thesis

    920 Downloads (Pure)

    Abstract

    Automatic human action recognition in videos is a significant research problem and has many applications in surveillance, human-computer interaction and video retrieval. Depth cameras have become popular for this problem because depth videos do not suffer from the uncertain attributes induced by variations in illumination and clothing texture. However, the presence of occlusion, sensor noise and most importantly viewpoint variations still make action recognition a challenging task. This thesis proposes algorithms for efficient modelling of depth and RGB videos with particular emphasis on automatic learning of the complex structures of human actions without making prior assumptions about the camera viewpoint.

    Original languageEnglish
    QualificationDoctor of Philosophy
    Awarding Institution
    • The University of Western Australia
    Award date2 Nov 2016
    Publication statusUnpublished - 2016

    Fingerprint

    Cameras
    Human computer interaction
    Textures
    Lighting
    Sensors

    Cite this

    @phdthesis{689f7717597d4cea930ce95ba3ca919e,
    title = "3D Human Action Recognition",
    abstract = "Automatic human action recognition in videos is a significant research problem and has many applications in surveillance, human-computer interaction and video retrieval. Depth cameras have become popular for this problem because depth videos do not suffer from the uncertain attributes induced by variations in illumination and clothing texture. However, the presence of occlusion, sensor noise and most importantly viewpoint variations still make action recognition a challenging task. This thesis proposes algorithms for efficient modelling of depth and RGB videos with particular emphasis on automatic learning of the complex structures of human actions without making prior assumptions about the camera viewpoint.",
    keywords = "Action Recognition, Depth Image, View-Invariant, 3D Human Model, 3D Video, Novel Viewpoint",
    author = "Hossein Rahmani",
    year = "2016",
    language = "English",
    school = "The University of Western Australia",

    }

    Rahmani, H 2016, '3D Human Action Recognition', Doctor of Philosophy, The University of Western Australia.

    3D Human Action Recognition. / Rahmani, Hossein.

    2016.

    Research output: ThesisDoctoral Thesis

    TY - THES

    T1 - 3D Human Action Recognition

    AU - Rahmani, Hossein

    PY - 2016

    Y1 - 2016

    N2 - Automatic human action recognition in videos is a significant research problem and has many applications in surveillance, human-computer interaction and video retrieval. Depth cameras have become popular for this problem because depth videos do not suffer from the uncertain attributes induced by variations in illumination and clothing texture. However, the presence of occlusion, sensor noise and most importantly viewpoint variations still make action recognition a challenging task. This thesis proposes algorithms for efficient modelling of depth and RGB videos with particular emphasis on automatic learning of the complex structures of human actions without making prior assumptions about the camera viewpoint.

    AB - Automatic human action recognition in videos is a significant research problem and has many applications in surveillance, human-computer interaction and video retrieval. Depth cameras have become popular for this problem because depth videos do not suffer from the uncertain attributes induced by variations in illumination and clothing texture. However, the presence of occlusion, sensor noise and most importantly viewpoint variations still make action recognition a challenging task. This thesis proposes algorithms for efficient modelling of depth and RGB videos with particular emphasis on automatic learning of the complex structures of human actions without making prior assumptions about the camera viewpoint.

    KW - Action Recognition

    KW - Depth Image

    KW - View-Invariant

    KW - 3D Human Model

    KW - 3D Video

    KW - Novel Viewpoint

    M3 - Doctoral Thesis

    ER -