A novel 3D vorticity based approach for automatic registration of low resolution range images

    Research output: Contribution to journalArticle

    17 Citations (Scopus)
    194 Downloads (Pure)

    Abstract

    © 2015 Elsevier Ltd. This paper tackles the problem of feature matching and range image registration. Our approach is based on a novel set of discriminating three-dimensional (3D) local features, named 3D-Vor (Vorticity). In contrast to conventional local feature representation techniques, which use the vector field (i.e. surface normals) to just construct their local reference frames, the proposed feature representation exploits the vorticity of the vector field computed at each point of the local surface to capture the distinctive characteristics at each point of the underlying 3D surface. The 3D-Vor descriptors of two range images are then matched using a fully automatic feature matching algorithm which identifies correspondences between the two range images. Correspondences are verified in a local validation step of the proposed algorithm and used for the pairwise registration of the range images. Quantitative results on low resolution Kinect 3D data (Washington RGB-D dataset) show that our proposed automatic registration algorithm is accurate and computationally efficient. The performance evaluation of the proposed descriptor was also carried out on the challenging low resolution Washington RGB-D (Kinect) object dataset, for the tasks of automatic range image registration. Reported experimental results show that the proposed local surface descriptor is robust to resolution, noise and more accurate than state-of-the-art techniques. It achieves 90% registration accuracy compared to 50%, 69.2% and 52% for spin image, 3D SURF and SISI/LD-SIFT descriptors, respectively.
    Original languageEnglish
    Pages (from-to)2859-2871
    JournalPattern Recognition
    Volume48
    Issue number9
    Early online date4 Apr 2015
    DOIs
    Publication statusPublished - Sep 2015

    Fingerprint

    Vorticity
    Image registration

    Cite this

    @article{e0ee925314ab4813936cef8be9592d0b,
    title = "A novel 3D vorticity based approach for automatic registration of low resolution range images",
    abstract = "{\circledC} 2015 Elsevier Ltd. This paper tackles the problem of feature matching and range image registration. Our approach is based on a novel set of discriminating three-dimensional (3D) local features, named 3D-Vor (Vorticity). In contrast to conventional local feature representation techniques, which use the vector field (i.e. surface normals) to just construct their local reference frames, the proposed feature representation exploits the vorticity of the vector field computed at each point of the local surface to capture the distinctive characteristics at each point of the underlying 3D surface. The 3D-Vor descriptors of two range images are then matched using a fully automatic feature matching algorithm which identifies correspondences between the two range images. Correspondences are verified in a local validation step of the proposed algorithm and used for the pairwise registration of the range images. Quantitative results on low resolution Kinect 3D data (Washington RGB-D dataset) show that our proposed automatic registration algorithm is accurate and computationally efficient. The performance evaluation of the proposed descriptor was also carried out on the challenging low resolution Washington RGB-D (Kinect) object dataset, for the tasks of automatic range image registration. Reported experimental results show that the proposed local surface descriptor is robust to resolution, noise and more accurate than state-of-the-art techniques. It achieves 90{\%} registration accuracy compared to 50{\%}, 69.2{\%} and 52{\%} for spin image, 3D SURF and SISI/LD-SIFT descriptors, respectively.",
    author = "S.A.A. Shah and Mohammed Bennamoun and Farid Boussaid",
    year = "2015",
    month = "9",
    doi = "10.1016/j.patcog.2015.03.014",
    language = "English",
    volume = "48",
    pages = "2859--2871",
    journal = "Pattern Recognition",
    issn = "0031-3203",
    publisher = "Elsevier",
    number = "9",

    }

    TY - JOUR

    T1 - A novel 3D vorticity based approach for automatic registration of low resolution range images

    AU - Shah, S.A.A.

    AU - Bennamoun, Mohammed

    AU - Boussaid, Farid

    PY - 2015/9

    Y1 - 2015/9

    N2 - © 2015 Elsevier Ltd. This paper tackles the problem of feature matching and range image registration. Our approach is based on a novel set of discriminating three-dimensional (3D) local features, named 3D-Vor (Vorticity). In contrast to conventional local feature representation techniques, which use the vector field (i.e. surface normals) to just construct their local reference frames, the proposed feature representation exploits the vorticity of the vector field computed at each point of the local surface to capture the distinctive characteristics at each point of the underlying 3D surface. The 3D-Vor descriptors of two range images are then matched using a fully automatic feature matching algorithm which identifies correspondences between the two range images. Correspondences are verified in a local validation step of the proposed algorithm and used for the pairwise registration of the range images. Quantitative results on low resolution Kinect 3D data (Washington RGB-D dataset) show that our proposed automatic registration algorithm is accurate and computationally efficient. The performance evaluation of the proposed descriptor was also carried out on the challenging low resolution Washington RGB-D (Kinect) object dataset, for the tasks of automatic range image registration. Reported experimental results show that the proposed local surface descriptor is robust to resolution, noise and more accurate than state-of-the-art techniques. It achieves 90% registration accuracy compared to 50%, 69.2% and 52% for spin image, 3D SURF and SISI/LD-SIFT descriptors, respectively.

    AB - © 2015 Elsevier Ltd. This paper tackles the problem of feature matching and range image registration. Our approach is based on a novel set of discriminating three-dimensional (3D) local features, named 3D-Vor (Vorticity). In contrast to conventional local feature representation techniques, which use the vector field (i.e. surface normals) to just construct their local reference frames, the proposed feature representation exploits the vorticity of the vector field computed at each point of the local surface to capture the distinctive characteristics at each point of the underlying 3D surface. The 3D-Vor descriptors of two range images are then matched using a fully automatic feature matching algorithm which identifies correspondences between the two range images. Correspondences are verified in a local validation step of the proposed algorithm and used for the pairwise registration of the range images. Quantitative results on low resolution Kinect 3D data (Washington RGB-D dataset) show that our proposed automatic registration algorithm is accurate and computationally efficient. The performance evaluation of the proposed descriptor was also carried out on the challenging low resolution Washington RGB-D (Kinect) object dataset, for the tasks of automatic range image registration. Reported experimental results show that the proposed local surface descriptor is robust to resolution, noise and more accurate than state-of-the-art techniques. It achieves 90% registration accuracy compared to 50%, 69.2% and 52% for spin image, 3D SURF and SISI/LD-SIFT descriptors, respectively.

    U2 - 10.1016/j.patcog.2015.03.014

    DO - 10.1016/j.patcog.2015.03.014

    M3 - Article

    VL - 48

    SP - 2859

    EP - 2871

    JO - Pattern Recognition

    JF - Pattern Recognition

    SN - 0031-3203

    IS - 9

    ER -