An accurate and robust range image registration algorithm for 3D object modeling

    Research output: Contribution to journalArticle

    79 Citations (Scopus)

    Abstract

    Range image registration is a fundamental research topic for 3D object modeling and recognition. In this paper, we propose an accurate and robust algorithm for pairwise and multi-view range image registration. We first extract a set of Rotational Projection Statistics (RoPS) features from a pair of range images, and perform feature matching between them. The two range images are then registered using a transformation estimation method and a variant of the Iterative Closest Point (ICP) algorithm. Based on the pairwise registration algorithm, we propose a shape growing based multi-view registration algorithm. The seed shape is initialized with a selected range image and then sequentially updated by performing pairwise registration between itself and the input range images. All input range images are iteratively registered during the shape growing process. Extensive experiments were conducted to test the performance of our algorithm. The proposed pairwise registration algorithm is accurate, and robust to small overlaps, noise and varying mesh resolutions. The proposed multi-view registration algorithm is also very accurate. Rigorous comparisons with the state-of-the-art show the superiority of our algorithm. © 1999-2012 IEEE.
    Original languageEnglish
    Pages (from-to)1377-1390
    JournalIEEE Transactions on Multimedia
    Volume16
    Issue number5
    DOIs
    Publication statusPublished - Aug 2014

    Fingerprint

    Image registration
    Seed
    Statistics

    Cite this

    @article{1060b2ede08d4904a9a8db82f2bfbeaa,
    title = "An accurate and robust range image registration algorithm for 3D object modeling",
    abstract = "Range image registration is a fundamental research topic for 3D object modeling and recognition. In this paper, we propose an accurate and robust algorithm for pairwise and multi-view range image registration. We first extract a set of Rotational Projection Statistics (RoPS) features from a pair of range images, and perform feature matching between them. The two range images are then registered using a transformation estimation method and a variant of the Iterative Closest Point (ICP) algorithm. Based on the pairwise registration algorithm, we propose a shape growing based multi-view registration algorithm. The seed shape is initialized with a selected range image and then sequentially updated by performing pairwise registration between itself and the input range images. All input range images are iteratively registered during the shape growing process. Extensive experiments were conducted to test the performance of our algorithm. The proposed pairwise registration algorithm is accurate, and robust to small overlaps, noise and varying mesh resolutions. The proposed multi-view registration algorithm is also very accurate. Rigorous comparisons with the state-of-the-art show the superiority of our algorithm. {\circledC} 1999-2012 IEEE.",
    author = "Yulan Guo and Ferdous Sohel and Mohammed Bennamoun and J. Wan and M. Lu",
    year = "2014",
    month = "8",
    doi = "10.1109/TMM.2014.2316145",
    language = "English",
    volume = "16",
    pages = "1377--1390",
    journal = "IEEE Transactions on Multimedia",
    issn = "1520-9210",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    number = "5",

    }

    An accurate and robust range image registration algorithm for 3D object modeling. / Guo, Yulan; Sohel, Ferdous; Bennamoun, Mohammed; Wan, J.; Lu, M.

    In: IEEE Transactions on Multimedia, Vol. 16, No. 5, 08.2014, p. 1377-1390.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - An accurate and robust range image registration algorithm for 3D object modeling

    AU - Guo, Yulan

    AU - Sohel, Ferdous

    AU - Bennamoun, Mohammed

    AU - Wan, J.

    AU - Lu, M.

    PY - 2014/8

    Y1 - 2014/8

    N2 - Range image registration is a fundamental research topic for 3D object modeling and recognition. In this paper, we propose an accurate and robust algorithm for pairwise and multi-view range image registration. We first extract a set of Rotational Projection Statistics (RoPS) features from a pair of range images, and perform feature matching between them. The two range images are then registered using a transformation estimation method and a variant of the Iterative Closest Point (ICP) algorithm. Based on the pairwise registration algorithm, we propose a shape growing based multi-view registration algorithm. The seed shape is initialized with a selected range image and then sequentially updated by performing pairwise registration between itself and the input range images. All input range images are iteratively registered during the shape growing process. Extensive experiments were conducted to test the performance of our algorithm. The proposed pairwise registration algorithm is accurate, and robust to small overlaps, noise and varying mesh resolutions. The proposed multi-view registration algorithm is also very accurate. Rigorous comparisons with the state-of-the-art show the superiority of our algorithm. © 1999-2012 IEEE.

    AB - Range image registration is a fundamental research topic for 3D object modeling and recognition. In this paper, we propose an accurate and robust algorithm for pairwise and multi-view range image registration. We first extract a set of Rotational Projection Statistics (RoPS) features from a pair of range images, and perform feature matching between them. The two range images are then registered using a transformation estimation method and a variant of the Iterative Closest Point (ICP) algorithm. Based on the pairwise registration algorithm, we propose a shape growing based multi-view registration algorithm. The seed shape is initialized with a selected range image and then sequentially updated by performing pairwise registration between itself and the input range images. All input range images are iteratively registered during the shape growing process. Extensive experiments were conducted to test the performance of our algorithm. The proposed pairwise registration algorithm is accurate, and robust to small overlaps, noise and varying mesh resolutions. The proposed multi-view registration algorithm is also very accurate. Rigorous comparisons with the state-of-the-art show the superiority of our algorithm. © 1999-2012 IEEE.

    U2 - 10.1109/TMM.2014.2316145

    DO - 10.1109/TMM.2014.2316145

    M3 - Article

    VL - 16

    SP - 1377

    EP - 1390

    JO - IEEE Transactions on Multimedia

    JF - IEEE Transactions on Multimedia

    SN - 1520-9210

    IS - 5

    ER -