A novel local surface feature for 3D object recognition under clutter and occlusion

    Research output: Contribution to journalArticle

    57 Citations (Scopus)
    339 Downloads (Pure)

    Abstract

    © 2014 Elsevier Inc. All rights reserved. This paper presents a highly distinctive local surface feature called the TriSI feature for recognizing 3D objects in the presence of clutter and occlusion. For a feature point, we first construct a unique and repeatable Local Reference Frame (LRF) using the implicit geometrical information of neighboring triangular faces. We then generate three signatures from the three orthogonal coordinate axes of the LRF. These signatures are concatenated and then compressed into a TriSI feature. Finally, we propose an effective 3D object recognition algorithm based on hierarchical feature matching. We tested our TriSI feature on two popular datasets. Rigorous experimental results show that the TriSI feature was highly descriptive and outperformed existing algorithms under all levels of Gaussian noise, Laplacian noise, shot noise, varying mesh resolutions, occlusion, and clutter. Moreover, we tested our TriSI-based 3D object recognition algorithm on four standard datasets. The experimental results show that our algorithm achieved the best overall recognition results on these datasets.
    Original languageEnglish
    Pages (from-to)196-213
    JournalInformation Sciences
    Volume293
    DOIs
    Publication statusPublished - 1 Feb 2015

    Fingerprint

    3D Object Recognition
    Object recognition
    Clutter
    Occlusion
    Recognition Algorithm
    Signature
    Co-ordinate axis
    Feature Matching
    Shot Noise
    Feature Point
    Gaussian Noise
    Experimental Results
    Shot noise
    Triangular
    Mesh
    Face
    Frame of reference

    Cite this

    @article{bd6516a2fb3e4c9caf873a0fbe81190e,
    title = "A novel local surface feature for 3D object recognition under clutter and occlusion",
    abstract = "{\circledC} 2014 Elsevier Inc. All rights reserved. This paper presents a highly distinctive local surface feature called the TriSI feature for recognizing 3D objects in the presence of clutter and occlusion. For a feature point, we first construct a unique and repeatable Local Reference Frame (LRF) using the implicit geometrical information of neighboring triangular faces. We then generate three signatures from the three orthogonal coordinate axes of the LRF. These signatures are concatenated and then compressed into a TriSI feature. Finally, we propose an effective 3D object recognition algorithm based on hierarchical feature matching. We tested our TriSI feature on two popular datasets. Rigorous experimental results show that the TriSI feature was highly descriptive and outperformed existing algorithms under all levels of Gaussian noise, Laplacian noise, shot noise, varying mesh resolutions, occlusion, and clutter. Moreover, we tested our TriSI-based 3D object recognition algorithm on four standard datasets. The experimental results show that our algorithm achieved the best overall recognition results on these datasets.",
    author = "Yulan Guo and Ferdous Sohel and Mohammed Bennamoun and J. Wan and M. Lu",
    year = "2015",
    month = "2",
    day = "1",
    doi = "10.1016/j.ins.2014.09.015",
    language = "English",
    volume = "293",
    pages = "196--213",
    journal = "Information Sciences",
    issn = "0020-0255",
    publisher = "Elsevier",

    }

    A novel local surface feature for 3D object recognition under clutter and occlusion. / Guo, Yulan; Sohel, Ferdous; Bennamoun, Mohammed; Wan, J.; Lu, M.

    In: Information Sciences, Vol. 293, 01.02.2015, p. 196-213.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - A novel local surface feature for 3D object recognition under clutter and occlusion

    AU - Guo, Yulan

    AU - Sohel, Ferdous

    AU - Bennamoun, Mohammed

    AU - Wan, J.

    AU - Lu, M.

    PY - 2015/2/1

    Y1 - 2015/2/1

    N2 - © 2014 Elsevier Inc. All rights reserved. This paper presents a highly distinctive local surface feature called the TriSI feature for recognizing 3D objects in the presence of clutter and occlusion. For a feature point, we first construct a unique and repeatable Local Reference Frame (LRF) using the implicit geometrical information of neighboring triangular faces. We then generate three signatures from the three orthogonal coordinate axes of the LRF. These signatures are concatenated and then compressed into a TriSI feature. Finally, we propose an effective 3D object recognition algorithm based on hierarchical feature matching. We tested our TriSI feature on two popular datasets. Rigorous experimental results show that the TriSI feature was highly descriptive and outperformed existing algorithms under all levels of Gaussian noise, Laplacian noise, shot noise, varying mesh resolutions, occlusion, and clutter. Moreover, we tested our TriSI-based 3D object recognition algorithm on four standard datasets. The experimental results show that our algorithm achieved the best overall recognition results on these datasets.

    AB - © 2014 Elsevier Inc. All rights reserved. This paper presents a highly distinctive local surface feature called the TriSI feature for recognizing 3D objects in the presence of clutter and occlusion. For a feature point, we first construct a unique and repeatable Local Reference Frame (LRF) using the implicit geometrical information of neighboring triangular faces. We then generate three signatures from the three orthogonal coordinate axes of the LRF. These signatures are concatenated and then compressed into a TriSI feature. Finally, we propose an effective 3D object recognition algorithm based on hierarchical feature matching. We tested our TriSI feature on two popular datasets. Rigorous experimental results show that the TriSI feature was highly descriptive and outperformed existing algorithms under all levels of Gaussian noise, Laplacian noise, shot noise, varying mesh resolutions, occlusion, and clutter. Moreover, we tested our TriSI-based 3D object recognition algorithm on four standard datasets. The experimental results show that our algorithm achieved the best overall recognition results on these datasets.

    U2 - 10.1016/j.ins.2014.09.015

    DO - 10.1016/j.ins.2014.09.015

    M3 - Article

    VL - 293

    SP - 196

    EP - 213

    JO - Information Sciences

    JF - Information Sciences

    SN - 0020-0255

    ER -