A Comprehensive Performance Evaluation of 3D Local Feature Descriptors

Yulan Guo, Mohammed Bennamoun, Ferdous Sohel, M. Lu, J. Wan, N.M. Kwok

    Research output: Contribution to journalArticle

    168 Citations (Scopus)
    11 Downloads (Pure)

    Abstract

    © 2015, Springer Science+Business Media New York. A number of 3D local feature descriptors have been proposed in the literature. It is however, unclear which descriptors are more appropriate for a particular application. A good descriptor should be descriptive, compact, and robust to a set of nuisances. This paper compares ten popular local feature descriptors in the contexts of 3D object recognition, 3D shape retrieval, and 3D modeling. We first evaluate the descriptiveness of these descriptors on eight popular datasets which were acquired using different techniques. We then analyze their compactness using the recall of feature matching per each float value in the descriptor. We also test the robustness of the selected descriptors with respect to support radius variations, Gaussian noise, shot noise, varying mesh resolution, distance to the mesh boundary, keypoint localization error, occlusion, clutter, and dataset size. Moreover, we present the performance results of these descriptors when combined with different 3D keypoint detection methods. We finally analyze the computational efficiency for generating each descriptor.
    Original languageEnglish
    Pages (from-to)66-89
    JournalInternational Journal of Computer Vision
    Volume116
    Issue number1
    Early online date16 Apr 2015
    DOIs
    Publication statusPublished - Jan 2016

    Fingerprint

    Shot noise
    Object recognition
    Computational efficiency
    Industry

    Cite this

    @article{9bdef8b284a54fcca89053010d3dab03,
    title = "A Comprehensive Performance Evaluation of 3D Local Feature Descriptors",
    abstract = "{\circledC} 2015, Springer Science+Business Media New York. A number of 3D local feature descriptors have been proposed in the literature. It is however, unclear which descriptors are more appropriate for a particular application. A good descriptor should be descriptive, compact, and robust to a set of nuisances. This paper compares ten popular local feature descriptors in the contexts of 3D object recognition, 3D shape retrieval, and 3D modeling. We first evaluate the descriptiveness of these descriptors on eight popular datasets which were acquired using different techniques. We then analyze their compactness using the recall of feature matching per each float value in the descriptor. We also test the robustness of the selected descriptors with respect to support radius variations, Gaussian noise, shot noise, varying mesh resolution, distance to the mesh boundary, keypoint localization error, occlusion, clutter, and dataset size. Moreover, we present the performance results of these descriptors when combined with different 3D keypoint detection methods. We finally analyze the computational efficiency for generating each descriptor.",
    author = "Yulan Guo and Mohammed Bennamoun and Ferdous Sohel and M. Lu and J. Wan and N.M. Kwok",
    year = "2016",
    month = "1",
    doi = "10.1007/s11263-015-0824-y",
    language = "English",
    volume = "116",
    pages = "66--89",
    journal = "International Journal of Computer Vision",
    issn = "0920-5691",
    publisher = "Springer",
    number = "1",

    }

    A Comprehensive Performance Evaluation of 3D Local Feature Descriptors. / Guo, Yulan; Bennamoun, Mohammed; Sohel, Ferdous; Lu, M.; Wan, J.; Kwok, N.M.

    In: International Journal of Computer Vision, Vol. 116, No. 1, 01.2016, p. 66-89.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - A Comprehensive Performance Evaluation of 3D Local Feature Descriptors

    AU - Guo, Yulan

    AU - Bennamoun, Mohammed

    AU - Sohel, Ferdous

    AU - Lu, M.

    AU - Wan, J.

    AU - Kwok, N.M.

    PY - 2016/1

    Y1 - 2016/1

    N2 - © 2015, Springer Science+Business Media New York. A number of 3D local feature descriptors have been proposed in the literature. It is however, unclear which descriptors are more appropriate for a particular application. A good descriptor should be descriptive, compact, and robust to a set of nuisances. This paper compares ten popular local feature descriptors in the contexts of 3D object recognition, 3D shape retrieval, and 3D modeling. We first evaluate the descriptiveness of these descriptors on eight popular datasets which were acquired using different techniques. We then analyze their compactness using the recall of feature matching per each float value in the descriptor. We also test the robustness of the selected descriptors with respect to support radius variations, Gaussian noise, shot noise, varying mesh resolution, distance to the mesh boundary, keypoint localization error, occlusion, clutter, and dataset size. Moreover, we present the performance results of these descriptors when combined with different 3D keypoint detection methods. We finally analyze the computational efficiency for generating each descriptor.

    AB - © 2015, Springer Science+Business Media New York. A number of 3D local feature descriptors have been proposed in the literature. It is however, unclear which descriptors are more appropriate for a particular application. A good descriptor should be descriptive, compact, and robust to a set of nuisances. This paper compares ten popular local feature descriptors in the contexts of 3D object recognition, 3D shape retrieval, and 3D modeling. We first evaluate the descriptiveness of these descriptors on eight popular datasets which were acquired using different techniques. We then analyze their compactness using the recall of feature matching per each float value in the descriptor. We also test the robustness of the selected descriptors with respect to support radius variations, Gaussian noise, shot noise, varying mesh resolution, distance to the mesh boundary, keypoint localization error, occlusion, clutter, and dataset size. Moreover, we present the performance results of these descriptors when combined with different 3D keypoint detection methods. We finally analyze the computational efficiency for generating each descriptor.

    U2 - 10.1007/s11263-015-0824-y

    DO - 10.1007/s11263-015-0824-y

    M3 - Article

    VL - 116

    SP - 66

    EP - 89

    JO - International Journal of Computer Vision

    JF - International Journal of Computer Vision

    SN - 0920-5691

    IS - 1

    ER -