Fitting undeformed superquadrics to range data: improving model recovery and classification

E.R. van Dop, Paulus P.L. Regtien

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    10 Citations (Scopus)
    91 Downloads (Pure)

    Abstract

    Undeformed superquadrics are volumetric modeling primitives with an extensive shape vocabulary that are described by only 5 parameters. Fitting these models viewpoint invariantly to range data enables classification based on the superquadric parameters. However, current recovery routines show several limitations, especially when the algorithms are applied to range images instead of true 3D images. In this paper problems with the common superquadric recovery procedure are identified and solutions are presented
    Original languageUndefined
    Title of host publicationProceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
    Place of PublicationSanta Barbara, California, USA
    PublisherIEEE
    Pages396-402
    ISBN (Print)0-8186-8497-6
    DOIs
    Publication statusPublished - 23 Jun 1998

    Publication series

    Name
    PublisherIEEE

    Keywords

    • IR-16326
    • METIS-113211

    Cite this

    van Dop, E. R., & Regtien, P. P. L. (1998). Fitting undeformed superquadrics to range data: improving model recovery and classification. In Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 396-402). Santa Barbara, California, USA: IEEE. https://doi.org/10.1109/CVPR.1998.698636
    van Dop, E.R. ; Regtien, Paulus P.L. / Fitting undeformed superquadrics to range data: improving model recovery and classification. Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Santa Barbara, California, USA : IEEE, 1998. pp. 396-402
    @inproceedings{ccf0c0253b164081949dd1d645c62b74,
    title = "Fitting undeformed superquadrics to range data: improving model recovery and classification",
    abstract = "Undeformed superquadrics are volumetric modeling primitives with an extensive shape vocabulary that are described by only 5 parameters. Fitting these models viewpoint invariantly to range data enables classification based on the superquadric parameters. However, current recovery routines show several limitations, especially when the algorithms are applied to range images instead of true 3D images. In this paper problems with the common superquadric recovery procedure are identified and solutions are presented",
    keywords = "IR-16326, METIS-113211",
    author = "{van Dop}, E.R. and Regtien, {Paulus P.L.}",
    year = "1998",
    month = "6",
    day = "23",
    doi = "10.1109/CVPR.1998.698636",
    language = "Undefined",
    isbn = "0-8186-8497-6",
    publisher = "IEEE",
    pages = "396--402",
    booktitle = "Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
    address = "United States",

    }

    van Dop, ER & Regtien, PPL 1998, Fitting undeformed superquadrics to range data: improving model recovery and classification. in Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, Santa Barbara, California, USA, pp. 396-402. https://doi.org/10.1109/CVPR.1998.698636

    Fitting undeformed superquadrics to range data: improving model recovery and classification. / van Dop, E.R.; Regtien, Paulus P.L.

    Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Santa Barbara, California, USA : IEEE, 1998. p. 396-402.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    TY - GEN

    T1 - Fitting undeformed superquadrics to range data: improving model recovery and classification

    AU - van Dop, E.R.

    AU - Regtien, Paulus P.L.

    PY - 1998/6/23

    Y1 - 1998/6/23

    N2 - Undeformed superquadrics are volumetric modeling primitives with an extensive shape vocabulary that are described by only 5 parameters. Fitting these models viewpoint invariantly to range data enables classification based on the superquadric parameters. However, current recovery routines show several limitations, especially when the algorithms are applied to range images instead of true 3D images. In this paper problems with the common superquadric recovery procedure are identified and solutions are presented

    AB - Undeformed superquadrics are volumetric modeling primitives with an extensive shape vocabulary that are described by only 5 parameters. Fitting these models viewpoint invariantly to range data enables classification based on the superquadric parameters. However, current recovery routines show several limitations, especially when the algorithms are applied to range images instead of true 3D images. In this paper problems with the common superquadric recovery procedure are identified and solutions are presented

    KW - IR-16326

    KW - METIS-113211

    U2 - 10.1109/CVPR.1998.698636

    DO - 10.1109/CVPR.1998.698636

    M3 - Conference contribution

    SN - 0-8186-8497-6

    SP - 396

    EP - 402

    BT - Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

    PB - IEEE

    CY - Santa Barbara, California, USA

    ER -

    van Dop ER, Regtien PPL. Fitting undeformed superquadrics to range data: improving model recovery and classification. In Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Santa Barbara, California, USA: IEEE. 1998. p. 396-402 https://doi.org/10.1109/CVPR.1998.698636