Object recognition from range images using superquadric representations

Erik van Dop, Paul Regtien

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

    1 Downloads (Pure)

    Abstract

    Segmentation of range images using superquadric entities has been pointed out by a number of researchers as a powerful approach towards object recognition. Problems exist in finding an unbiased decision function for the assignment of a superquadric representation with an object prototype. This paper discusses current distance measures between recovered models and prototypes and presents a novel method for classification of uncertain superquadric representations using a maximum likelihood criterium and incorporating the range image characteristics of an active optical triangulation sensor. The main advantage of this probabilistic method is its inherent minimisation of the classification error rate. The approach is applied to recognition of electronic components for printed circuit board waste management.
    Original languageEnglish
    Title of host publicationProceedings of MVA '96
    Subtitle of host publicationIAPR Workshop on Machine Vision Applications : November 12-14 1996, Tokyo, Japan
    Place of PublicationTokyo, Japan
    PublisherKeio University
    Pages267-270
    Publication statusPublished - 12 Nov 1996
    EventIAPR Workshop on Machine Vision Applications, MVA 1996 - Tokyo, Japan
    Duration: 12 Nov 199614 Nov 1996

    Workshop

    WorkshopIAPR Workshop on Machine Vision Applications, MVA 1996
    CountryJapan
    CityTokyo
    Period12/11/9614/11/96

    Fingerprint

    Object recognition
    Triangulation
    Waste management
    Printed circuit boards
    Maximum likelihood
    Sensors

    Keywords

    • METIS-113418

    Cite this

    van Dop, E., & Regtien, P. (1996). Object recognition from range images using superquadric representations. In Proceedings of MVA '96 : IAPR Workshop on Machine Vision Applications : November 12-14 1996, Tokyo, Japan (pp. 267-270). Tokyo, Japan: Keio University.
    van Dop, Erik ; Regtien, Paul. / Object recognition from range images using superquadric representations. Proceedings of MVA '96 : IAPR Workshop on Machine Vision Applications : November 12-14 1996, Tokyo, Japan. Tokyo, Japan : Keio University, 1996. pp. 267-270
    @inproceedings{9fc4207ad9684c0ab39370c74f9f177d,
    title = "Object recognition from range images using superquadric representations",
    abstract = "Segmentation of range images using superquadric entities has been pointed out by a number of researchers as a powerful approach towards object recognition. Problems exist in finding an unbiased decision function for the assignment of a superquadric representation with an object prototype. This paper discusses current distance measures between recovered models and prototypes and presents a novel method for classification of uncertain superquadric representations using a maximum likelihood criterium and incorporating the range image characteristics of an active optical triangulation sensor. The main advantage of this probabilistic method is its inherent minimisation of the classification error rate. The approach is applied to recognition of electronic components for printed circuit board waste management.",
    keywords = "METIS-113418",
    author = "{van Dop}, Erik and Paul Regtien",
    year = "1996",
    month = "11",
    day = "12",
    language = "English",
    pages = "267--270",
    booktitle = "Proceedings of MVA '96",
    publisher = "Keio University",
    address = "Japan",

    }

    van Dop, E & Regtien, P 1996, Object recognition from range images using superquadric representations. in Proceedings of MVA '96 : IAPR Workshop on Machine Vision Applications : November 12-14 1996, Tokyo, Japan. Keio University, Tokyo, Japan, pp. 267-270, IAPR Workshop on Machine Vision Applications, MVA 1996, Tokyo, Japan, 12/11/96.

    Object recognition from range images using superquadric representations. / van Dop, Erik; Regtien, Paul.

    Proceedings of MVA '96 : IAPR Workshop on Machine Vision Applications : November 12-14 1996, Tokyo, Japan. Tokyo, Japan : Keio University, 1996. p. 267-270.

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

    TY - GEN

    T1 - Object recognition from range images using superquadric representations

    AU - van Dop, Erik

    AU - Regtien, Paul

    PY - 1996/11/12

    Y1 - 1996/11/12

    N2 - Segmentation of range images using superquadric entities has been pointed out by a number of researchers as a powerful approach towards object recognition. Problems exist in finding an unbiased decision function for the assignment of a superquadric representation with an object prototype. This paper discusses current distance measures between recovered models and prototypes and presents a novel method for classification of uncertain superquadric representations using a maximum likelihood criterium and incorporating the range image characteristics of an active optical triangulation sensor. The main advantage of this probabilistic method is its inherent minimisation of the classification error rate. The approach is applied to recognition of electronic components for printed circuit board waste management.

    AB - Segmentation of range images using superquadric entities has been pointed out by a number of researchers as a powerful approach towards object recognition. Problems exist in finding an unbiased decision function for the assignment of a superquadric representation with an object prototype. This paper discusses current distance measures between recovered models and prototypes and presents a novel method for classification of uncertain superquadric representations using a maximum likelihood criterium and incorporating the range image characteristics of an active optical triangulation sensor. The main advantage of this probabilistic method is its inherent minimisation of the classification error rate. The approach is applied to recognition of electronic components for printed circuit board waste management.

    KW - METIS-113418

    M3 - Conference contribution

    SP - 267

    EP - 270

    BT - Proceedings of MVA '96

    PB - Keio University

    CY - Tokyo, Japan

    ER -

    van Dop E, Regtien P. Object recognition from range images using superquadric representations. In Proceedings of MVA '96 : IAPR Workshop on Machine Vision Applications : November 12-14 1996, Tokyo, Japan. Tokyo, Japan: Keio University. 1996. p. 267-270