ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Part-level object recognition using superquadrics

Jaka Krivic and Franc Solina (2004) Part-level object recognition using superquadrics. Computer Vision and Image Understanding, 95 (1). pp. 105-126.

Download (811Kb)


    This paper proposes a technique for object recognition using superquadric built models. Superquadrics, which are three-dimensional models suitable for part-level representation of objects, are reconstructed from range images using the recover-and-select paradigm. Using interpretation trees, the presence of an object from the model database can be hypothesized. These hypotheses are verified by projecting and re-fitting the object model to the range image of the scene which at the same time enables a better localization of the object in the scene.

    Item Type: Article
    Keywords: superquadrics, part-level object modelling, range images, object recognition
    Language of Content: English
    Related URLs:
    URLURL Type
    http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(id=4212052)Alternative location
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Divisions: Faculty of Computer and Information Science > Computer Vision Laboratory
    Item ID: 124
    Date Deposited: 08 Jul 2004
    Last Modified: 10 Dec 2013 14:42
    URI: http://eprints.fri.uni-lj.si/id/eprint/124

    Actions (login required)

    View Item