It is shown that curved planar objects have shape descriptors that are unaffected by the position, orientation and intrinsic parameters of the camera. These shape descriptors can be used to index quickly and efficiently into a large model base of curved planar objects, because their value is independent of pose and unaffected by perspective. Thus, recognition can proceed independent of calculating pose. Object curves are represented using conics, attached with a fitting technique that commutes with projection. This means that the pose of an object can be determined by backprojecting known conics. The authors show examples of recognition and pose determination using real image data.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Invariance-a new framework for vision


    Contributors:
    Forsyth, D. (author) / Mundy, J.L. (author) / Zisserman, A. (author) / Brown, C.M. (author)


    Publication date :

    1990-01-01


    Size :

    1015795 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    On Affine Invariance in the Beltrami Framework for Vision

    Sochen, N. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2001


    Vision and Lie's approach to invariance

    Van Gool, L. / Moons, T. / Pauwels, E. et al. | British Library Online Contents | 1995


    Invariance Signatures: Characterizing Contours by Their Departures from Invariance

    Squire, D. M. / Caelli, T. M. | British Library Online Contents | 2000


    DDS framework for automotive vision systems

    Pandit,S.M. / Guo,R. / Joshi,G.A. et al. | Automotive engineering | 1993