A recognition strategy consisting of a mixture of indexing on invariants and search, allows objects to be recognised up to a Euclidean ambiguity with an uncalibrated camera. The approach works by using projective invariants to determine all the possible projectively equivalent models for a particular imaged object; then a system of global consistency constraints is used to determine which of these projectively equivalent, but Euclidean distinct, models corresponds to the objects viewed. These constraints follow from properties of the imaging geometry. In particular, a recognition hypothesis is equivalent to an assertion about, among other things, viewing conditions and geometric relationships between objects, and these assertions must be consistent for hypotheses to be correct. The approach is demonstrated to work on images of real scenes consisting of polygonal objects and polyhedra.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Using global consistency to recognise Euclidean objects with an uncalibrated camera


    Contributors:
    Forsyth (author) / Mundy (author) / Zisserman (author) / Rothwell (author)


    Publication date :

    1994-01-01


    Size :

    539040 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Using Global Consistency to Recognise Euclidean Objects with an Uncalibrated Camera

    Forsyth, D. A. / Mundy, J. L. / Zisserman, A. et al. | British Library Conference Proceedings | 1994


    Uncalibrated Euclidean reconstruction: a review

    Fusiello, A. | British Library Online Contents | 2000


    Quasi-Euclidean epipolar rectification of uncalibrated images

    Fusiello, A. / Irsara, L. | British Library Online Contents | 2011



    Recognizing Large 3-D Objects through Next View Planning using an Uncalibrated Camera

    Roy, S. / Chaudhury, S. / Banerjee, S. et al. | British Library Conference Proceedings | 2001