We present a new on-line scheme for the recognition and pose estimation of a large isolated 3-D object, which may not entirely fit in a camera's field of view. We do not assume any knowledge of the internal parameters of the camera, or their constancy. We use a probabilistic reasoning framework for recognition and next view planning. We show results of successful recognition and pose estimation even in cases of a high degree of interpretation ambiguity associated with the initial view.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Recognizing large 3-D objects through next view planning using an uncalibrated camera


    Contributors:
    Roy, S.D. (author) / Chaudhury, S. (author) / Banerjee, S. (author)


    Publication date :

    2001-01-01


    Size :

    868653 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    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


    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 three-view image rectification

    Sun, C. | British Library Online Contents | 2003


    View synthesis from uncalibrated images using parallax

    Fusiello, A. / Caldrer, S. / Ceglie, S. et al. | IEEE | 2003


    View Synthesis of Scenes with Multiple Independently Translating Objects from Uncalibrated Views

    Sharma, Geetika / Chaudhury, Santanu / Srivastava, J. B. | Springer Verlag | 2006