The objective of this work is to enlarge the class of camera motions for which epipolar geometry and image correspondences can be computed automatically. This facilitates matching between quite disparate views-wide baseline stereo. Two extensions are made to the current small baseline algorithms: first, and most importantly, a viewpoint invariant measure is developed for assessing the affinity of corner neighbourhoods over image pairs; second, algorithms are given for generating putative corner matches between image pairs using local homographies. Two novel infrastructure developments are also described: the automatic generation of local homographies, and the combination of possibly conflicting sets of matches prior to RANSAC estimation. The wide baseline matching algorithm is demonstrated on a number of image pairs with varying relative motion, and for different scene types. All processing is automatic.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Wide baseline stereo matching


    Contributors:


    Publication date :

    1998-01-01


    Size :

    1057739 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Wide Baseline Stereo Matching

    Pritchett, P. / Zisserman, A. / IEEE; Computer Society | British Library Conference Proceedings | 1998


    Wide-baseline stereo matching with line segments

    Bay, H. / Ferraris, V. / Van Gool, L. | IEEE | 2005


    Viewpoint invariant texture matching and wide baseline stereo

    Schaffalitzky, F. / Zisserman, A. | IEEE | 2001


    Viewpoint Invariant Texture Matching and Wide Baseline Stereo

    Schaffalitzky, F. / Zisserman, A. / IEEE | British Library Conference Proceedings | 2001


    Correspondence expansion for wide baseline stereo

    Steele, K.L. / Egbert, P.K. | IEEE | 2005