Matching algorithms use random-start local search and a 3D pose recovery algorithm to find optimal matches between 3D object models and 2D image features. An algorithm using only a a weak-perspective approximation to full 3D perspective solves a subset of the test problems presented. A second algorithm always uses an iterative 3D pose algorithm to account for 3D perspective and solves all test problems including those with varying 3D perspective. A third hybrid algorithm uses weak-perspective to direct search and 3D pose to periodically correct for perspective. It is faster than the second. A fourth algorithm is a hybrid which also uses a technique called 'subset-convergence ' to escape from some local optima. It performs best on the most difficult matching problems.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Optimal geometric model matching under full 3D perspective


    Contributors:


    Publication date :

    1994-01-01


    Size :

    987795 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Optimal Geometric Model Matching under Full 3D Perspective

    Beveridge, J. R. / Riseman, E. M. | British Library Online Contents | 1995


    Optimal Geometric Model Matching Under Full 3D Perspective

    Beveridge, J. R. / Riseman, E. M. / IEEE Computer Society; Technical Committee on Pattern Analysis and Machine Intelligence | British Library Conference Proceedings | 1994


    Geometric Matching

    Kwon, Kye‐Si ;Ready, Steven | Wiley | 2014


    Geometric blur for template matching

    Berg, A.C. / Malik, J. | IEEE | 2001


    Where's Wally? - Geometric Hashing for Model Based Image Matching

    Deguchi, K. | British Library Online Contents | 1993