We present a hierarchical approach for feature description and stereo matching in computer vision. Hierarchy is first used to make a high-level description of the scene. Edge pixels and lines are extracted and grouped into higher level symbolic descriptions: L-junctions, facets, surfaces. Because they are fewer in number and more significant, high-level features are easier to match, and help reduce matching ambiguity. Thus, the matching process is hierarchical: it starts with surfaces at the highest level, and is propagated down to lines at the lowest level. To determine the best order of matching, a control strategy is defined by classifying high-level features into areas of attention according to certainty and confidence criteria. Thus better formed features are matched first.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Hierarchical feature grouping for stereo matching


    Contributors:


    Publication date :

    1996-01-01


    Size :

    797951 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Hierarchical Feature Grouping for Stereo Matching

    Hamrouni, Z. / IEEE; Signal Processing Society | British Library Conference Proceedings | 1996


    Hierarchical region based stereo matching

    Cohen, L. / Vinet, L. / Sander, P.T. et al. | IEEE | 1989


    Hierarchical Stereo Matching Using Chromatic Information

    De la Fuente, E. / Trespaderne, F. M. / Peran, J. R. et al. | British Library Conference Proceedings | 1998



    Hierarchical stereo matching with image bit-plane slicing

    Lin, H. Y. | British Library Online Contents | 2013