The common approach to image matching is to detect spatial features present in both images and create a mapping that relates both images. The main drawback of this method takes place when more than one matching is likely. A first simplification to this ambiguity is to represent with a parametric model the point locus where the matching is highly likely, and then use a POCS (projection onto convex sets) procedure combined with Tikhonov regularization that results in the mapping vectors. However, if there is more than one model per pixel, the regularization and constraint-forcing process faces a multiple-choice dilemma that has no easy solution. This work proposes a framework to overcome this drawback: the combined projection over multiple models based on the L/sub k/, norm of the projection-point distance. This approach is tested on a stereo-pair that presents multiple choices of similar likelihood.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Multiple feature models for image matching


    Beteiligte:
    Morales, J. (Autor:in) / Verdu, R. (Autor:in) / Sancho, J.L. (Autor:in) / Weruaga, L. (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    280936 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Multiple Feature Models for Image Matching

    Morales, J. / Verdu, R. / Sancho, J. L. et al. | British Library Conference Proceedings | 2005


    Feature Matching for Building Extraction from Multiple Views

    Roux, M. / McKeown, D. M. / Institute of Electrical and Electronics Engineers; Computer Society | British Library Conference Proceedings | 1994



    Hierarchical semantic image matching using CNN feature pyramid

    Yu, Wei / Sun, Xiaoshuai / Yang, Kuiyuan et al. | British Library Online Contents | 2018


    Image Feature Matching Algorithm Research on Topography Measurement

    Wang, W. / Li, P. / Zhang, Y. | British Library Online Contents | 2008