We study and compare two novel embedding methods for segmenting feature points of piece-wise planar structures from two (uncalibrated) perspective images. We show that a set of different homographies can be embedded in different ways to a higher-dimensional real or complex space, so that each homography corresponds to either a complex bilinear form or a real quadratic form. Each embedding reveals different algebraic properties and relations of homographies. We give a closed-form segmentation solution for each case by utilizing these properties based on subspace-segmentation methods. These theoretical results show that one can intrinsically segment a piece-wise planar scene from 2-D images without explicitly performing any 3-D reconstruction. The resulting segmentation may make subsequent 3-D reconstruction much better-conditioned. We demonstrate the proposed methods with some convincing experimental results.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Segmentation of a piece-wise planar scene from perspective images


    Contributors:
    Yang, A.L. (author) / Rao, S. (author) / Wagner, A. (author) / Yi Ma, (author)


    Publication date :

    2005-01-01


    Size :

    524966 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Piecewise Planar Segmentation for Automatic Scene Modeling

    Bartoli, A. / IEEE | British Library Conference Proceedings | 2001



    INDOOR SCENE UNDERSTANDING FROM SINGLE-PERSPECTIVE IMAGES

    LIU BUYU / JI PAN / ZHUANG BINGBING et al. | European Patent Office | 2022

    Free access

    A random sampling strategy for piecewise planar scene segmentation

    Bartoli, A. | British Library Online Contents | 2007


    Segmentation of range images into planar regions

    Checchin, P. / Trassoudaine, L. / Alizon, J. | IEEE | 1997