Symmetry is an effective geometric cue to facilitate conventional segmentation techniques on images of man-made environment. Based on three fundamental principles that summarize the relations between symmetry and perspective imaging, namely, structure from symmetry, symmetry hypothesis testing, and global symmetry testing, we develop a prototype system which is able to automatically segment symmetric objects in space from single 2D perspective images. The result of such a segmentation is a hierarchy of geometric primitives, called symmetry cells and complexes, whose 3D structure and pose are fully recovered. Such a geometrically meaningful segmentation may greatly facilitate applications such as feature matching and robot navigation.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Geometric segmentation of perspective images based on symmetry groups


    Contributors:
    Yang, (author) / Shankar Rao, (author) / Kun Huang, (author) / Wei Hong, (author) / Yi Ma, (author)


    Publication date :

    2003-01-01


    Size :

    944846 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Geometric Segmentation of Perspective Images Based on Symmetry Groups

    Yang, A. / Rao, S. / Huang, K. et al. | British Library Conference Proceedings | 2003


    Symmetry-based 3-D reconstruction from perspective images

    Yang, A. Y. / Huang, K. / Rao, S. et al. | British Library Online Contents | 2005


    Segmentation of Range Images as the Search for Geometric Parametric Models

    Leonardis, A. / Gupta, A. / Bajcsy, R. | British Library Online Contents | 1995


    Coupled Geometric and Texture Pde-Based Segmentation

    Sofou, A. / Evangelopoulos, G. / Maragos, P. | British Library Conference Proceedings | 2005


    Coupled geometric and texture PDE-based segmentation

    Sofou, A. / Evangelopoulos, G. / Maragos, P. | IEEE | 2005