Presents a method to determine the 3D motion of multiple objects from two perspective views. In our method, segmentation is determined based on a 3D rigidity constraint. We divide the input image into overlapping patches, and for each sample of the translation parameter space, we compute the rotation parameters of patches using a least-squares fit. Every patch votes for a sample in the translation and rotation parameter space. For a patch containing multiple motions, we use an M-estimator to compute rotation parameters of a dominant motion. We use the adaptive Hough transform to refine the relevant parameter space in a "coarse-to-fine" fashion. Applications of the proposed method to both synthetic and real images are demonstrated with promising results.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Recovering 3D motion of multiple objects using adaptive Hough transform


    Contributors:
    Tina Yu Tian (author) / Shah, M. (author)


    Publication date :

    1995-01-01


    Size :

    602201 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Recovering 3D Motion of Multiple Objects Using Adaptive Hough Transform

    Yu Tian, T. / Shah, M. / IEEE Computer Society et al. | British Library Conference Proceedings | 1995


    Which Hough Transform?

    Leavers, V. F. | British Library Online Contents | 1993


    Connective Hough transform

    Yuen, S. Y. K. / Lam, T. S. L. / Leung, N. K. D. | British Library Online Contents | 1993


    Adaptive dual-point Hough transform for object recognition

    Chau, C. P. / Siu, W. C. | British Library Online Contents | 2004


    Multiple vehicle tracking using invariant moments and Hough transform

    Rhee, Seung Hak / Ahmad, Muhammad Bilal / Park, Seung-Jin et al. | SPIE | 2004