Recovering 3D motion of multiple objects using adaptive Hough transform

    Authors

    T. Y. Tian;M. Shah

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    IEEE Trans. Pattern Anal. Mach. Intell.

    Keywords

    multiple-motion analysis; segmentation; structure-from-motion; robust; estimation; adaptive Hough transform; OPTICAL-FLOW; MOVING-OBJECTS; ALGORITHM; Computer Science, Artificial Intelligence; Engineering, Electrical &; Electronic

    Abstract

    We present a method to determine 3D motion and structure of multiple objects from two perspective views, using adaptive Hough transform. In our method, segmentation is determined based on a 3D rigidity constraint. Instead of searching candidate solutions over the entire five-dimensional translation and rotation parameter space, we only examine the two-dimensional translation space. We divide the input image into overlapping patches, and, for each sample of the translation space, we compute the rotation parameters of patches using least-squares fit. Every patch votes for a sample in the five-dimensional parameter space. For a patch containing multiple motions, we use a redescending M-estimator to compute rotation parameters of a dominant motion within the patch. To reduce computational and storage burdens of standard multidimensional Hough transform, we use adaptive Hough transform to iteratively refine the relevant parameter space in a ''coarse-to-fine'' fashion. Our method can robustly recover 3D motion parameters, reject outliers of the flow estimates, and deal with multiple moving objects present in the scene. Applications of the proposed method to both synthetic and real image sequences are demonstrated with promising results.

    Journal Title

    Ieee Transactions on Pattern Analysis and Machine Intelligence

    Volume

    19

    Issue/Number

    10

    Publication Date

    1-1-1997

    Document Type

    Article

    Language

    English

    First Page

    1178

    Last Page

    1183

    WOS Identifier

    WOS:A1997YB67800015

    ISSN

    0162-8828

    Share

    COinS