Title

Recovering 3D motion of multiple objects using adaptive hough transform

Keywords

Adaptive hough transform; Multiple-motion analysis; Robust estimation; Segmentation; Structure-frommotion

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 fivedimensional 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. © 1997 IEEE.

Publication Date

12-1-1997

Publication Title

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volume

19

Issue

10

Number of Pages

1178-1183

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/34.625131

Socpus ID

0031248787 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/0031248787

This document is currently not available here.

Share

COinS