Share Email Print

Proceedings Paper

Affine models for motion and shape recovery
Author(s): Chiou-Shann Fuh; Petros Maragos
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper presents an affine model for 3-D motion and shape recovery using two perspective views and their relative 2-D displacement field. The 2-D displacement vectors are estimated as parameters of a 2-D affine model that generalizes standard block matching by allowing affine shape deformations of image blocks and affine intensity transformations. The matching block size is effectively found via morphological size histograms. The parameters of the 3-D affine model are estimated using a least-squares algorithm that requires solving a system of linear equations with rank three. Some stabilization of the recovered motion parameters under noise is achieved through a simple form of MAP estimation. A multi-scale searching in the parameter space is also used to improve accuracy without high computational cost. Experiments on applying these affine models to various real world image sequences demonstrate that they can estimate dense displacement fields and recover motion parameters and object shape with relatively small errors.

Paper Details

Date Published: 1 November 1992
PDF: 15 pages
Proc. SPIE 1818, Visual Communications and Image Processing '92, (1 November 1992); doi: 10.1117/12.131421
Show Author Affiliations
Chiou-Shann Fuh, Harvard Univ. (United States)
Petros Maragos, Harvard Univ. (United States)

Published in SPIE Proceedings Vol. 1818:
Visual Communications and Image Processing '92
Petros Maragos, Editor(s)

© SPIE. Terms of Use
Back to Top