Rigid object motion estimation from intensity images using straight-line correspondences
Liu, Yuncai
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/21089
Description
Title
Rigid object motion estimation from intensity images using straight-line correspondences
Author(s)
Liu, Yuncai
Issue Date
1990
Doctoral Committee Chair(s)
Huang, Thomas S.
Department of Study
Electrical and Computer Engineering
Discipline
Electrical Engineering
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Engineering, Electronics and Electrical
Physics, Electricity and Magnetism
Computer Science
Language
eng
Abstract
Determining three-dimensional (3D) rigid object motion from intensity images is a central problem in computer vision. This thesis presents a computational approach of 3D rigid object motion estimation using straight line correspondences. Based on the rigidity assumption, a linear algorithm and a nonlinear algorithm of motion estimation are developed. With six or more line correspondences over three frames, the nonlinear algorithm first solves for the rotations, then eliminates the rotations from the original motion and computes the translations. The linear algorithm requires at least thirteen straight line correspondences over three frames to recover motion. A set of intermediate parameters is first estimated, and motion parameters are then determined from these intermediate parameters.
Also discussed in this thesis are techniques of straight edge extraction and straight line matching used for obtaining line correspondences of significant edges with high accuracy for motion estimation.
The algorithms of motion estimation have also been extended to two applications. The first extension considers the problem of camera location determination from lines and points, and the second, the problem of 3D rigid object motion estimation from image corners.
Experimental results on synthetic as well as real image data are given.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
