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/2142/20282
Description
Title
Learning and feature selection in stereo matching
Author(s)
Lew, Michael S.
Issue Date
1995
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
Language
eng
Abstract
A novel stereo matching algorithm is presented which integrates learning, feature, selection, and surface reconstruction. First, a new instance based learning (IBL) algorithm is used to generate an approximation to the optimal feature set for matching. In addition, the importance of two separate kinds of knowledge, image dependent knowledge and image independent knowledge, is discussed. Second, an adaptive method for refining the feature set is developed. This adaptive method analyzes the feature error to locate areas of the image which would lead to false matches. Then these areas are used to glide the search through feature space towards maximizing the class separation distance between the correct match and the false matches. Third, a self-diagnostic method is developed for determining when a priori knowledge is necessary for finding the correct match. If the a priori knowledge is necessary, then a surface reconstruction model is used to discriminate between match possibilities. The algorithm is comprehensively tested against fixed feature set algorithms and against a traditional pyramid algorithm. Finally, extensive empirical results based on a large set of real images are presented and discussed.
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.
