Files in this item

FilesDescriptionFormat

application/pdf

application/pdf9543647.pdf (4MB)Restricted to U of Illinois
(no description provided)PDF

Description

Title:Learning and feature selection in stereo matching
Author(s):Lew, Michael S.
Doctoral Committee Chair(s):Huang, Thomas S.
Department / Program:Electrical and Computer Engineering
Discipline:Electrical Engineering
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:Ph.D.
Genre:Dissertation
Subject(s):Engineering, Electronics and Electrical
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.
Issue Date:1995
Type:Text
Language:English
URI:http://hdl.handle.net/2142/20282
Rights Information:Copyright 1995 Lew, Michael S.
Date Available in IDEALS:2011-05-07
Identifier in Online Catalog:AAI9543647
OCLC Identifier:(UMI)AAI9543647


This item appears in the following Collection(s)

Item Statistics