Files in this item

FilesDescriptionFormat

application/pdf

application/pdf8108655.pdf (5MB)Restricted to U of Illinois
(no description provided)PDF

Description

Title:Network Matching: A Versatile Computer Vision Tool
Author(s):Selander, John Michael
Department / Program:Electrical Engineering
Discipline:Electrical Engineering
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:Ph.D.
Genre:Dissertation
Subject(s):Engineering, Electronics and Electrical
Computer Science
Abstract:This work consists of a development and an investigation of the computational process of network matching as it is applied to the computer vision domain. In particular a cost based definition of network matching is developed which is oriented toward the kinds of computational problems that occur in computer vision. Emphasis is placed on the concurrent use of distance and topologic information. Several optimal and near optimal algorithms are developed, and their properties are examined. One of these algorithms was found to be a versatile tool for solving several hereto unrelated problems in the computer vision domain.
The latter part of this work describes the application of this algorithm to four problems. The first problem deals with the determination of depth information from a camera motion sequence. The second problem deals with the construction of three dimensional object models from many images. This problem is made more difficult by denying the computer information concerning the angles and distance between the camera and the object. The third problem deals with the recognition of occluding three dimensional objects in a single view. The final problem deals with network matching as applied to scene labeling in a noisy and ambiguous environment.
Issue Date:1980
Type:Text
Language:English
Description:149 p.
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1980.
URI:http://hdl.handle.net/2142/66244
Other Identifier(s):(UMI)AAI8108655
Date Available in IDEALS:2014-12-12
Date Deposited:1980


This item appears in the following Collection(s)

Item Statistics