Elastic Conformal Transformation of Digital Images
Result description
A novel transformation model for registration of geometrically distorted digital images is proposed in the contribution. The registration method is based on a set of ground control points (GCPs) whose coordinates have been captured with limited accuracy.The spatial inaccuracy of the GCPs influences precision of transformation between input and reference images. Quality of the transformation is also affected by unknown nonlinear elastic distortions of the input image. Simultaneous impact of the both sources of inaccuracy results in spatial imprecision of the transformed image. Correct estimation of the resulting spatial imprecision is significant constituent of the proposed registration method. Theoretical principle of the proposed method stems from theory of Gaussian processes (collocation, kriging) and is worked out with the aid of Bayesian approach. The overall solution embodies advantages of non-parametric and parametric estimation - it is both data-driven and tunable by a simple s
Keywords
CartographyGeoinformationEngineering surveyCadastreImage ProcessingData qualityAccuracy analysisBayesian approach
The result's identifiers
Result code in IS VaVaI
Result on the web
http://fig.net/pub/fig2012/papers/ts02f/TS02F_soukup_havrlant_et_al_5765.pdf
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Elastic Conformal Transformation of Digital Images
Original language description
A novel transformation model for registration of geometrically distorted digital images is proposed in the contribution. The registration method is based on a set of ground control points (GCPs) whose coordinates have been captured with limited accuracy.The spatial inaccuracy of the GCPs influences precision of transformation between input and reference images. Quality of the transformation is also affected by unknown nonlinear elastic distortions of the input image. Simultaneous impact of the both sources of inaccuracy results in spatial imprecision of the transformed image. Correct estimation of the resulting spatial imprecision is significant constituent of the proposed registration method. Theoretical principle of the proposed method stems from theory of Gaussian processes (collocation, kriging) and is worked out with the aid of Bayesian approach. The overall solution embodies advantages of non-parametric and parametric estimation - it is both data-driven and tunable by a simple s
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
DE - Earth magnetism, geodesy, geography
OECD FORD branch
—
Result continuities
Project
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings FIG Working Week 2012 Rome, Italy, 6-10 May 2012
ISBN
978-87-90907-98-3
ISSN
—
e-ISSN
—
Number of pages
10
Pages from-to
1-10
Publisher name
International Federation of Surveyors
Place of publication
Řím, Itálie
Event location
Řím, Itálie
Event date
Jan 1, 2012
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—
Basic information
Result type
D - Article in proceedings
CEP
DE - Earth magnetism, geodesy, geography
Year of implementation
2012