Home // GEOProcessing 2014, The Sixth International Conference on Advanced Geographic Information Systems, Applications, and Services // View article

Pattern Based Feature Matching for Geospatial Data Conflation

Authors:
Weiping Yang
Dan Lee
Nobbir Ahmed

Keywords: geospatial featture patterns; feature matching; geospatial data conflation; geoprocessing.

Abstract:
This paper describes a linear feature matching method for overlapping data sources aimed at developing geospatial conflation tools. This method is based on identifying distinguished feature patterns, which are categorized as atomic patterns and composite patterns. It is hoped that these feature level patterns, once identified and modeled, will serve as a signature and as a helpful vehicle to enrich semantic meanings of a dataset. Features from overlapping sources will then be matched, by first matching large or complex structures and then breaking down to individual features of varying cardinalities. This feature matching method has been implemented as a core component for geoprocessing conflation tools to perform spatial adjustment, attribute transfer, and feature change detection. Applying these tools, in workflows, to real world data has produced promising results.

Pages: 64 to 69

Copyright: Copyright (c) IARIA, 2014

Publication date: March 23, 2014

Published in: conference

ISSN: 2308-393X

ISBN: 978-1-61208-326-1

Location: Barcelona, Spain

Dates: from March 23, 2014 to March 27, 2014