MULTIPLE-MODEL BASED UPDATE OF BELGIAN REFERENCE ROAD DATA

This paper describes a semi-automatic system for road update based on high resolution orthophotos and 3D surface models. Potential update regions are identified by an object-wise verification of all existing database records, followed by a scene-wide detection of redevelopment regions. The propose...

Full description

Bibliographic Details
Main Authors: M. Ziems, J. Beyen, S. Mueller, S. Roovers, C. Heipke
Format: Article
Language:English
Published: Copernicus Publications 2012-08-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XXXVIII-4-W25/73/2011/isprsarchives-XXXVIII-4-W25-73-2011.pdf
_version_ 1811276162930835456
author M. Ziems
J. Beyen
S. Mueller
S. Roovers
C. Heipke
author_facet M. Ziems
J. Beyen
S. Mueller
S. Roovers
C. Heipke
author_sort M. Ziems
collection DOAJ
description This paper describes a semi-automatic system for road update based on high resolution orthophotos and 3D surface models. Potential update regions are identified by an object-wise verification of all existing database records, followed by a scene-wide detection of redevelopment regions. The proposed system combines several road detection and road verification approaches from current literature to form a more general solution. Each road detection / verification approach is realized as an independent module representing a unique road model combined with a corresponding processing strategy. The object-wise verification result of each module is formulated as a binary decision between the classes "correct road" and "incorrect road". These individual decisions are combined by Dempster-Shafer fusion, which provides tools for dealing with uncertain and incomplete knowledge about the statistical properties of the data. For each road detection / verification module a confidence function for the result is introduced that reflects the degree of correspondence of an actual test situation with an optimal situation according to the underlying road model of that module. Experimental results achieved with data from the national Belgian road database in a test site of about 134 km<sup>2</sup> demonstrate the potential of the method.
first_indexed 2024-04-12T23:52:42Z
format Article
id doaj.art-8ca25b1047754d99bbcac875f6737aa7
institution Directory Open Access Journal
issn 1682-1750
2194-9034
language English
last_indexed 2024-04-12T23:52:42Z
publishDate 2012-08-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj.art-8ca25b1047754d99bbcac875f6737aa72022-12-22T03:11:39ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342012-08-01XXXVIII-4-W25737910.5194/isprsarchives-XXXVIII-4-W25-73-2011MULTIPLE-MODEL BASED UPDATE OF BELGIAN REFERENCE ROAD DATAM. Ziems0J. Beyen1S. Mueller2S. Roovers3C. Heipke4IPI &ndash; Institute of Photogrammetry and GeoInformation, Leibniz Universität Hannover, Nienburger Str. 1, 30167 Hannover, GermanyNGI &ndash; National Geographical Institute, Abdij Ter Kameren 13, B-1000 Brussels, BelgiumIPI &ndash; Institute of Photogrammetry and GeoInformation, Leibniz Universität Hannover, Nienburger Str. 1, 30167 Hannover, GermanyNGI &ndash; National Geographical Institute, Abdij Ter Kameren 13, B-1000 Brussels, BelgiumIPI &ndash; Institute of Photogrammetry and GeoInformation, Leibniz Universität Hannover, Nienburger Str. 1, 30167 Hannover, GermanyThis paper describes a semi-automatic system for road update based on high resolution orthophotos and 3D surface models. Potential update regions are identified by an object-wise verification of all existing database records, followed by a scene-wide detection of redevelopment regions. The proposed system combines several road detection and road verification approaches from current literature to form a more general solution. Each road detection / verification approach is realized as an independent module representing a unique road model combined with a corresponding processing strategy. The object-wise verification result of each module is formulated as a binary decision between the classes "correct road" and "incorrect road". These individual decisions are combined by Dempster-Shafer fusion, which provides tools for dealing with uncertain and incomplete knowledge about the statistical properties of the data. For each road detection / verification module a confidence function for the result is introduced that reflects the degree of correspondence of an actual test situation with an optimal situation according to the underlying road model of that module. Experimental results achieved with data from the national Belgian road database in a test site of about 134 km<sup>2</sup> demonstrate the potential of the method.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XXXVIII-4-W25/73/2011/isprsarchives-XXXVIII-4-W25-73-2011.pdf
spellingShingle M. Ziems
J. Beyen
S. Mueller
S. Roovers
C. Heipke
MULTIPLE-MODEL BASED UPDATE OF BELGIAN REFERENCE ROAD DATA
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title MULTIPLE-MODEL BASED UPDATE OF BELGIAN REFERENCE ROAD DATA
title_full MULTIPLE-MODEL BASED UPDATE OF BELGIAN REFERENCE ROAD DATA
title_fullStr MULTIPLE-MODEL BASED UPDATE OF BELGIAN REFERENCE ROAD DATA
title_full_unstemmed MULTIPLE-MODEL BASED UPDATE OF BELGIAN REFERENCE ROAD DATA
title_short MULTIPLE-MODEL BASED UPDATE OF BELGIAN REFERENCE ROAD DATA
title_sort multiple model based update of belgian reference road data
url https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XXXVIII-4-W25/73/2011/isprsarchives-XXXVIII-4-W25-73-2011.pdf
work_keys_str_mv AT mziems multiplemodelbasedupdateofbelgianreferenceroaddata
AT jbeyen multiplemodelbasedupdateofbelgianreferenceroaddata
AT smueller multiplemodelbasedupdateofbelgianreferenceroaddata
AT sroovers multiplemodelbasedupdateofbelgianreferenceroaddata
AT cheipke multiplemodelbasedupdateofbelgianreferenceroaddata