Semi-automatic verification of cropland and grassland using very high resolution mono-temporal satellite images

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autoren

  • Petra Helmholz
  • Franz Rottensteiner
  • Christian Heipke

Externe Organisationen

  • Curtin University
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)204-218
Seitenumfang15
FachzeitschriftISPRS Journal of Photogrammetry and Remote Sensing
Jahrgang97
Frühes Online-Datum8 Okt. 2014
PublikationsstatusVeröffentlicht - 1 Nov. 2014

Abstract

Many public and private decisions rely on geospatial information stored in a GIS database. For good decision making this information has to be complete, consistent, accurate and up-to-date. In this paper we introduce a new approach for the semi-automatic verification of a specific part of the, possibly outdated GIS database, namely cropland and grassland objects, using mono-temporal very high resolution (VHR) multispectral satellite images. The approach consists of two steps: first, a supervised pixel-based classification based on a Markov Random Field is employed to extract image regions which contain agricultural areas (without distinction between cropland and grassland), and these regions are intersected with boundaries of the agricultural objects from the GIS database. Subsequently, GIS objects labelled as cropland or grassland in the database and showing agricultural areas in the image are subdivided into different homogeneous regions by means of image segmentation, followed by a classification of these segments into either cropland or grassland using a Support Vector Machine. The classification result of all segments belonging to one GIS object are finally merged and compared with the GIS database label. The developed approach was tested on a number of images. The evaluation shows that errors in the GIS database can be significantly reduced while also speeding up the whole verification task when compared to a manual process.

ASJC Scopus Sachgebiete

Zitieren

Semi-automatic verification of cropland and grassland using very high resolution mono-temporal satellite images. / Helmholz, Petra; Rottensteiner, Franz; Heipke, Christian.
in: ISPRS Journal of Photogrammetry and Remote Sensing, Jahrgang 97, 01.11.2014, S. 204-218.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Helmholz P, Rottensteiner F, Heipke C. Semi-automatic verification of cropland and grassland using very high resolution mono-temporal satellite images. ISPRS Journal of Photogrammetry and Remote Sensing. 2014 Nov 1;97:204-218. Epub 2014 Okt 8. doi: 10.1016/j.isprsjprs.2014.09.008
Download
@article{aafdcbd454b845dfad8ec9b745a816ad,
title = "Semi-automatic verification of cropland and grassland using very high resolution mono-temporal satellite images",
abstract = "Many public and private decisions rely on geospatial information stored in a GIS database. For good decision making this information has to be complete, consistent, accurate and up-to-date. In this paper we introduce a new approach for the semi-automatic verification of a specific part of the, possibly outdated GIS database, namely cropland and grassland objects, using mono-temporal very high resolution (VHR) multispectral satellite images. The approach consists of two steps: first, a supervised pixel-based classification based on a Markov Random Field is employed to extract image regions which contain agricultural areas (without distinction between cropland and grassland), and these regions are intersected with boundaries of the agricultural objects from the GIS database. Subsequently, GIS objects labelled as cropland or grassland in the database and showing agricultural areas in the image are subdivided into different homogeneous regions by means of image segmentation, followed by a classification of these segments into either cropland or grassland using a Support Vector Machine. The classification result of all segments belonging to one GIS object are finally merged and compared with the GIS database label. The developed approach was tested on a number of images. The evaluation shows that errors in the GIS database can be significantly reduced while also speeding up the whole verification task when compared to a manual process.",
keywords = "Automation, GIS, Mono-temporal, Quality control, Satellite images, Verification",
author = "Petra Helmholz and Franz Rottensteiner and Christian Heipke",
note = "Funding Information: The work was carried out as part of the WiPKA project ( Helmholz et al., 2012 ). The project was supported by the German Federal Agency for Cartography and Geodesy (BKG). The support is gratefully acknowledged.",
year = "2014",
month = nov,
day = "1",
doi = "10.1016/j.isprsjprs.2014.09.008",
language = "English",
volume = "97",
pages = "204--218",
journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
issn = "0924-2716",
publisher = "Elsevier",

}

Download

TY - JOUR

T1 - Semi-automatic verification of cropland and grassland using very high resolution mono-temporal satellite images

AU - Helmholz, Petra

AU - Rottensteiner, Franz

AU - Heipke, Christian

N1 - Funding Information: The work was carried out as part of the WiPKA project ( Helmholz et al., 2012 ). The project was supported by the German Federal Agency for Cartography and Geodesy (BKG). The support is gratefully acknowledged.

PY - 2014/11/1

Y1 - 2014/11/1

N2 - Many public and private decisions rely on geospatial information stored in a GIS database. For good decision making this information has to be complete, consistent, accurate and up-to-date. In this paper we introduce a new approach for the semi-automatic verification of a specific part of the, possibly outdated GIS database, namely cropland and grassland objects, using mono-temporal very high resolution (VHR) multispectral satellite images. The approach consists of two steps: first, a supervised pixel-based classification based on a Markov Random Field is employed to extract image regions which contain agricultural areas (without distinction between cropland and grassland), and these regions are intersected with boundaries of the agricultural objects from the GIS database. Subsequently, GIS objects labelled as cropland or grassland in the database and showing agricultural areas in the image are subdivided into different homogeneous regions by means of image segmentation, followed by a classification of these segments into either cropland or grassland using a Support Vector Machine. The classification result of all segments belonging to one GIS object are finally merged and compared with the GIS database label. The developed approach was tested on a number of images. The evaluation shows that errors in the GIS database can be significantly reduced while also speeding up the whole verification task when compared to a manual process.

AB - Many public and private decisions rely on geospatial information stored in a GIS database. For good decision making this information has to be complete, consistent, accurate and up-to-date. In this paper we introduce a new approach for the semi-automatic verification of a specific part of the, possibly outdated GIS database, namely cropland and grassland objects, using mono-temporal very high resolution (VHR) multispectral satellite images. The approach consists of two steps: first, a supervised pixel-based classification based on a Markov Random Field is employed to extract image regions which contain agricultural areas (without distinction between cropland and grassland), and these regions are intersected with boundaries of the agricultural objects from the GIS database. Subsequently, GIS objects labelled as cropland or grassland in the database and showing agricultural areas in the image are subdivided into different homogeneous regions by means of image segmentation, followed by a classification of these segments into either cropland or grassland using a Support Vector Machine. The classification result of all segments belonging to one GIS object are finally merged and compared with the GIS database label. The developed approach was tested on a number of images. The evaluation shows that errors in the GIS database can be significantly reduced while also speeding up the whole verification task when compared to a manual process.

KW - Automation

KW - GIS

KW - Mono-temporal

KW - Quality control

KW - Satellite images

KW - Verification

UR - http://www.scopus.com/inward/record.url?scp=84907756097&partnerID=8YFLogxK

U2 - 10.1016/j.isprsjprs.2014.09.008

DO - 10.1016/j.isprsjprs.2014.09.008

M3 - Article

AN - SCOPUS:84907756097

VL - 97

SP - 204

EP - 218

JO - ISPRS Journal of Photogrammetry and Remote Sensing

JF - ISPRS Journal of Photogrammetry and Remote Sensing

SN - 0924-2716

ER -