Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Land-Cover Mapping in StockholmUsing Fusion of ALOS PALSARand SPOT Data
KTH, School of Architecture and the Built Environment (ABE), Urban Planning and Environment, Geodesy and Satellite Positioning.
2008 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

The objective of this research was to investigate the capabilities for landcoverclassication using fusion of SAR data from the PALSAR sensor andoptical data from the SPOT sensor using a hierarchical approach.The Study area was Stockholm, Sweden. Two dual polarization PALSARimages and one multispectral SPOT HRG image acquired summer2007 was used. The data was classied in two levels. First the images wereseparated into four classes (Water, Forest, Urban and Open Area) with anarticial neural network (ANN) classier. In the second step, these classeswere rened by a hybrid classier to Water, Forest, Low Density Built-up,High Density Built-up, Road, Park and Open Field.As some areas in the optical image were covered by clouds, a hierarchicalclassication using only PALSAR was made. This classication was usedto ll in for \information gaps" in the joint classication of SPOT andPALSAR.The result from the hierarchical classier shows an overall accuracy increasewith more than 10% compared to an ordinary ANN-classier (from75,4% to 87,6%). The accuracy of all land cover classes increased except forthe Low Density Built-up, where the two classiers had approximately thesame result.For testing the capabilities of PALSAR for Land cover classication, tworeference classications using only ANN where created. The comparisonof those two land cover maps shows an overall accuracy increases whenincluding PALSAR data compared to only using optical data. Especiallythe accuracy of the classes Forest and Open Field increased; forest from87,6% to 94,0% and Open Field from 34,1% to 72,3%.The research shows that PALSAR data to some degree can be used toimprove the land cover classication in urban areas, and the hierarchicalapproach increases the classication accuracy compared to pixel-based classication.v

Place, publisher, year, edition, pages
2008.
Series
TRITA-GIT EX ; 08-12
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-199698OAI: oai:DiVA.org:kth-199698DiVA, id: diva2:1065093
Supervisors
Available from: 2017-01-19 Created: 2017-01-13 Last updated: 2017-01-19Bibliographically approved

Open Access in DiVA

fulltext(18449 kB)113 downloads
File information
File name FULLTEXT01.pdfFile size 18449 kBChecksum SHA-512
aa5a7c75cf93406ead1c13d536f1a0119862ff1a08cf3c8b9a35f1a3e6d9cdf1613551cdcc16ae5993dface442f1ceec5951f007e3baf5e7c690c88fd10f7e05
Type fulltextMimetype application/pdf

By organisation
Geodesy and Satellite Positioning
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 113 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 24 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf