
Proceedings Paper
Fusion of RADARSAT fine-beam SAR and QuickBird data for land-cover mapping and change detectionFormat | Member Price | Non-Member Price |
---|---|---|
$17.00 | $21.00 |
Paper Abstract
The objective of this research is to evaluate multitemporal RADARSAT Fine-Beam C-HH SAR data, QuickBird MS
data, and fusion of SAR and MS for urban land-cover mapping and change detection One scene of QuickBird imagery
was acquired on July 18, 2002 and five-date RADARSAT fine-beam SAR images were acquired during May to August
in 2002. Landsat TM imagery from 1988 was used for change detection. QucikBird images were classified using an
object-based and rule-based approach. RADARSAR SAR texture images were classified using a hybrid approach. The
results demonstrated that, for identifying 19 land-cover classes, object-based and rule-based classification of Quickbird
data yielded an overall classification accuracy of 86.7% (kappa 0.857). For identifying 11 land-cover classes, ANN
classification of the combined Mean, Standard Deviation and Correlation texture images yielded an overall accuracy:
71.4%, (Kappa: 0.69). The hybrid classification of RADARSAT fine-beam SAR data improved the ANN classification
accuracy to 83.56% (kappa: 0.803). Decision level fusion of RADARSAT SAR and QuickBird data improved the
classification accuracy of several land cover classes.
The post-classification change detection was able to identify the areas of significant change, for example, major new
roads, new low-density and high-density builtup areas and golf courses, even though the change detection results
contained large amount of noise due to classification errors of individual images. QuickBrid classification result was
able add detailed change information to the major changes identified.
Paper Details
Date Published: 26 July 2007
PDF: 11 pages
Proc. SPIE 6752, Geoinformatics 2007: Remotely Sensed Data and Information, 67522H (26 July 2007); doi: 10.1117/12.760747
Published in SPIE Proceedings Vol. 6752:
Geoinformatics 2007: Remotely Sensed Data and Information
Weimin Ju; Shuhe Zhao, Editor(s)
PDF: 11 pages
Proc. SPIE 6752, Geoinformatics 2007: Remotely Sensed Data and Information, 67522H (26 July 2007); doi: 10.1117/12.760747
Show Author Affiliations
Irene Rangel, Kungliga Tekniska Högskolan (Sweden)
Published in SPIE Proceedings Vol. 6752:
Geoinformatics 2007: Remotely Sensed Data and Information
Weimin Ju; Shuhe Zhao, Editor(s)
© SPIE. Terms of Use
