This paper investigates the capability of high-resolution SAR data for urban landuse/land-cover mapping by integrating
support vector machines (SVMs) into object-based analysis. Five-date RADARSAT fine-beam C-HH SAR images with
a pixel spacing of 6.25 meter were acquired over the rural-urban fringe of the Great Toronto Area (GTA) during May to
August in 2002. First, the SAR images were segmented using multi-resolution segmentation algorithm and two
segmentation levels were created. Next, a range of spectral, shape and texture features were selected and calculated for
all image objects on both levels. The objects on the lower level then inherited features of their super objects. In this way,
the objects on the lower level received detailed descriptions about their neighbours and contexts. Finally, SVM
classifiers were used to classify the image objects on the lower level based on the selected features. For training the
SVM, sample image objects on the lower level were used. One-against-one approach was chosen to apply SVM to multiclass
classification of SAR images in this research. The results show that the proposed method can achieve a high
accuracy for the classification of high-resolution SAR images over urban areas.
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.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.