The development of SAR technology during the last decade has made it possible to collect a huge amount of data over many regions of the world. In particular, the availability of SAR images from different sensors, with metric or sub-metric spatial resolution, offers novel opportunities in different fields as land cover, urban monitoring, soil consumption etc. On the other hand, automatic approaches become crucial for the exploitation of such a huge amount of information. In such a scenario, especially if single polarization images are considered, the main issue is to select appropriate contextual descriptors, since the backscattering coefficient of a single pixel may not be sufficient to classify an object on the scene. In this paper a comparison among three different approaches for contextual features definition is presented so as to design optimum procedures for VHR SAR scene understanding. The first approach is based on Gray Level Co- Occurrence Matrix since it is widely accepted and several studies have used it for land cover classification with SAR data. The second approach is based on the Fourier spectra and it has been already proposed with positive results for this kind of problems, the third one is based on Auto-associative Neural Networks which have been already proven effective for features extraction from polarimetric SAR images. The three methods are evaluated in terms of the accuracy of the classified scene when the features extracted using each method are considered as input to a neural network classificator and applied on different Cosmo-SkyMed spotlight products.
Satellite SAR Interferometry (InSAR) has already proved its effectiveness in the analysis of seismic events. In fact,
measuring the surface displacement field generated by an earthquake can be useful to define fault parameters regarding
the geometry (such as dip and strike angles, width, length), the extension of the rupture and the distribution of slip on the
fault plain. However, to retrieve the source parameters from InSAR measurements is rather complex since the inversion
problem is ill-posed. In this work we propose an inversion approach for retrieving the fault parameters based on neural
networks, trained by simulated data sets generated by means of the Okada forward model. The developed work-flow
implements a pre-processing step, aiming to reducing the data dimensionality, in order to improve the performance of the
neural network inversion. The methodology has been validated by using experimental data sets obtained using different
wavelength and representative of different kind of seismic source mechanisms.
Satellite SAR Interferometry (InSAR) has been already proven to be effective in the analysis of seismic events. In fact,
the surface displacement field obtained by InSAR application contains useful information to define the fault geometry
(such as dip and strike angles, width, length), the extension of the rupture, the distribution of slip on the fault plain.
However, the solution of the inverse problem, which means to recover the source parameters from the knowledge of
InSAR surface displacement field, is rather complex. In this work we propose an inversion approach for the seismic
source classification and the fault parameter quantitative retrieval based on neural networks. The network is trained by
using a simulated data set generated by means of a forward model. The application of the methodology has been
validated with a set of experimental data corresponding to different types of seismic events.
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.