Abstract : The paper addresses a new application of time-frequency representation in classification of non-stationary signals. It defines an approach to characterize curves describing the temporal reflectance profiles related to land-cover behavior. These curves are obtained from processing multi-resolution remote sensing data and then projected on a representation space improving discrimination between different land cover types. This approach can be applied in a scenario dedicated to the detection of land use changes caused by erosion.
https://hal.inria.fr/inria-00527191
Contributeur : Brigitte Briot
<>
Soumis le : mardi 18 octobre 2016 - 14:09:08
Dernière modification le : vendredi 25 mai 2018 - 12:02:05
Sonia Bouzidi, Isabelle Herlin. An approach using wavelet transform for land cover changes detection on remote sensing data. Sciences of Electronic, Technologies of Information and Telecommunications : SETIT 2003, Mar 2003, Mahdia, Tunisia. 2003. 〈inria-00527191〉
