This paper proposes a new HR spatio-temporal vegetation classification approach based on SVM. A multi-band SVM
approach is first applied on satellite images time series then a graph based SVM algorithm is used for temporal analysis.
SAR change detection techniques have proved to be a precious
tool for damaged areas rapid mapping especially after
natural disasters. In case of similar acquisition modalities,
general framework uses SAR images local statistics to extract
efficient change measures. Recent works propose a new technique
adapted to different sensors, acquisition modalities or
climatic conditions. This technique is based on projecting the
statistics of the first image to the acquisition conditions of the
second image using the copula theory modelled by a quantile
regression. However, this is done without considering the
SAR texture behaviour which follows a Rayleigh distribution.
In this paper, we present a new method adapted to heterogeneous
SAR images. A new copula has been constructed
starting fromtwo marginal Rayleigh distributions. Then usual
Kullback Leibler (KL) based comparisons are used to validate
the proposedmethod and shows its suitability to SAR images.
Different climatic conditions ENVISAT SAR images are used
to highlight the performances of this technique.
Many are the examples of application of SAR and differential SAR interferometry for topographic mapping and ground deformation monitoring. However, on repeat pass geometry, the performances of these two techniques are limited by the loss of correlation (coherence) between the two radar acquisitions. The lack of coherence causes an additional noise thus a poor estimate of the interferometric phase. The disturbances can be due either to surface changes because of long period cover (temporal decorrelation) or to a too large baseline (spatial decorrelation). In this paper, we propose an empirical model for the estimate of coherence considering separately these two sources of disturbances. Starting from the observations of experimental data, we study the behaviour of coherence according to baseline and period cover in order to express the two terms of correlation. A number of 170 multi temporal and multi baseline differential interferograms covering the same region is used to validate the proposed model.