In this work we address the synergy of optical, SAR (Synthetic Aperture Radar) and topographic data in soil moisture retrieval over an Alpine area. As estimation technique, we consider Gaussian Process Regression (GPR). The test area is located in South Tyrol, Italy where the main land types are meadows and pastures. Time series of ASAR Wide Swath - SAR, optical, topographic and ancillary data (meteorological information and snow cover maps) acquired repetitively in 2010 were examined. Regarding optical data, we used both, daily MODIS reflectances, and daily NDVI, interpolated from the 16-day MODIS composite. Slope, elevation and aspect were extracted from a 2.5 m DEM (Digital Elevation Model) and resampled to 10 m. Daily soil moisture measurements were collected in the three fixed stations (two located in meadows and one located in pasture). The snow maps were used to mask the points covered by snow. The best performance was obtained by adding MODIS band 6 at
1640 nm to SAR and DEM features. The corresponding coefficient of determination, R2, was equal to 0.848, and the root mean square error, RMSE, to 5.4 % Vol. Compared to the case when no optical data were considered, there was an increase of ca. 0.05 in R2 and a decrease in RMSE of ca. 0.7 % Vol. This work showed that the joint use of NDVI or water absorption reflectance with SAR and topographic data can improve the estimation of soil moisture in specific Alpine area and that GPR is an effective method for estimation.
This contribution studies a feature extraction technique aiming at reducing differences between domains in image
classification. The purpose is to find a common feature space between labeled samples issued from a source image
and test samples belonging to a related target image. The presented approach, Transfer Component Analysis,
finds a transformation matrix performing a joint mapping of the two domains by minimizing a probability
distribution distance measure, the Maximum Mean Discrepancy criterion. When predicting on a target image,
such a projection allows to apply a supervised classifier trained exclusively on labeled source pixels mapped
in this common latent subspace. Promising results are observed on a urban scene captured by a hyperspectral
image. The experiments reveal improvements with respect to a standard classification model built on the original
source image and other feature extraction techniques.
This paper presents a novel unsupervised clustering scheme to find changes in two or more coregistered remote
sensing images acquired at different times. This method is able to find nonlinear boundaries to the change
detection problem by exploiting a kernel-based clustering algorithm. The kernel k-means algorithm is used in
order to cluster the two groups of pixels belonging to the 'change' and 'no change' classes (binary mapping). In
this paper, we provide an effective way to solve the two main challenges of such approaches: i) the initialization
of the clustering scheme and ii) a way to estimate the kernel function hyperparameter(s) without an explicit
training set. The former is solved by initializing the algorithm on the basis of the Spectral Change Vector (SCV)
magnitude and the latter is optimized by minimizing a cost function inspired by the geometrical properties of
the clustering algorithm. Experiments on VHR optimal imagery prove the consistency of the proposed approach.
A key factor for the success of supervised remote sensing image classification is the definition of an efficient training
set. Suboptimality in the selection of the training samples can bring to low classification performance. Active
learning algorithms aim at building the training set in a smart and efficient way, by finding the most relevant
samples for model improvement and thus iteratively improving the classification performance. In uncertaintybased
approaches, a user-defined heuristic ranks the unlabeled samples according to the classifier's uncertainty
about their class membership. Finally, the user is asked to define the labels of the pixels scoring maximum
uncertainty. In the present work, an unbiased uncertainty scoring function encouraging sampling diversity is
investigated. A modified version of the Entropy Query by Bagging (EQB) approach is presented and tested
on very high resolution imagery using both SVM and LDA classifiers. Advantages of favoring diversity in the
heuristics are discussed. By the diverse sampling it enhances, the unbiased approach proposed leads to higher
convergence rates in the first iterations for both the models considered.
In this paper, mixed spectral-structural kernel machines are proposed for the classification of very-high resolution
images. The simultaneous use of multispectral and structural features (computed using morphological
filters) allows a significant increase in classification accuracy of remote sensing images. Subsequently, weighted
summation kernel support vector machines are proposed and applied in order to take into account the multiscale
nature of the scene considered. Such classifiers use the Mercer property of kernel matrices to compute a new
kernel matrix accounting simultaneously for two scale parameters. Tests on a Zurich QuickBird image show
the relevance of the proposed method : using the mixed spectral-structural features, the classification accuracy
increases of about 5%, achieving a Kappa index of 0.97. The multikernel approach proposed provide an overall
accuracy of 98.90% with related Kappa index of 0.985.