Jocelyn Chanussot

ABSTRACT The integration of massive solar energy supply in the existing grids requires an accurate forecast of the solar resources to manage the energetic balance. In this context, we propose a new approach to forecast the Global Horizontal Irradiance at ground level from satellite images and ground based measurements. The training of spatio-temporal multidimensional autoregressive models with HelioClim-3 data along with 15-min averaged GHI times series is tested with respect to a ground based station from the BSRN network. Forecast horizons from 15 min to 1 h provided very promising results validated on a one year ground-based pyranometric data set. The performances have been compared to another similar method from the literature by means of relative metrics. The proposed approach paves the way of the use of satellite-based surface solar irradiance (SSI) estimation as an SSI map nowcasting method that enables to capture spatio-temporal correlation for the improvement of a local SSI forecast.

Nowadays, diverse sensor technologies allow us to
measure different aspects of objects on the Earth surface (spectral
characteristics in hyperspectral (HS) images, height in Light
Detection And Ranging (LiDAR) data, etc), with increasing
spectral and spatial resolutions. Remote sensing images of very
high geometrical resolution can provide a precise and detailed
representation of the monitored scene. Thus, the spatial infor-
mation is fundamental for many applications. Morphological
profiles (MPs) and attribute profiles (APs) have been widely
used to model the spatial information of very high resolution
(VHR) remote sensing images. MPs are obtained by comput-
ing a sequence of morphological operators based on geodesic
reconstruction. However, both morphological operators based
on geodesic reconstruction and attribute filters are connected
filters, and hence suffer the problem of ‘leakage’ (i.e., regions
related to different structures in the image that happen to
be connected by spurious links will be considered as a single
object). Objects expected to disappear at a given stage still
remain present when they are connected with other objects in
the image. As a consequence, the attributes of small objects
will be mixed with their larger connected objects, leading to
poor performances on post-applications (e.g., classification). In
this work, we introduce morphological partial reconstruction
for spatial information modeling of VHR urban remote sensing
images. The ultimate goal of partial reconstruction is to extract
spatial features which better model the attributes of different
objects leading to improved classification performances. These
methods are applied to three datasets with different sensor modalities, resolutions and properties (including panchromatic,
hyperspectral and LiDAR images), and their effectiveness and
robustness are quantitatively and qualitatively evaluated. In
addition, morphological partial reconstruction codes introduced
in this paper have been implemented in a MATLAB toolbox
http://telin.ugent.be/~wliao/Partial Reconstruction that is made
available to the community.

ABSTRACT The estimation of the seismic vulnerability of buildings at an urban scale, a crucial element in any risk assessment, is an expensive, time-consuming, and complicated task, especially in moderate-to-low seismic hazard regions, where the mobilization of resources for the seismic evaluation is reduced, even if the hazard is not negligible. In this paper, we propose a way to perform a quick estimation using convenient, reliable building data that are readily available regionally instead of the information usually required by traditional methods. Using a dataset of existing buildings in Grenoble (France) with an EMS98 vulnerability classification and by means of two different data mining techniques—association rule learning and support vector machine—we developed seismic vulnerability proxies. These were applied to the whole France using basic information from national databases (census information) and data derived from the processing of satellite images and aerial photographs to produce a nationwide vulnerability map. This macroscale method to assess vulnerability is easily applicable in case of a paucity of information regarding the structural characteristics and constructional details of the building stock. The approach was validated with data acquired for the city of Nice, by comparison with the RiskUE method. Finally, damage estimations were compared with historic earthquakes that caused moderate-to-strong damage in France. We show that due to the evolution of vulnerability in cities, the number of seriously damaged buildings can be expected to double or triple if these historic earthquakes were to occur today.

Classification of high-resolution hyperspectral data is investigated. Previously, in classification of high-resolution panchromatic data, simple morphological profiles have been constructed with a repeated use of morphological opening and closing operators with a structuring element of increasing size, starting with the original panchromatic image. This approach has recently been extended for hyperspectral data. In the extension, principal components of the hyperspectral imagery have been computed in order to produce an extended morphological profile. In this paper, we investigate the use of independent components instead of principal components in extended morphological profiles, i.e., selected independent components are used as base images for an extended morphological profile. In the proposed approach, the extended morphological profiles based on the independent components are used as inputs to a neural network classifier. In experiments, a hyperspectral data sets from an urban area in Pavia, Italy is classified.

Image guided interventions have seen growing interest in recent years. The use of X-rays for the procedure impels limiting the dose over time. Image sequences obtained thereby exhibit high levels of noise and very low contrasts. Hence, the development of efficient methods to enable optimal visualization of these sequences is crucial. We propose an original denoising method based on the curvelet transform. First, we apply a recursive temporal filter to the curvelet coefficients. As some residual noise remains, a spatial filtering is performed in the second step, which uses a magnitude-based classification and a contextual comparison of curvelet coefficients. This procedure allows to denoise the sequence while preserving low-contrasted structures, but does not improve their contrast. Finally, a third step is carried out to enhance the features of interest. For this, we propose a line enhancement technique in the curvelet domain. Indeed, thin structures are sparsely represented in that domain, allowing a fast and efficient detection. Quantitative and qualitative evaluations performed on synthetic and real low-dose sequences demonstrate that the proposed method enables a 50% dose reduction.