Search results for "PATT"
showing 10 items of 4353 documents
Convolutional Neural Networks for Cloud Screening: Transfer Learning from Landsat-8 to Proba-V
2018
Cloud detection is a key issue for exploiting the information from Earth observation satellites multispectral sensors. For Proba-V, cloud detection is challenging due to the limited number of spectral bands. Advanced machine learning methods, such as convolutional neural networks (CNN), have shown to work well on this problem provided enough labeled data. However, simultaneous collocated information about the presence of clouds is usually not available or requires a great amount of manual labor. In this work, we propose to learn from the available Landsat −8 cloud masks datasets and transfer this learning to solve the Proba-V cloud detection problem. CNN are trained with Landsat images adap…
Tree Species Classification of Drone Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks
2020
Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include the detection of individual trees, tree species classification, biomass estimation, etc. Deep neural networks (DNN) have shown superior results when comparing with conventional machine learning methods such as multi-layer perceptron (MLP) in cases of huge input data. The objective of this research is to investigate 3D convolutional neural networks (3D-CNN) to classify three major tree species in a boreal forest: pine, spruce, and birch. The proposed 3D-CNN models were emp…
Estimating Missing Information by Cluster Analysis and Normalized Convolution
2018
International audience; Smart city deals with the improvement of their citizens' quality of life. Numerous ad-hoc sensors need to be deployed to know humans' activities as well as the conditions in which these actions take place. Even if these sensors are cheaper and cheaper, their installation and maintenance cost increases rapidly with their number. We propose a methodology to limit the number of sensors to deploy by using a standard clustering technique and the normalized convolution to estimate environmental information whereas sensors are actually missing. In spite of its simplicity, our methodology lets us provide accurate assesses.
Stochastic Galerkin method for cloud simulation
2018
AbstractWe develop a stochastic Galerkin method for a coupled Navier-Stokes-cloud system that models dynamics of warm clouds. Our goal is to explicitly describe the evolution of uncertainties that arise due to unknown input data, such as model parameters and initial or boundary conditions. The developed stochastic Galerkin method combines the space-time approximation obtained by a suitable finite volume method with a spectral-type approximation based on the generalized polynomial chaos expansion in the stochastic space. The resulting numerical scheme yields a second-order accurate approximation in both space and time and exponential convergence in the stochastic space. Our numerical results…
SVM-based classification of High resolution Urban Satellites Images using Dense SURF and Spectral Information
2018
Remote-sensing focusing on image classification knows a large progress and receives the attention of the remote-sensing community day by day. Combining many kinds of extracted features has been successfully applied to High resolution urban satellite images using support vector machine (SVM). In this paper, we present a methodology that is promoting a performed classification by using pixel-wise SURF description features combined with spectral information in Cielab space for the first time on common scenes of urban imagery. The proposed method gives a promising classification accuracy when compared with the two types of features used separately.
SAR Image Classification Combining Structural and Statistical Methods
2011
The main objective of this paper is to develop a new technique of SAR image classification. This technique combines structural parameters, including the Sill, the slope, the fractal dimension and the range, with statistical methods in a supervised image classification. Thanks to the range parameter, we define the suitable size of the image window used in the proposed approach of supervised image classification. This approach is based on a new way of characterising different classes identified on the image. The first step consists in determining relevant area of interest. The second step consists in characterising each area identified, by a matrix. The last step consists in automating the pr…
Climate indices for the Baltic states from principal component analysis
2017
Abstract. We used principal component analysis (PCA) to derive climate indices that describe the main spatial features of the climate in the Baltic states (Estonia, Latvia, and Lithuania). Monthly mean temperature and total precipitation values derived from the ensemble of bias-corrected regional climate models (RCMs) were used. Principal components were derived for the years 1961–1990. The first three components describe 92 % of the variance in the initial data and were chosen as climate indices in further analysis. Spatial patterns of these indices and their correlation with the initial variables were analyzed, and it was detected (based on correlation coefficient between principal compon…
Spectral alignment of multi-temporal cross-sensor images with automated kernel canonical correlation analysis
2015
In this paper we present an approach to perform relative spectral alignment between optical cross-sensor acquisitions. The proposed method aims at projecting the images from two different and possibly disjoint input spaces into a common latent space, in which standard change detection algorithms can be applied. The system relies on the regularized kernel canonical correlation analysis transformation (kCCA), which can accommodate nonlinear dependencies between pixels by means of kernel functions. To learn the projections, the method employs a subset of samples belonging to the unchanged areas or to uninteresting radiometric differences. Since the availability of ground truth information to p…
Exploiting Maximum Entropy method and ASTER data for assessing debris flow and debris slide susceptibility for the Giampilieri catchment (north-easte…
2016
This study aims at evaluating the performance of the Maximum Entropy method in assessing landslide susceptibility, exploiting topographic and multispectral remote sensing predictors. We selected the catchment of the Giampilieri stream, which is located in the north-eastern sector of Sicily (southern Italy), as test site. On 1 October 2009, a storm rainfall triggered in this area hundreds of debris flow/avalanche phenomena causing extensive economical damage and loss of life. Within this area a presence-only-based statistical method was applied to obtain susceptibility models capable of distinguishing future activation sites of debris flow and debris slide, which where the main source of fai…
Hyperspectral dimensionality reduction for biophysical variable statistical retrieval
2017
Abstract Current and upcoming airborne and spaceborne imaging spectrometers lead to vast hyperspectral data streams. This scenario calls for automated and optimized spectral dimensionality reduction techniques to enable fast and efficient hyperspectral data processing, such as inferring vegetation properties. In preparation of next generation biophysical variable retrieval methods applicable to hyperspectral data, we present the evaluation of 11 dimensionality reduction (DR) methods in combination with advanced machine learning regression algorithms (MLRAs) for statistical variable retrieval. Two unique hyperspectral datasets were analyzed on the predictive power of DR + MLRA methods to ret…