Jean-Philippe Ovarlez

The French Aerospace Lab ONERA & SONDRA CentraleSupelec · Electromagnetism and Radar Department

This paper proposes new algorithms for the metric learning problem. We start by noticing that several classical metric learning formulations from the literature can be viewed as modified covariance matrix estimation problems. Leveraging this point of view, a general approach, called Robust Geometric Metric Learning (RGML), is then studied. This met...

Change detection (CD) for remotely sensed images of the Earth has been a popular subject of study in the past decades. With the increase in the number of spatial missions with embedded synthetic aperture radar (SAR) sensors, the amount of readily available observations has now reached the "big data" era. This chapter introduces several families of...

The Doppler signature of a man walking in a forested area analysed at L-band is presented here. The aim is twofold: to assess the best time-frequency distribution to characterise the activity; to highlight the similarity of the simulated data to the measured ones to validate the simulation tool. Indeed, the Doppler-Time (DT) signal variation repres...

This paper studies a statistical model for heteroscedastic (i.e., power fluctuating) signals embedded in white Gaussian noise. Using the Riemannian geometry theory, we propose an unified approach to tackle several problems related to this model. The first axis of contribution concerns parameters (signal subspace and power factors) estimation, for w...

Measurements of the Doppler signature in UHF-band of a human moving in outdoor sites are presented in this paper. A radar campaign has been carried out, observing a subject walking and running outside, near and within a forest. A bistatic radar has been employed working in continuous wave (CW) at 1 GHz and 435 MHz. The spectrograms acquired in VV p...

The contributions of this paper are twofold. First, we show the potential interest of Complex-Valued Neural Network (CVNN) on classification tasks for complex-valued datasets. To highlight this assertion, we investigate an example of complex-valued data in which the real and imaginary parts are statistically dependent through the property of non-ci...

This paper derives a new change detector for multivariate Synthetic Aperture Radar image time series. Classical statistical change detection methodologies based on covariance matrix analysis are usually built upon the Gaussian assumption, as well as an unstructured signal model. Both of these hypotheses may be inaccurate for high-dimension/resoluti...

This paper presents how the use of a cleaned and robust covariance matrix estimate can improve significantly the overall performance of Maximum Variety and Minimum Variance portfolios. We assume that the asset returns are modelled through a multi-factor model where the error term is a multivariate and correlated elliptical symmetric noise extending...

In this technical report, we explain how our proposed sparse and low-rank matrix decomposition method for hyperspectral target detection, provided in our work «Automatic Target Detection for Sparse Hyperspectral Images», can be extended to the lq norm (0 < q ≤ 1). Since the use of the l1 norm is still too far away from the ideal l0 norm, many non-c...

This paper presents how the most recent improvements made on covariance matrix estimation and model order selection can be applied to the portfolio optimization problem. Our study is based on the case of the Maximum Variety Portfolio and may be obviously extended to other classical frameworks with analogous results. We focus on the fact that the as...

This paper considers the problem of detecting changes in multivariate Synthetic Aperture Radar image time series. Classical methodologies based on covariance matrix analysis are usually built upon the Gaussian assumption, as well as an unstructured signal model. Both of these hypotheses may be inaccurate for high-dimension/resolution images, where...

This paper presents how the most recent improvements made on covariance matrix estimation and model order selection can be applied to the portfolio optimization problem. Our study is based on the case of the Maximum Variety Portfolio and may be obviously extended to other classical frameworks with analogous results. We focus on the fact that the as...

Ce papier considère la détection de changements dans une série temporelle d'images multivariées obtenues par radar à synthèse d'ouverture. Dans ce cadre les méthodologies classiques modélisent les données par une distribution gaussienne à moyenne nulle et une covariance non structurée. Ces deux hypothèses montrent leur limite lorsque les données so...

A preliminary Doppler analysis on a man walking in free space at 1 GHz is presented in the paper. Firstly, the backscattered response of the moving target has been provided by a simulation tool based on physical optics (PO) theory. Then, a short-time Fourier transform (STFT), a reassignment spectrogram (RE-Spect) and a Wigner-Ville distribution (WV...

This paper presents how the most recent improvements made on covariance matrix estimation and model order selection can be applied to the portfolio optimisation problem. The particular case of the Maximum Variety Portfolio is treated but the same improvements apply also in the other optimisation problems such as the Minimum Variance Portfolio. We a...

This paper considers the problem of detecting changes in mul-tivariate Synthetic Aperture Radar image time series. Classical methodologies based on covariance matrix analysis are usually built upon the Gaussian assumption, as well as an unstructured signal model. Both of these hypotheses may be inaccurate for high-dimension/resolution images, where...

In this work, a novel target detector for hyperspectral imagery is developed. The detector is independent on the unknown covariance matrix, behaves well in large dimensions, distributional free, invariant to atmospheric effects, and does not require a background dictionary to be constructed. Based on a modification of the Robust Principal Component...

In this work, a novel target detector for hyperspectral imagery is developed. The detector is independent on the unknown covariance matrix, behaves well in large dimensions, distributional free, invariant to atmospheric effects, and does not require a background dictionary to be constructed. Based on a modification of the Robust Principal Component...

In this work, a novel target detector for hyperspectral imagery is developed. The detector is independent on the unknown covariance matrix, behaves well in large dimensions, distributional free, invariant to atmospheric effects, and does not require a background dictionary to be constructed. Based on a modification of the Robust Principal Component...

A growing problem in the remote sensing community concerns the estimation of change-points in a time series of Synthetic Aperture Radar (SAR) images. Although the methodologies of change-point estimation have already been investigated in the literature, there are, to the best of our knowledge, no study on the expected performance for the estimation...

Given a target prior information, our goal is to propose a method for automatically separating targets of interests from the background in hyperspectral imagery. More precisely, we regard the given hyperspectral image (HSI) as being made up of the sum of low-rank background HSI and a sparse target HSI that contains the targets based on a pre-learne...

This paper explores the problem of change detection in time series of heterogeneous multivariate synthetic aperture radar images. Classical change detection schemes have modelled the data as a realisation of Gaussian random vectors and have derived statistical tests under this assumption. However, when considering high-resolution images, the hetero...

High resolution in synthetic aperture radar (SAR) leads to new physical characterizations of scatterers which are anisotropic and dispersive. These behaviors present an interesting source of diversity for target detection schemes. Unfortunately, such characteristics have been integrated and have been naturally lost in monovariate single-look SAR im...

This paper presents how the most recent improvements made on covariance matrix estimation and model order selection can be applied to the portfolio optimisation problem. The particular case of the Maximum Variety Portfolio is treated but the same improvements apply also in the other optimisation problems such as the Minimum Variance Portfolio. We a...

It is a better version than to that submitted on HAL or present in the library at CentraleSupélec. I suggest you to read this version.

C'est une meilleure version que celle présente sur HAL et au sein de la bibliothèque de l'établissement de soutenance ... Je vous suggère alors de lire cette version.

In this paper, we study the problem of detecting and estimating change-points in a time series of multivariate images. We extend existent works to take into account the heterogeneity of the dataset on a spatial neighborhood. The classic complex Gaussian assumption of the data is replaced by a complex elliptically symmetric assumption. Then robust s...

In this paper, we propose new detectors for Change Detection between two multivariate images. The data is supposed to follow a Compound Gaussian distribution. By using Likelihood Ratio Test (LRT) and Generalised LRT (GLRT) approaches, we derive our detectors. The CFAR behaviour has been studied and the simulations show that they outperform the clas...

This paper deals with the optimization a sequence and its associated mismatched filter. This question has already been addressed in the literature, by alternatively solving two minimizations problem, one per sequence, meaning that the optimization is never performed on both sequences at the same time. So, this article introduces some methods in ord...

In this paper, we propose new detectors for Change Detection between two multivariate images. The data is supposed to follow a Compound Gaussian distribution. By using Likelihood Ratio Test (LRT) and Generalised LRT (GLRT) approaches, we derive our detectors. The CFAR behaviour has been studied and the simulations show that they outperform the clas...

This paper presents a new algorithm to estimate the number of sources embedded in a correlated Complex Elliptically Distributed (CES) noise in the context of large dimensional regime. The proposed method is a two-steps ones: first the data covariance matrix is estimated with a robust and consistent estimator exploiting the Toeplitz structure assump...

In this paper, we propose a method for separating known targets of interests from the background in hyperspectral imagery. More precisely, we regard the given hyperspectral image (HSI) as being made up of the sum of low-rank background HSI and a sparse target HSI that contains the known targets based on a pre-learned target dictionary specified by...

One of the most general and acknowledged models for background statistics characterization is the family of elliptically symmetric distributions. They account for heterogeneity and non-Gaussianity of real data. Today, although non-Gaussian models are assumed for background modeling and detectors design, the parameters estimation is usually performe...

Estimating large covariance matrices has been a long-standing important problem in many applications and has attracted increased attention over several decades. This paper deals with two methods based on pre-existing works to impose sparsity on the covariance matrix via its unit lower triangular matrix (aka Cholesky factor) T. The first method serv...

Estimating large covariance matrices has been a longstanding important problem in many applications and has attracted increased attention over several decades. This paper deals with two methods based on pre-existing works to impose sparsity on the covariance matrix via its unit lower triangular matrix (aka Cholesky factor) $\mathbf{T}$. The first m...

This paper deals with model order selection in context of correlated noise. More precisely, one considers sources embedded in an additive Complex Elliptically Symmetric (CES) noise, with unknown parameters. The main difficultly for estimating the model order lies into the noise correlation, namely the scatter matrix of the corresponding CES distrib...

Deux strat´egies de parcimonie sont proposées et appliquées sur la matrice de covariance à travers sa matrice unitaire triangulaire inférieure (ou facteur de Cholesky) T. La première permet d’abord d’estimer les entrées de T par la méthode des moindres carrés ordinaires (Ordinary Least Squares (OLS)), et ensuite introduire de la parcimonie en profi...

Nous proposons, dans ce papier, une nouvelle méthodologie pour la Détection de Changement entre deux images SAR monovarié. Des outils d'analyse Temps-Fréquence Linéaire sont utilisés pour obtenir une diversité spectrale et angulaire. Cette diversité est utilisée dans uneprobì eme de détection sur vecteurs multivariés et le détecteur obtenu affiche...

Détection de changement pour des images SAR très haute résolution

In this paper, we propose a novel methodology for Change Detection between two monovariate complex SAR images. Linear Time-Frequency tools are used in order to recover a spectral and angular diversity of the scatterers present in the scene. This diversity is used in bi-date change detection framework to develop a detector, whose performances are be...

In this paper, a simultaneous sparsity representation-based binary hypothesis (S-SRBBH) model for target detection in hyperspectral image (HSI) is proposed. The S-SRBBH exploits the interpixel correlation within neighboring pixels in HSI, and then, each test pixel is represented by only the background dictionary (A b) under null hypothesis or from...

Usually, in radar imaging, the scatterers are supposed to respond the same way regardless of the angle from which they are viewed and have the same properties within the emitted spectral bandwidth. Nevertheless, new capacities in SAR imaging (large bandwidth, large angular extent) make this assumption obsolete. An original application of the Linear...

Classical target detection schemes are usually obtained by deriving the likelihood ratio under Gaussian hypothesis and replacing the unknown background parameters by their estimates. In most applications, interference signals are assumed to be Gaussian with zero mean [or with a known mean vector (MV)] and with an unknown covariance matrix (CM). Whe...