Olivier D'Hondt

In this paper, we provide the first in-depth evaluation of exploiting Tomographic Synthetic Aperture Radar (TomoSAR) for the task of supervised land-cover classification. Our main contribution is the design of specific TomoSAR features to reach this objective. In particular, we show that classification based on TomoSAR significantly outperforms Pol...

In this paper, we introduce two spatially adaptive filtering methods to improve the estimation of the covariance matrix (CM), which is required for the processing of tomographic SAR data. We evaluate their effect on scatterer separation and height estimation. We propose several criteria to evaluate such methods and introduce a spatial simulation pr...

TomoSAR (Tomographic SAR) is a technique that allows to extend Synthetic Aperture Radar (SAR) imaging to the third dimension by using several images of a scene acquired from different sensor positions. 3D point clouds extracted thanks to tomographic processing methods are often corrupted by noise and artifacts which need to be corrected. In this pa...

In this paper, we introduce a method to detect and reconstruct building parts from tomographic Synthetic Aperture Radar (SAR) airborne data. Our approach extends recent works in two ways: first, the radiometric information is used to guide the extraction of geometric primitives. Second, building facades and roofs are extracted thanks to geometric c...

This paper deals with spatial analysis of texture in synthetic aperture radar (SAR) images. A new parametric model for local two-point statistics of the image is introduced, in order to characterize the spatially nonstationary and anisotropic behavior of the image. The texture is first modeled by a nonstationary Gaussian process resulting from the...

Most of the world’s 1500 active volcanoes are not instrumentally monitored, resulting in deadly eruptions which can occur without observation of precursory activity. The new Sentinel missions are now providing freely available imagery with unprecedented spatial and temporal resolutions, with payloads allowing for a comprehensive monitoring of volca...

Learning the proxy task of transcoding SAR images into optical images forces an employed conditional generative adversarial network (GAN) to distinguish between different land surfaces. Such a network can then be used to build a classifier with significantly fewer free parameters that generalizes well even when trained on a very small amount of lab...

Satellite-borne Synthetic Aperture Radar (SAR) has been used for characterizing and mapping in two relevant ice-free areas in the South Shetland Islands. The objective has been to identify and characterize land surface covers that mainly include periglacial and glacial landforms, using fully polarimetric SAR C band RADARSAT-2 data, on Fildes Penins...

In this paper, we introduce a method to detect and reconstruct building parts from tomographic Synthetic Aperture Radar (SAR) airborne data. Our approach extends recent works in two ways: first, the radiometric information is used to guide the extraction of geometric primitives. Second, building facades and roofs are extracted thanks to geometric c...

This work proposes to evaluate the effects of a spatially adaptive filter called NDSAR-BLF (N-Dimensional SAR Bilateral Filter) on scatterer separation and height estimation from SAR tomograms. We have developed a spatial simulation procedure allowing to generate a tomographic image stack from a simple 3D building model, assuming a multi-track airb...

In this paper, we describe a new approach to analyse and quantify land surface covers on Deception Island, a volcanic island located in the Northern Antarctic Peninsula region by means of fully polarimetric RADARSAT-2 (C-Band) SAR image. Data have been filtered by a new polarimetric speckle filter (PolSAR-BLF) that is based on the bilateral filter....

In this paper, we introduce an automatic parameter selection technique for the polarimetric bilateral filter. The method is inspired by the theory of unbiased risk estimation that allows to compare different estimators with respect to a loss function. Moreover, a local risk estimation allows spatially varying parameters. We demonstrate our approach...

This paper describes the analysis of complex scenario of urban area by means of a reduced number of tomographic SAR data. First, the tomographic data are processed using the standard MUSIC algorithm, which requires an estimation of the data covariance matrix and an estimation of number of sources. We introduce the tomographic bilateral filter (To-m...

In this paper, we present a set of tools developed during the creation of a platform that allows the automatic generation of virtual views in a live soccer game production. Observing the scene through a multi-camera system, a 3D approximation of the players is computed and used for the synthesis of virtual views. The system is suitable both for sta...

In this paper, we introduce an iterative speckle filtering method for polarimetric SAR (PolSAR) images based on the bilateral filter. To locally adapt to the spatial structure of images, this filter relies on pixel similarities in both spatial and radiometric domains. To deal with polarimetric data, we study the use of similarities based on a stati...

In this paper we propose to study the potential of jointly using polarimetric and tomographic SAR data to recognize and localize buildings in complex scenarios. We present extraction methods for both polarimetric and tomographic features. One the one hand, we propose to use the polarimetric bilateral filter that has proved to be a powerful tool to...

This paper describes the characterization of buildings using fully polarimetric tomographic SAR data at L-Band. This analysis is performed in three steps. Polarimetric tomographic data are first processed using the high resolution spectral estimator MUSIC (FP-MUSIC-1), assuming 1 scatterer. Then, points of interest are extracted using a novel signa...

In this paper we propose a method that performs an automatic extraction of geometric primitives from tomographic SAR data. This technique allows to identify surfaces by assuming they can be locally described by a piecewise planar model. It is therefore suitable to reconstruct man-made structures in urban areas. Our approach takes advantage of the s...

In this paper we introduce a method that allows automatic extraction of planar features from tomographic SAR data. Our approach takes advantage of the spatial connectivity of pixels from tomographic height maps in order to retrieve planar patches from noise corrupted complex scenes. We demonstrate how our method outperforms the well-known RANSAC al...

In this paper we propose a new speckle filter for polarimetric SAR data based on the bilateral filter. We also study the use of Riemannian metrics related to the Hermitian nature of the complex covariance matrices. The approach is validated over synthetic and experimental data. The method achieves a strong smoothing in homogeneous areas while prese...

In this paper we present a SAR tomographic post-processing technique to extract point of interest from SAR tomograms. We propose a signal-to-noise index adapted to tomogram generated by SP-MUSIC-1 (single polarization, assuming 1 scatterer) that quantifies the separation of scatterer peak from other artifacts (noise,...). This index allows to remov...

We present a method to compute the relative depth of moving objects in video sequences. The method relies on the fact that the boundary between two moving objects follows the movement of the object which is closest to the camera. Thus, the input of the method is a segmentation (to know the boundaries of objects) and an optical flow (to know the mov...

In this paper we introduce an unsupervised scheme for the segmentation of motion layers in video sequences. The number of layers is automatically determined by the method. Our approach first extracts the motion models thanks to a RANSAC-based random sampling algorithm improved by the use of geodesic distance information. Then those models are assig...

Video inpainting consists in recovering the missing or corrupted parts of an image sequence so that the reconstructed sequence looks natural. For each frame, the reconstruction has to be spatially coherent with the rest of the image and temporally with respect to the reconstructions of adjacent frames. There have been many methods proposed in the r...

In this paper, we present a set of tools developed during the creation of a platform that allows the automatic generation of virtual views in a live soccer game production. Observing the scene through a multi-camera system, a 3D approximation of the players is computed and used for the synthesis of virtual views. The system is suitable both for sta...

This paper deals with the validation of a previously developed texture model for SAR data as well as its associated parameter estimation algorithm. The mentioned model is named the Anisotropic Gaussian Kernel (AGK) model and allows the description of the possibly nonstationary and anisotropic behaviour of texture on heterogeneous areas of SAR image...

This letter proposes a new model for the second-order statistics of spatial texture in synthetic aperture radar images. The autocovariance function is locally approximated by a two-dimensional anisotropic Gaussian kernel (AGK) to characterize texture by its local orientation and anisotropy. The estimation of texture parameters at a given scale is b...

In this paper, the analysis of spatially nonstationary texture from polarimetric SAR data is studied. A previously introduced model named Anisotropic Gaussian Kernel (AGK) was shown to be a pertinent descriptor of local orientation and allowed a simple representation of the complex spatial structure in SAR images. Here, two methods for the estimati...

This work deals with the analysis and characterization of nonstationary spatial texture in SAR images. Most studies considering texture in SAR images are using stationary statistics and spatial isotropy hypotheses. However, visual observation of data shows that dominant orientations may appear in the image. Moreover, measures of autocorrelation at...

Ce travail porte sur l'analyse et la caractérisation de la texture spatiale non stationnaire dans les images SAR. La plupart des études considérant la texture dans les images SAR utilisent les hypothèses de stationnarité statistique et d'isotropie spatiale. Cependant, l'observation des images montre que des orientations spatiales privilégiées peuv...

This paper proposes a new model for the two-point statistics of spatial texture in SAR images. The autocovariance function is locally approximated by a 2-D anisotropic Gaussian kernel (AGK) in order to characterise texture by its local orientation and anisotropy. The estimation of texture parameters at a given scale is based on the gradient structu...

·Cet article propose un nouveau modèle pour les statistiques d'ordre deux de la texture spatiale dans les images SAR. La fonction d'auto-covariance est approximée localement par un noyau gaussien anisotrope (AGK) 2-D dans le but de décrire la texture en termes d'orientation et d'anisotropie locales. L'estimation des paramètres de la texture à une é...

First Page of the Article

In this paper we present two methods to estimate the local orientation of spatial texture in polarimetric SAR data. The first approach is based on an original spatial parametric modelling of the 2D autocorrelation function, and was introduced in a previous paper. The second method is based on orientation interpolation between a reduced set of basis...