Centre dedocumentation
scientifique

Multi-objective CNN-based algorithm for SAR despeckling / Sergio Vitale in IEEE Transactions on geoscience and remote sensing, vol 59 n° 11 (November 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 11 (November 2021) . - pp 9336 - 9349 Titre : Multi-objective CNN-based algorithm for SAR despeckling Type de document : Article/Communication Auteurs : Sergio Vitale, Auteur ; Giampaolo Ferraioli, Auteur ; Vito Pascazio, Auteur Année de publication : 2021 Article en page(s) : pp 9336 - 9349 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] apprentissage profond [Termes IGN] chatoiement [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] filtre de déchatoiement [Termes IGN] image radar moirée [Termes IGN] image Radarsat [Termes IGN] restauration d'image Résumé : (auteur) Deep learning (DL) in remote sensing has nowadays become an effective operative tool: it is largely used in applications, such as change detection, image restoration, segmentation, detection, and classification. With reference to the synthetic aperture radar (SAR) domain, the application of DL techniques is not straightforward due to the nontrivial interpretation of SAR images, especially caused by the presence of speckle. Several DL solutions for SAR despeckling have been proposed in the last few years. Most of these solutions focus on the definition of different network architectures with similar cost functions, not involving SAR image properties. In this article, a convolutional neural network (CNN) with a multi-objective cost function taking care of spatial and statistical properties of the SAR image is proposed. This is achieved by the definition of a peculiar loss function obtained by the weighted combination of three different terms. Each of these terms is dedicated mainly to one of the following SAR image characteristics: spatial details, speckle statistical properties, and strong scatterers identification. Their combination allows balancing these effects. Moreover, a specifically designed architecture is proposed to effectively extract distinctive features within the considered framework. Experiments on simulated and real SAR images show the accuracy of the proposed method compared with the state-of-art despeckling algorithms, both from a quantitative and qualitative point of view. The importance of considering such SAR properties in the cost function is crucial for correct noise rejection and details preservation in different underlined scenarios, such as homogeneous, heterogeneous, and extremely heterogeneous. Numéro de notice : A2021-810 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3034852 Date de publication en ligne : 16/11/2020 En ligne : https://doi.org/10.1109/TGRS.2020.3034852 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98874 [article]

Joint estimation of moving target reflectivity and velocity via AT-InSAR systems based on complex interferometric data / Alessandra Budillon in ISPRS Journal of photogrammetry and remote sensing, vol 75 (January 2013)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 75 (January 2013) . - pp 1 - 10 Titre : Joint estimation of moving target reflectivity and velocity via AT-InSAR systems based on complex interferometric data Type de document : Article/Communication Auteurs : Alessandra Budillon, Auteur ; Vito Pascazio, Auteur ; G. Schirinzi, Auteur Année de publication : 2013 Article en page(s) : pp 1 - 10 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] image radar moirée [Termes IGN] interféromètrie par radar à antenne synthétique [Termes IGN] mesurage de phase [Termes IGN] objet mobile [Termes IGN] phase [Termes IGN] réflectivité Résumé : (Auteur) In this paper a technique for the joint estimation of the complex reflectivity and of the radial velocity of ground moving targets, by means of Along-Track Interferometric Synthetic Aperture Radar (AT-InSAR) systems, is presented. It is essentially based on statistical estimation techniques and exploits the complex interferometric SAR images, contrarily to other conventional AT-InSAR methods, which estimate the target radial velocity exploiting only the interferometric phases. The performances of the method are evaluated both for single baseline and for dual-baseline satellite systems, in terms of Cramer Rao Lower Bounds and of Root Mean Square Errors obtained in numerical experiments, with reference to all the target parameters to be estimated, which are the amplitude and phase of the target reflectivity and the target radial velocity. It is shown that for single baseline systems the obtained radial velocity estimation accuracy is comparable with the one achievable with AT-InSAR methods exploiting phase-only data, and is very high for high values of signal to clutter ratio. For dual-baseline systems, instead, the use of amplitude and phase data allows a performance significantly better than the one achievable exploiting phase-only data. Moreover, in the dual baseline case, high velocity estimation accuracy can be obtained also with lower signal to clutter ratios. Numéro de notice : A2013-028 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2012.08.008 En ligne : https://doi.org/10.1016/j.isprsjprs.2012.08.008 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32166 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2013011	RAB	Revue	Centre de documentation	En réserve 3L	Disponible

The effect of modified Markov random fields on the local minima occurrence in microwave imaging / G. Ferraiuolo in IEEE Transactions on geoscience and remote sensing, vol 41 n° 5 (May 2003)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 41 n° 5 (May 2003) . - pp 1043 - 1055 Titre : The effect of modified Markov random fields on the local minima occurrence in microwave imaging Type de document : Article/Communication Auteurs : G. Ferraiuolo, Auteur ; Vito Pascazio, Auteur Année de publication : 2003 Article en page(s) : pp 1043 - 1055 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] champ aléatoire de Markov [Termes IGN] estimation bayesienne [Termes IGN] hyperfréquence [Termes IGN] image satellite [Termes IGN] tomographie Résumé : (Auteur) The application of a maximum a posteriori estimation method for microwave imaging that makes use of a Markov random field (MRF) a priori statistical model is presented in this paper. In particular, the MRF family adopted is generalized for complex profiles, characterized by a quadratic energy function and "modified" such to make it possible to statistically represent spatial interactions between real and imaginary parts. Thanks to its peculiarities, the use of this approach simultaneously favors in many cases well posedness and robustness against local minima occurrence, as well as high quality in the reconstructed images. Numerical results show the performance of the method. Numéro de notice : A2003-204 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2003.811549 En ligne : https://doi.org/10.1109/TGRS.2003.811549 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22500 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-03051	RAB	Revue	Centre de documentation	En réserve 3L	Disponible