Centre dedocumentation
scientifique

Super-resolution of Sentinel-2 images : Learning a globally applicable deep neural network / Charis Lanaras in ISPRS Journal of photogrammetry and remote sensing, vol 146 (December 2018)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 146 (December 2018) . - pp 305 - 319 Titre : Super-resolution of Sentinel-2 images : Learning a globally applicable deep neural network Type de document : Article/Communication Auteurs : Charis Lanaras, Auteur ; José Bioucas-Dias, Auteur ; Silvano Galliani, Auteur ; Emmanuel Baltsavias, Auteur ; Konrad Schindler, Auteur Année de publication : 2018 Article en page(s) : pp 305 - 319 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] bande spectrale [Termes descripteurs IGN] échantillonnage de données [Termes descripteurs IGN] erreur moyenne quadratique [Termes descripteurs IGN] image à basse résolution [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] pansharpening (fusion d'images) [Termes descripteurs IGN] pas d'échantillonnage au sol [Termes descripteurs IGN] pouvoir de résolution spectrale [Termes descripteurs IGN] réseau neuronal convolutif Résumé : (Auteur) The Sentinel-2 satellite mission delivers multi-spectral imagery with 13 spectral bands, acquired at three different spatial resolutions. The aim of this research is to super-resolve the lower-resolution (20 m and 60 m Ground Sampling Distance – GSD) bands to 10 m GSD, so as to obtain a complete data cube at the maximal sensor resolution. We employ a state-of-the-art convolutional neural network (CNN) to perform end-to-end upsampling, which is trained with data at lower resolution, i.e., from 40  20 m, respectively 360  60 m GSD. In this way, one has access to a virtually infinite amount of training data, by downsampling real Sentinel-2 images. We use data sampled globally over a wide range of geographical locations, to obtain a network that generalises across different climate zones and land-cover types, and can super-resolve arbitrary Sentinel-2 images without the need of retraining. In quantitative evaluations (at lower scale, where ground truth is available), our network, which we call DSen2, outperforms the best competing approach by almost 50% in RMSE, while better preserving the spectral characteristics. It also delivers visually convincing results at the full 10 m GSD. Numéro de notice : A2018-540 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.09.018 date de publication en ligne : 21/10/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.09.018 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91554 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2018131	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2018133	DEP-EXM	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2018132	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Spatially sensitive statistical shape analysis for pedestrian recognition from LIDAR data / Michalis A. Savelonas in Computer Vision and image understanding, vol 171 (June 2018)  

Public [article]  inComputer Vision and image understanding > vol 171 (June 2018) . - pp 1 - 9 Titre : Spatially sensitive statistical shape analysis for pedestrian recognition from LIDAR data Type de document : Article/Communication Auteurs : Michalis A. Savelonas, Auteur ; Ioannis Pratikakis, Auteur ; Theoharis Theoharis, Auteur ; Georgios Thanellas, Auteur ; et al., Auteur Année de publication : 2018 Article en page(s) : pp 1 - 9 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] analyse de sensibilité [Termes descripteurs IGN] analyse spatiale [Termes descripteurs IGN] classification barycentrique [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] codage [Termes descripteurs IGN] détection de piéton [Termes descripteurs IGN] discrétisation spatiale [Termes descripteurs IGN] distribution de Fisher [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] échantillonnage de données [Termes descripteurs IGN] image à basse résolution [Termes descripteurs IGN] reconnaissance de formes Résumé : (auteur) Range-based pedestrian recognition is instrumental towards the development of autonomous driving and driving assistance systems. This work introduces encoding methods for pedestrian recognition, based on statistical shape analysis of 3D LIDAR data. The proposed approach has two variants, based on the encoding of local shape descriptors either in a spatially agnostic or spatially sensitive fashion. The latter method derives more detailed cues, by enriching the ‘gross’ information reflected by overall statistics of local shape descriptors, with ‘fine-grained’ information reflected by statistics associated with spatial clusters. Experiments on artificial LIDAR datasets, which include challenging samples, as well as on a large scale dataset of real LIDAR data, lead to the conclusion that both variants of the proposed approach (i) obtain high recognition accuracy, (ii) are robust against low-resolution sampling, (iii) are robust against increasing distance, and (iv) are robust against non-standard shapes and poses. On the other hand, the spatially-sensitive variant is more robust against partial occlusion and bad clustering. Numéro de notice : A2018-586 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.cviu.2018.06.001 date de publication en ligne : 15/06/2018 En ligne : https://www.sciencedirect.com/science/article/pii/S1077314218300766 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92439 [article]

Improved geometric modeling of 1960s KH-5 ARGON satellite images for regional Antarctica applications / Wenkai Ye in Photogrammetric Engineering & Remote Sensing, PERS, vol 83 n° 7 (July 2017)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 83 n° 7 (July 2017) . - pp 477 - 491 Titre : Improved geometric modeling of 1960s KH-5 ARGON satellite images for regional Antarctica applications Type de document : Article/Communication Auteurs : Wenkai Ye, Auteur ; Gang Qiao, Auteur ; Fansi Kong, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 477 - 491 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] image satellite historique [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] Antarctique [Termes descripteurs IGN] changement temporel [Termes descripteurs IGN] image à basse résolution [Termes descripteurs IGN] image KH-5 [Termes descripteurs IGN] image satellite [Termes descripteurs IGN] modélisation géométrique de prise de vue [Termes descripteurs IGN] numérisation de photographie [Termes descripteurs IGN] point d'appui Résumé : (auteur) Long-term observations of the Antarctic ice sheet will contribute to a quantitative evaluation and precise prediction of the sea level change induced by global changes in climate. This paper proposes an improved rigorous geometric modeling method for the declassified KH-5 ARGON satellite images collected in Antarctica in 1960s. The scanned film images are preprocessed beforehand to enhance the quality for further analysis. Systematic errors such as lens distortion and atmospheric refraction are also considered and corrected. A scheme is proposed to measure the ground control points for the historical images based on modern image mosaic and DEM products. The bundle adjustment results of four blocks in regions in East Antarctica present a geometric positioning accuracy of less than one nominal pixel resolution (140 m) in both horizontal and vertical directions, outperforming the published results. A regional DEM of the ice sheet that represents the topography in 1963 is then generated from the stereo ARGON images for the first time, the evaluation of which shows its consistency with the modern product but with great value for studying the recent change history of the ice sheet. Numéro de notice : A2017-432 Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.83.7.477 En ligne : https://doi.org/10.14358/PERS.83.7.477 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86336 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2017071	SL	Revue	Centre de documentation	Revues en salle	Disponible

Single Image Super-Resolution based on Neural Networks for text and face recognition / Clément Peyrard (2017)  

Public Titre : Single Image Super-Resolution based on Neural Networks for text and face recognition Type de document : Thèse/HDR Auteurs : Clément Peyrard, Auteur ; Christophe Garcia, Auteur Editeur : Université de Lyon Année de publication : 2017 Autre Editeur : Lyon : Institut National des Sciences Appliquées INSA Lyon Importance : 187 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de Doctorat de l'Université de Lyon opérée au sein de INSA de Lyon, discipline : Informatique Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] artefact [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection de visage [Termes descripteurs IGN] image à basse résolution [Termes descripteurs IGN] image à haute résolution [Termes descripteurs IGN] méthode fondée sur le noyau [Termes descripteurs IGN] reconnaissance automatique [Termes descripteurs IGN] reconnaissance de caractères [Termes descripteurs IGN] reconnaissance de formes Résumé : (auteur) This thesis is focussed on super-resolution (SR) methods for improving automatic recognition system (Optical Character Recognition, face recognition) in realistic contexts. SR methods allow to generate high resolution images from low resolution ones. Unlike upsampling methods such as interpolation, they restore spatial high frequencies and compensate artefacts such as blur or jaggy edges. In particular, example-based approaches learn and model the relationship between low and high resolution spaces via pairs of low and high resolution images. Artificial Neural Networks are among the most efficient systems to address this problem. This work demonstrate the interest of SR methods based on neural networks for improved automatic recognition systems. By adapting the data, it is possible to train such Machine Learning algorithms to produce high-resolution images. Convolutional Neural Networks are especially efficient as they are trained to simultaneously extract relevant non-linear features while learning the mapping between low and high resolution spaces. On document text images, the proposed method improves OCR accuracy by +7.85 points compared with simple interpolation. The creation of an annotated image dataset and the organisation of an international competition (ICDAR2015) highlighted the interest and the relevance of such approaches. Moreover, if a priori knowledge is available, it can be used by a suitable network architecture. For facial images, face features are critical for automatic recognition. A two step method is proposed in which image resolution is first improved, followed by specialised models that focus on the essential features. An off-the-shelf face verification system has its performance improved from +6.91 up to +8.15 points. Finally, to address the variability of real-world low-resolution images, deep neural networks allow to absorb the diversity of the blurring kernels that characterise the low-resolution images. With a single model, high-resolution images are produced with natural image statistics, without any knowledge of the actual observation model of the low-resolution image. Note de contenu : 1- Introduction 2- Definitions and application domains 3- Literature review 4- Text single image super-resolution 5- Face single image super-resolution 6- Blind and robust super-resolution 7- Conclusion Numéro de notice : 25863 Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Discipline : Informatique : Lyon 2017 Organisme de stage : LIRIS En ligne : http://www.theses.fr/2017LYSEI083 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95506

Multiband image fusion based on spectral unmixing / Qi Wei in IEEE Transactions on geoscience and remote sensing, vol 54 n° 12 (December 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 12 (December 2016) . - pp 7236 - 7249 Titre : Multiband image fusion based on spectral unmixing Type de document : Article/Communication Auteurs : Qi Wei, Auteur ; José Bioucas-Dias, Auteur ; Nicolas Dobigeon, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 7236 - 7249 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] analyse des mélanges spectraux [Termes descripteurs IGN] fusion d'images [Termes descripteurs IGN] image à basse résolution [Termes descripteurs IGN] image à haute résolution [Termes descripteurs IGN] image hyperspectrale [Termes descripteurs IGN] image multibande [Termes descripteurs IGN] matrice de covariance Résumé : (Auteur) This paper presents a multiband image fusion algorithm based on unsupervised spectral unmixing for combining a high-spatial-low-spectral-resolution image and a low-spatial-high-spectral-resolution image. The widely used linear observation model (with additive Gaussian noise) is combined with the linear spectral mixture model to form the likelihoods of the observations. The nonnegativity and sum-to-one constraints resulting from the intrinsic physical properties of the abundances are introduced as prior information to regularize this ill-posed problem. The joint fusion and unmixing problem is then formulated as maximizing the joint posterior distribution with respect to the endmember signatures and abundance maps. This optimization problem is attacked with an alternating optimization strategy. The two resulting subproblems are convex and are solved efficiently using the alternating direction method of multipliers. Experiments are conducted for both synthetic and semi-real data. Simulation results show that the proposed unmixing-based fusion scheme improves both the abundance and endmember estimation compared with the state-of-the-art joint fusion and unmixing algorithms. Numéro de notice : A2016-930 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern En ligne : http://dx.doi.org/10.1109/TGRS.2016.2598784 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83344 [article]

Sub-pixel-scale land cover map updating by integrating change detection and sub-pixel mapping / Xiaodong Li in Photogrammetric Engineering & Remote Sensing, PERS, vol 81 n° 1 (January 2015)  

Permalink

Land cover classification of finer resolution remote sensing data integrating temporal features from time series coarser resolution data / Kun Jia in ISPRS Journal of photogrammetry and remote sensing, vol 93 (July 2014)

Permalink

Using thermal time and pixel purity for enhancing biophysical variable time series: An interproduct comparison / Grégory Duveiller in IEEE Transactions on geoscience and remote sensing, vol 51 n° 4 Tome 1 (April 2013)  

Permalink

Semi-automatic quality control of topographic data sets / Petra Helmholz in Photogrammetric Engineering & Remote Sensing, PERS, vol 78 n° 9 (September 2012)  

Permalink

Automatic classification of building types in 3D city models: Using SVMs for semantic enrichment of low resolution building data / A. Henn in Geoinformatica, vol 16 n° 2 (April 2012)  

Permalink

A new pan-sharpening method using multiobjective particle swarm optimization and the shiftable contourlet transform / J. Saeedi in ISPRS Journal of photogrammetry and remote sensing, vol 65 n° 3 (May - June 2011)

Permalink

La télédétection et son application à l'étude de la végétation : quelques principes / Anne Jolly in Rendez-vous techniques, n° 31 (hiver 2011) 

Permalink

L'Afrique prépare son GMES / Françoise de Blomac in SIG la lettre, n° 122 (décembre 2010)

Permalink

Amélioration de la carte d'occupation du sol par la fusion d'images satellitaires multi-échelle : Application au milieu urbain et périurbain de la région / R. Khedam in Revue internationale de géomatique, vol 19 n° 1 (mars – mai 2009)

Permalink

Optimizing the high-pass filter addition technique for image fusion / U.G. Gangkofner in Photogrammetric Engineering & Remote Sensing, PERS, vol 74 n° 9 (September 2008)

Permalink