Centre de documentation
scientifique

Generating Sentinel-2 all-band 10-m data by sharpening 20/60-m bands: A hierarchical fusion network / Jingan Wu in ISPRS Journal of photogrammetry and remote sensing, vol 196 (February 2023)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 196 (February 2023) . - pp 16 - 31 Titre : Generating Sentinel-2 all-band 10-m data by sharpening 20/60-m bands: A hierarchical fusion network Type de document : Article/Communication Auteurs : Jingan Wu, Auteur ; Liupeng Lin, Auteur ; Chi Zhang, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 16 - 31 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] affinage d'image [Termes IGN] approche hiérarchique [Termes IGN] bande spectrale [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] filtre passe-haut [Termes IGN] fusion d'images [Termes IGN] image à haute résolution [Termes IGN] image Sentinel-MSI Résumé : (Auteur) Earth observations from the Sentinel-2 mission have been extensively accepted in a variety of land services. The thirteen spectral bands of Sentinel-2, however, are collected at three spatial resolutions of 10/20/60 m, and such a difference brings difficulties to analyze multispectral imagery at a uniform resolution. To address this problem, we developed a hierarchical fusion network (HFN) to sharpen 20/60-m bands and generate Sentinel-2 all-band 10-m data. The deep learning architecture is used to learn the complex mapping between multi-resolution input and output data. Given the deficiency of previous studies in which the spatial information is inferred only from the fine-resolution bands, the proposed hierarchical fusion framework simultaneously leverages the self-similarity information from coarse-resolution bands and the spatial structure information from fine-resolution bands, to enhance the sharpening performance. Technically, the coarse-resolution bands are super-resolved by exploiting the information from themselves and then sharpened by fusing with the fine-resolution bands. Both 20-m and 60-m bands can be sharpened via the developed approach. Experimental results regarding visual comparison and quantitative assessment demonstrate that HFN outperforms the other benchmarking models, including pan-sharpening-based, model-based, geostatistical-based, and other deep-learning-based approaches, showing remarkable performance in reproducing explicit spatial details and maintaining original spectral features. Moreover, the developed model works more effectively than the other models over the heterogeneous landscape, which is usually considered a challenging application scenario. To sum up, the fusion model can sharpen Sentinel-2 20/60-m bands, and the created all-band 10-m data allows image analysis and geoscience applications to be authentically carried out at the 10-m resolution. Numéro de notice : A2023-063 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2022.12.017 Date de publication en ligne : 01/01/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.12.017 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102392 [article]

Damage detection using SAR coherence statistical analysis, application to Beirut, Lebanon / Tamer ElGharbawi in ISPRS Journal of photogrammetry and remote sensing, vol 173 (March 2021)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 173 (March 2021) . - pp 1 - 9 Titre : Damage detection using SAR coherence statistical analysis, application to Beirut, Lebanon Type de document : Article/Communication Auteurs : Tamer ElGharbawi, Auteur ; Fawzi Zarzoura, Auteur Année de publication : 2021 Article en page(s) : pp 1 - 9 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] Beyrouth [Termes IGN] corrélation [Termes IGN] décorrélation [Termes IGN] dommage matériel [Termes IGN] étude d'impact [Termes IGN] filtre passe-haut [Termes IGN] image radar moirée [Termes IGN] risque technologique Résumé : (auteur) Early well-coordinated response during unexpected catastrophes can define the near future of the stricken regions. Beirut city, Lebanon, was one of the unfortunate regions to endure the horrific ordeal of an unexpected explosion that caused thousands of human casualties, billions of dollars’ worth of property damage, and destroyed its main maritime entry point. In this paper, we identify damaged regions and classify their severity using a simple and robust SAR correlation technique. We employ phase coherence and amplitude correlation of a SAR stack to estimate pixels’ damage probability using hypothesis testing. We use a spatial phase filter applied in the frequency domain to improve the estimated coherence by removing the spatial decorrelation component of the total estimated coherence. Using this filter improved the coherence of nearly 44.2% of pixels identified with coherence less than 0.25 in our study area. The estimated damaged regions are presented and compared against a damage map issued by Advanced Rapid Imaging and Analysis (ARIA) which shows an average agreement of 68.3%. Also, a fine agreement was observed when compared to optical satellite images. Numéro de notice : A2021-100 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2021.01.00 Date de publication en ligne : 15/01/2021 En ligne : https://doi.org/10.1016/j.isprsjprs.2021.01.001 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96871 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2021031	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2021033	DEP-RECP	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2021032	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Initialization methods of convolutional neural networks for detection of image manipulations / Ivan Castillo Camacho (2021)  

Public Titre : Initialization methods of convolutional neural networks for detection of image manipulations Titre original : Méthodes d'initialisation des réseaux de neurones convolutifs pour la détection des manipulations d'images Type de document : Thèse/HDR Auteurs : Ivan Castillo Camacho, Auteur ; Kai Wang, Directeur de thèse Editeur : Grenoble [France] : Université Grenoble Alpes Année de publication : 2021 Importance : 145 p. Format : 21 x 30 cm Note générale : bibliographie Thèse pour obtenir le grade de Docteur de l'Université Grenoble, spécialité : signal, image, paroles, télécoms Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] altération [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] covariance [Termes IGN] détection d'anomalie [Termes IGN] estompage [Termes IGN] filtre passe-haut [Termes IGN] flux de données [Termes IGN] infraction [Termes IGN] manipulation de données [Termes IGN] qualité des données [Termes IGN] retouche [Termes IGN] variance Index. décimale : THESE Thèses et HDR Résumé : (auteur) Fake images and videos have engulfed mass communication media. This is not something recent, manipulations and forgeries have occurred since the advent of photography itself. These alterations can go from innocent retouches in an attempt to make an image visually attractive to the spread of misleading information or even the use of false media in legal instances. Accordingly, the creation of methods that can help us assure the authenticity of an image presented as non-modified is of paramount importance. In this thesis, we aim at detecting image manipulation operations using deep learning techniques. We present three methods showing the progression of our work under one common objective, i.e, the design and test of Convolutional Neural Network (CNN) initialization methods for image forensic problems with a variance stability focus for the output of a CNN layer.First, we carry out an extensive review of the state of the art in deep-learning-based methods for image forensics. From this review we can confirm that the first layer of a CNN has big impact on the final performance. Specifically, the initialization used on the first-layer filters plays an important role that should be in line with the image forensic task in hand.As our first attempt to address this research problem, we propose a low-complexity initialization method for CNNs. Taking advantage of previous methods designed for the computer vision field, we extend the popular Xavier method to design a filter that would provide variance stability after a convolution operation. This method generates a set of random high-pass filters for the initialization of a CNN's first layer. These filters allow us to better identify forensic traces which usually lie towards the high-frequency part of the image.This first approach constitutes a good staring point of our work. However, a wrong assumption, largely utilized in the research community, was made. This is corrected in our second method where we follow a different data-dependent approach and take into consideration the real statistical properties of natural images. Accordingly, we propose a scaling method for first-layer filters which can cope well with different CNN initialization algorithms. The objective remains in keeping the stability of the variance of data flow in a CNN. We also present theoretical and experimental studies on the output variance for convolutional filter, which are the basis of our proposed data-dependent scaling.Next we describe a revisited version of our first proposal now with a corrected assumption on the statistics of natural images. More precisely, we propose an improved random high-pass initialization method which does not explicitly compute the statistics of input data. We believe that such a ``data-independent'' approach has higher flexibility and broader application range than our second method in situations where the computation of input statistics is not possible.Our proposed methods are tested over several image forensic problems and different CNN architectures.Finally, during all this thesis work we took part in a challenge competition of image forgery detection organized by the French National Research Agency and the French Directorate General of Armaments. We explain in the Appendix the objectives of the challenge along with a brief description of our work conducted for the competition. Note de contenu : 1- Introduction 2- Background knowledge and state of the art 3- Random high-pass initialization 4- Data-dependent initialization 5- Revisiting the random high-pass initialization 6- Conclusions and perspectives Numéro de notice : 28437 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : signal, image, paroles, télécoms : Grenoble : 2021 DOI : sans En ligne : https://hal.science/tel-03346063/ Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98833

fusionImage: An R package for pan‐sharpening images in open source software / Fulgencio Cánovas‐García in Transactions in GIS, Vol 24 n° 5 (October 2020)  

Public [article]  inTransactions in GIS > Vol 24 n° 5 (October 2020) . - pp 1185-1207 Titre : fusionImage: An R package for pan‐sharpening images in open source software Type de document : Article/Communication Auteurs : Fulgencio Cánovas‐García, Auteur ; Paúl Pesántez‐Cobos, Auteur ; Francisco Alonso‐Sarría, Auteur Année de publication : 2020 Article en page(s) : pp 1185-1207 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] algorithme de Gram-Schmidt [Termes IGN] analyse en composantes principales [Termes IGN] filtre passe-haut [Termes IGN] logiciel libre [Termes IGN] pansharpening (fusion d'images) [Termes IGN] pouvoir de résolution géométrique [Termes IGN] R (langage) Résumé : (Auteur) The objective of this article is to evaluate the performance of three pan‐sharpening algorithms (high‐pass filter, principal component analysis and Gram–Schmidt) to increase the spatial resolution of five types of multispectral images and to evaluate the results in terms of color, coherence and spatial sharpness, both qualitatively and quantitatively. A secondary objective is to present an implementation of the aforementioned pan‐sharpening techniques within the open source software R. From a qualitative point of view, pan‐sharpening of images with a high spatial resolution ratio give better results than those whose spatial resolution ratio is 2. According to the quantitative evaluation, there is no pan‐sharpening methodology that obtains optimal results simultaneously for all types of images used. The results of the spectral and spatial ERGAS index vary for four out of the five types of images analyzed. The results show that none of the methods implemented in this work can be considered a priori better than the others. At the same time, this work indicates the importance of both qualitative and quantitative assessment. Numéro de notice : A2020-499 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12676 Date de publication en ligne : 15/09/2020 En ligne : https://doi.org/10.1111/tgis.12676 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96206 [article]

Measuring phase scintillation at different frequencies with conventional GNSS receivers operating at 1 Hz / Viet Khoi Nguyen in Journal of geodesy, vol 93 n°10 (October 2019)  

Public [article]  inJournal of geodesy > vol 93 n°10 (October 2019) Titre : Measuring phase scintillation at different frequencies with conventional GNSS receivers operating at 1 Hz Type de document : Article/Communication Auteurs : Viet Khoi Nguyen, Auteur ; Adria Rovira-Garcia, Auteur ; José Miguel Juan, Auteur ; et al., Auteur Année de publication : 2019 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale [Termes IGN] artefact [Termes IGN] filtre passe-haut [Termes IGN] glissement de cycle [Termes IGN] horloge du récepteur [Termes IGN] ionosphère [Termes IGN] mesurage de phase [Termes IGN] oscillateur [Termes IGN] phase GNSS [Termes IGN] récepteur GNSS [Termes IGN] retard ionosphèrique [Termes IGN] scintillation [Termes IGN] teneur totale en électrons [Termes IGN] zone équatoriale Résumé : (auteur) Ionospheric scintillation causes rapid fluctuations of measurements from Global Navigation Satellite Systems (GNSSs), thus threatening space-based communication and geolocation services. The phenomenon is most intense in equatorial regions, around the equinoxes and in maximum solar cycle conditions. Currently, ionospheric scintillation monitoring receivers (ISMRs) measure scintillation with high-pass filter algorithms involving high sampling rates, e.g. 50 Hz, and highly stable clocks, e.g. an ultra-low-noise Oven-Controlled Crystal Oscillator. The present paper evolves phase scintillation indices implemented in conventional geodetic receivers with sampling rates of 1 Hz and rapidly fluctuating clocks. The method is capable to mitigate ISMR artefacts that contaminate the readings of the state-of-the-art phase scintillation index. Our results agree in more than 99.9% within ± 0.05 rad (2 mm) of the ISMRs, with a data set of 8 days which include periods of moderate and strong scintillation. The discrepancies are clearly identified, being associated with data gaps and to cycle-slips in the carrier-phase tracking of ISMR that occur simultaneously with ionospheric scintillation. The technique opens the door to use huge databases available from the International GNSS Service and other centres for scintillation studies. This involves GNSS measurements from hundreds of worldwide-distributed geodetic receivers over more than one Solar Cycle. This overcomes the current limitations of scintillation studies using ISMRs, as only a few tens of ISMRs are available and their data are provided just for short periods of time. Numéro de notice : A2019-609 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00190-019-01297-z Date de publication en ligne : 01/10/2019 En ligne : https://doi.org/10.1007/s00190-019-01297-z Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94792 [article]

Evaluation of pan-sharpening methods for spatial and spectral quality / Jagalingam Pushparaj in Applied geomatics, vol 9 n° 1 (March 2017)  

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

Automatisation de l'extraction du réseau routier sur cartes JOG digitalisées / Marc Pierrot-Deseilligny (1991)

Permalink

Détermination automatique de rosaces directionnelles à partir de données de télédétection : apports à une étude classique de tectonique régionale (Cévennes) : résultats préliminaires / A. Blusson in Bulletin [Société Française de Photogrammétrie et Télédétection], n° 98 (Avril 1985)

Permalink