Centre de documentation
scientifique

HyperNet: A deep network for hyperspectral, multispectral, and panchromatic image fusion / Kun Li in ISPRS Journal of photogrammetry and remote sensing, vol 188 (June 2022)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 188 (June 2022) . - pp 30 - 44 Titre : HyperNet: A deep network for hyperspectral, multispectral, and panchromatic image fusion Type de document : Article/Communication Auteurs : Kun Li, Auteur ; Wei Zhang, Auteur ; Dian Yu, Auteur ; Xin Tian, Auteur Année de publication : 2022 Article en page(s) : pp 30 - 44 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] fusion d'images [Termes IGN] image à haute résolution [Termes IGN] image floue [Termes IGN] image hyperspectrale [Termes IGN] image multibande [Termes IGN] image panchromatique [Termes IGN] pansharpening (fusion d'images) [Termes IGN] réseau neuronal profond Résumé : (Auteur) Traditional approaches mainly fuse a hyperspectral image (HSI) with a high-resolution multispectral image (MSI) to improve the spatial resolution of the HSI. However, such improvement in the spatial resolution of HSIs is still limited because the spatial resolution of MSIs remains low. To further improve the spatial resolution of HSIs, we propose HyperNet, a deep network for the fusion of HSI, MSI, and panchromatic image (PAN), which effectively injects the spatial details of an MSI and a PAN into an HSI while preserving the spectral information of the HSI. Thus, we design HyperNet on the basis of a uniform fusion strategy to solve the problem of complex fusion of three types of sources (i.e., HSI, MSI, and PAN). In particular, the spatial details of the MSI and the PAN are extracted by multiple specially designed multiscale-attention-enhance blocks in which multi-scale convolution is used to adaptively extract features from different reception fields, and two attention mechanisms are adopted to enhance the representation capability of features along the spectral and spatial dimensions, respectively. Through the capability of feature reuse and interaction in a specially designed dense-detail-insertion block, the previously extracted features are subsequently injected into the HSI according to the unidirectional feature propagation among the layers of dense connection. Finally, we construct an efficient loss function by integrating the multi-scale structural similarity index with the norm, which drives HyperNet to generate high-quality results with a good balance between spatial and spectral qualities. Extensive experiments on simulated and real data sets qualitatively and quantitatively demonstrate the superiority of HyperNet over other state-of-the-art methods. Numéro de notice : A2022-272 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2022.04.001 Date de publication en ligne : 07/04/2022 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.04.001 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100461 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2022061	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2022063	DEP-RECP	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2022062	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Unsupervised multi-view CNN for salient view selection and 3D interest point detection / Ran Song in International journal of computer vision, vol 130 n° 5 (May 2022)  

Public [article]  inInternational journal of computer vision > vol 130 n° 5 (May 2022) . - pp 1210 - 1227 Titre : Unsupervised multi-view CNN for salient view selection and 3D interest point detection Type de document : Article/Communication Auteurs : Ran Song, Auteur ; Wei Zhang, Auteur ; Yitian Zhao, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 1210 - 1227 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] classification non dirigée [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection d'objet [Termes IGN] objet 3D [Termes IGN] point d'intérêt [Termes IGN] saillance Résumé : (auteur) We present an unsupervised 3D deep learning framework based on a ubiquitously true proposition named by us view-object consistency as it states that a 3D object and its projected 2D views always belong to the same object class. To validate its effectiveness, we design a multi-view CNN instantiating it for salient view selection and interest point detection of 3D objects, which quintessentially cannot be handled by supervised learning due to the difficulty of collecting sufficient and consistent training data. Our unsupervised multi-view CNN, namely UMVCNN, branches off two channels which encode the knowledge within each 2D view and the 3D object respectively and also exploits both intra-view and inter-view knowledge of the object. It ends with a new loss layer which formulates the view-object consistency by impelling the two channels to generate consistent classification outcomes. The UMVCNN is then integrated with a global distinction adjustment scheme to incorporate global cues into salient view selection. We evaluate our method for salient view section both qualitatively and quantitatively, demonstrating its superiority over several state-of-the-art methods. In addition, we showcase that our method can be used to select salient views of 3D scenes containing multiple objects. We also develop a method based on the UMVCNN for 3D interest point detection and conduct comparative evaluations on a publicly available benchmark, which shows that the UMVCNN is amenable to different 3D shape understanding tasks. Numéro de notice : A2022-415 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s11263-022-01592-x Date de publication en ligne : 16/03/2022 En ligne : https://doi.org/10.1007/s11263-022-01592-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100771 [article]

GPS satellite differential code bias estimation with current eleven low earth orbit satellites / Xingxing Li in Journal of geodesy, vol 95 n° 7 (July 2021)  

Public [article]  inJournal of geodesy > vol 95 n° 7 (July 2021) . - n° 76 Titre : GPS satellite differential code bias estimation with current eleven low earth orbit satellites Type de document : Article/Communication Auteurs : Xingxing Li, Auteur ; Wei Zhang, Auteur ; Keke Zhang, Auteur Année de publication : 2021 Article en page(s) : n° 76 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale [Termes IGN] erreur systématique de code différentiel [Termes IGN] orbite basse [Termes IGN] précision de l'estimation [Termes IGN] récepteur GPS [Termes IGN] teneur verticale totale en électrons [Termes IGN] trajet multiple Résumé : (auteur) Many low earth orbit (LEO) missions have been launched recently for different geoscience studying purposes such as ionosphere detecting and gravity recovering. The onboard observations from LEO satellites provide us a great opportunity to estimate the differential code bias (DCB) which is vital for precise applications of global navigation satellites system. This paper mainly focuses on the contribution of multi-LEO combination to the DCB estimation using onboard data collected by current eleven LEO satellites from day of year (DOY) 061, 2018 to DOY 120, 2018. The single-LEO solutions with different LEO and multi-LEO solutions with different LEO subsets are compared and analyzed in detail to fully exploit the potential of LEO onboard observations in the DCB estimation. We also evaluate and discuss the vertical total electron content (VTEC) results and posterior residuals to validate the estimation accuracy. Our results show that the average DCB standard deviation (STD) values are within 0.140 ns for all eleven single-LEO solutions with the best stability of 0.082 ns for Swarm-B solution. The evaluation of multi-LEO solutions indicates that with the increase in LEO satellites, the GPS DCB stability gets improved gradually. The 9-LEO solution can achieve the stability with STD value of 0.051 ns, better than that of DCB products from the German Aerospace Center (DLR) (0.055 ns) but slightly worse than that of DCB products from the Chinese Academy of Sciences (CAS) (0.048 ns). The results suggest that the GPS DCB stability based on the onboard observations of nine LEO satellites can be comparable to the ground-based solution derived from a global ground network with hundreds of stations. The LEO space-borne receiver DCB results illustrate that the inclusion of more LEO satellites can contribute to the stability improvement of receiver DCB. In addition, the VTEC estimation can benefit from the joint processing of multiple LEO observations and achieves a noticeable reduction in the percentage of negative VTEC values. Our results also reveal that the spherical symmetry ionosphere assumption might cause accuracy degradation in the DCB estimation at low latitudes. Numéro de notice : A2021-517 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s00190-021-01536-2 Date de publication en ligne : 22/06/2021 En ligne : https://doi.org/10.1007/s00190-021-01536-2 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97939 [article]

Ionospheric modeling using GPS: Greater fidelity using a 3D approach / Wei Zhang in GPS world, vol 25 n° 2 (February 2014)

Public [article]  inGPS world > vol 25 n° 2 (February 2014) . - pp 59 - 65 Titre : Ionospheric modeling using GPS: Greater fidelity using a 3D approach Type de document : Article/Communication Auteurs : Wei Zhang, Auteur ; Attila Komjathy, Auteur ; Simon Banville, Auteur ; Richard B. Langley, Auteur Année de publication : 2014 Article en page(s) : pp 59 - 65 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement du signal [Termes IGN] données localisées 3D [Termes IGN] fonction orthogonale [Termes IGN] modèle ionosphérique [Termes IGN] signal GPS [Termes IGN] temps réel Résumé : (Auteur) In this month's column, we look at the performance of this 3D approach to modeling the ionosphere including times when the ionosphere is particularly interesting. Numéro de notice : A2014-096 Affiliation des auteurs : non IGN Thématique : IMAGERIE/POSITIONNEMENT Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=33001 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
067-2014021	RAB	Revue	Centre de documentation	En réserve L003	Disponible