Centre dedocumentation
scientifique

Detail injection-based deep convolutional neural networks for pansharpening / Liang-Jian Deng in IEEE Transactions on geoscience and remote sensing, vol 59 n° 8 (August 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 8 (August 2021) . - pp 6995 - 7010 Titre : Detail injection-based deep convolutional neural networks for pansharpening Type de document : Article/Communication Auteurs : Liang-Jian Deng, Auteur ; Gemine Vivone, Auteur ; Cheng Jin, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 6995 - 7010 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse multirésolution [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] image à basse résolution [Termes IGN] image multibande [Termes IGN] image panchromatique [Termes IGN] injection d'image [Termes IGN] modèle non linéaire [Termes IGN] pansharpening (fusion d'images) Résumé : (auteur) The fusion of high spatial resolution panchromatic (PAN) data with simultaneously acquired multispectral (MS) data with the lower spatial resolution is a hot topic, which is often called pansharpening. In this article, we exploit the combination of machine learning techniques and fusion schemes introduced to address the pansharpening problem. In particular, deep convolutional neural networks (DCNNs) are proposed to solve this issue. The latter is combined first with the traditional component substitution and multiresolution analysis fusion schemes in order to estimate the nonlinear injection models that rule the combination of the upsampled low-resolution MS image with the extracted details exploiting the two philosophies. Furthermore, inspired by these two approaches, we also developed another DCNN for pansharpening. This is fed by the direct difference between the PAN image and the upsampled low-resolution MS image. Extensive experiments conducted both at reduced and full resolutions demonstrate that this latter convolutional neural network outperforms both the other detail injection-based proposals and several state-of-the-art pansharpening methods. Numéro de notice : A2021-639 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3031366 En ligne : https://doi.org/10.1109/TGRS.2020.3031366 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98293 [article]

An adaptive filtering algorithm of multilevel resolution point cloud / Youyuan Li in Survey review, Vol 53 n° 379 (July 2021)  

Public [article]  inSurvey review > Vol 53 n° 379 (July 2021) . - pp 300 - 311 Titre : An adaptive filtering algorithm of multilevel resolution point cloud Type de document : Article/Communication Auteurs : Youyuan Li, Auteur ; Jian Wang, Auteur ; Bin Li, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 300 - 311 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] algorithme de filtrage [Termes IGN] analyse multirésolution [Termes IGN] classification ascendante hiérarchique [Termes IGN] données lidar [Termes IGN] filtrage de points [Termes IGN] filtre adaptatif [Termes IGN] interpolation spatiale [Termes IGN] Kappa de Cohen [Termes IGN] octree [Termes IGN] pente [Termes IGN] semis de points [Termes IGN] seuillage de points Résumé : (auteur) The existing filtering methods for airborne LiDAR point cloud have low accuracy. An adaptive filtering algorithm is proposed which is improved based on multilevel resolution algorithm. First double index structure of Octree and KDtree is established. Then the initial reference surface is constructed by ground seed points. According to the slope fluctuation situation, the grid resolution of the ground referential surface is adjusted in an adaptive way. Finally, the refined surface is formed gradually by multilevel renewing resolution to provide filtered point cloud with high accuracy. Experimental results show that the error of Type II can be effectively reduced, the average Kappa coefficient increases by 0.53% and the average total error decreases by 0.44% compared with multiresolution hierarchical classification algorithm. The result tested by practically measured data shows that Kappa coefficient can reach 90%. Especially, it maintains advantages of high accuracy under complex topographic environment. Numéro de notice : A2021-544 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/00396265.2020.1755163 Date de publication en ligne : 29/04/2020 En ligne : https://doi.org/10.1080/00396265.2020.1755163 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98042 [article]

Textural classification of remotely sensed images using multiresolution techniques / Rizwan Ahmed Ansari in Geocarto international, vol 35 n° 14 ([15/10/2020])  

Public [article]  inGeocarto international > vol 35 n° 14 [15/10/2020] . - pp 1580 - 1602 Titre : Textural classification of remotely sensed images using multiresolution techniques Type de document : Article/Communication Auteurs : Rizwan Ahmed Ansari, Auteur ; Krishna Mohan Buddhiraju, Auteur ; Avik Bhattacharya, Auteur Année de publication : 2020 Article en page(s) : pp 1580 - 1602 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] analyse multirésolution [Termes IGN] analyse texturale [Termes IGN] classification par forêts aléatoires [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] détection de contours [Termes IGN] distance euclidienne [Termes IGN] image optique [Termes IGN] image radar moirée [Termes IGN] image RVB [Termes IGN] image satellite [Termes IGN] texture d'image [Termes IGN] transformation en ondelettes Résumé : (auteur) Multiresolution analysis (MRA) methods have been successfully used in texture analysis. Texture analysis is widely discussed in literature, but most of the methods which do not employ multiresolution strategy cannot exploit the fact that texture occurs at various spatial scales. This paper proposes a methodology to identify different classes in satellite images using texture features from newly developed multiresolution methods. The proposed method is tested on remotely sensed optical images and a Pauli RGB decomposed version of synthetic aperture radar image. The textural information is extracted at various scales and in different directions from curvelet and contourlet transforms. The results are compared with wavelet-based features. Accuracy assessment is performed and comparative analysis is carried out using minimum distance to mean, support vector machine and random forest classifiers. It is found that the proposed method shows better class discriminating power and classification capability as compared to existing wavelet-based method. Numéro de notice : A2020-618 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1581263 Date de publication en ligne : 15/04/2019 En ligne : https://doi.org/10.1080/10106049.2019.1581263 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95994 [article]

Comparison of two methods for multiresolution terrain modelling in GIS / Turkay Gokgoz in Geocarto international, vol 35 n° 12 ([01/09/2020])  

Public [article]  inGeocarto international > vol 35 n° 12 [01/09/2020] . - pp 1360 - 1372 Titre : Comparison of two methods for multiresolution terrain modelling in GIS Type de document : Article/Communication Auteurs : Turkay Gokgoz, Auteur ; Müslüm Hacar, Auteur Année de publication : 2020 Article en page(s) : pp 1360 - 1372 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Systèmes d'information géographique [Termes IGN] analyse comparative [Termes IGN] analyse multirésolution [Termes IGN] modèle numérique de surface [Termes IGN] point remarquable [Termes IGN] système d'information géographique [Termes IGN] Triangulated Irregular Network [Termes IGN] triangulation de Delaunay Résumé : (auteur) Very important points (VIPs) and important points and edges (IPEs) methods have been compared in accordance with the TINs obtained by: (1) Delaunay triangulation using DEM points determined by VIP and (2) constrained Delaunay triangulation using DEM points and triangle edges determined by IPE. It was ensured that the number of points in each TIN was approximately equal to the number calculated by Töpfer’s formula, and that the vertical error of each TIN was less than the error calculated by Koppe’s formula. According to the results, (1) both methods are quality prioritized, (2) IPE is more sensitive to local surface changes, (3) important triangle edges determined by IPE make a significant contribution to the TIN, (4) some of the points selected by IPE are more important points than that of VIP, and (5) IPE-based TINs are more structural fidelity than VIP-based TINs. Numéro de notice : A2020-485 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1573929 Date de publication en ligne : 27/02/2019 En ligne : https://doi.org/10.1080/10106049.2019.1573929 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95652 [article]

Pansharpening: context-based generalized Laplacian pyramids by robust regression / Gemine Vivone in IEEE Transactions on geoscience and remote sensing, vol 58 n° 9 (September 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 9 (September 2020) . - pp 6152 - 6167 Titre : Pansharpening: context-based generalized Laplacian pyramids by robust regression Type de document : Article/Communication Auteurs : Gemine Vivone, Auteur ; Stefano Marano, Auteur ; Jocelyn Chanussot, Auteur Année de publication : 2020 Article en page(s) : pp 6152 - 6167 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse multirésolution [Termes IGN] fonction de transfert de modulation [Termes IGN] fusion d'images [Termes IGN] image multibande [Termes IGN] image panchromatique [Termes IGN] lissage de données [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] pansharpening (fusion d'images) [Termes IGN] régression [Termes IGN] transformation en ondelettes Résumé : (auteur) Pansharpening refers to the combination of panchromatic (PAN) and multispectral (MS) images, designed to obtain a fused product retaining the fine spatial resolution of the former and the high spectral content of the latter. One of the most popular and successful approaches to pansharpening is the method known as context-based generalized Laplacian pyramid, which requires as a key ingredient for the estimation of the so-called injection coefficients. In this article, we propose the adoption of robust techniques for the estimation of the injection coefficients and detection strategies to select the clusters for which robust regression is needed, providing a suitable balancing between fusion performance and computational burden. Experimental results conducted on five real data sets acquired by the sensors QuickBird, WorldView-3, and WorldView-4, show the superiority of the proposed method with respect to current state-of-the-art pansharpening techniques. Numéro de notice : A2020-528 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2974806 Date de publication en ligne : 04/03/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2974806 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95706 [article]

Multi-Spatial Resolution Satellite and sUAS Imagery for Precision Agriculture on Smallholder Farms in Malawi / Brad G. Peter in Photogrammetric Engineering & Remote Sensing, PERS, vol 86 n° 2 (February 2020)  

Permalink

Multi-scale point cloud analysis / Thibault Lejemble (2020)  

Permalink

Forest change detection in incomplete satellite images with deep neural networks / Salman H. Khan in IEEE Transactions on geoscience and remote sensing, vol 55 n° 9 (September 2017)  

Permalink

Describing contrast across scales / Sohaib Ali Syed in ISPRS Journal of photogrammetry and remote sensing, vol 128 (June 2017)  

Permalink

A robust fixed rank kriging method for improving the spatial completeness and accuracy of satellite SST products / Yuxin Zhu in IEEE Transactions on geoscience and remote sensing, vol 53 n° 9 (September 2015)  

Permalink

MTF-adjusted pansharpening approach based on coupled multiresolution decompositions / Abdelaziz Kallel in IEEE Transactions on geoscience and remote sensing, vol 53 n° 6 (June 2015)  

Permalink

A critical comparison among pansharpening algorithms / Gemine Vivone in IEEE Transactions on geoscience and remote sensing, vol 53 n° 5 (mai 2015)  

Permalink

Crop type classification by simultaneous use of satellite images of different resolutions / Mark W. Liu in IEEE Transactions on geoscience and remote sensing, vol 52 n° 6 Tome 2 (June 2014)  

Permalink

A multiresolution hierarchical classification algorithm for filtering airborne LiDAR data / Chuanfa Chen in ISPRS Journal of photogrammetry and remote sensing, vol 82 (August 2013)

Permalink

Development of a modified neural network-based land cover classification system using automated data selector and multiresolution remotely sensed data / S. Khorram in Geocarto international, vol 26 n° 6 (October 2011)  

Permalink