Centre dedocumentation
scientifique

Remote sensing image colorization using symmetrical multi-scale DCGAN in YUV color space / Min Wu in The Visual Computer, vol 37 n° 7 (July 2021)  

Public [article]  inThe Visual Computer > vol 37 n° 7 (July 2021) . - pp 1707 - 1729 Titre : Remote sensing image colorization using symmetrical multi-scale DCGAN in YUV color space Type de document : Article/Communication Auteurs : Min Wu, Auteur ; Xin Jin, Auteur ; Qian Jiang, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 1707 - 1729 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] contraste de couleurs [Termes IGN] données multiéchelles [Termes IGN] image en couleur [Termes IGN] image RVB [Termes IGN] niveau de gris (image) [Termes IGN] réseau antagoniste génératif Résumé : (auteur) Image colorization technique is used to colorize the gray-level image or single-channel image, which is a very significant and challenging task in image processing, especially the colorization of remote sensing images. This paper proposes a new method for coloring remote sensing images based on deep convolution generation adversarial network. The adopted generator model is a symmetrical structure using the principle of auto-encoder, and a multi-scale convolutional module is specially designed to introduce into the generator model. Thus, the proposed generator can enable the whole model to retain more image features in the process of up-sampling and down-sampling. Meanwhile, the discriminator uses residual neural network 18 that can compete with the generator, so that the generator and discriminator can effectively optimize each other. In the proposed method, the color space transformation technique is first utilized to convert remote sensing images from RGB to YUV. Then, the Y channel (a gray-level image) is used as the input of the neural network model to predict UV channels. Finally, the predicted UV channels are concatenated with the original Y channel as a whole YUV that is then transformed into RGB space to get the final color image. Experiments are conducted to test the performance of different image colorization methods, and the results show that the proposed method has good performance in both visual quality and objective indexes on the colorization of remote sensing image. Numéro de notice : A2021-540 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00371-020-01933-2 date de publication en ligne : 28/08/2020 En ligne : https://doi.org/10.1007/s00371-020-01933-2 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98018 [article]

Pan-sharpening via multiscale dynamic convolutional neural network / Jianwen Hu in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 3 (March 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > Vol 59 n° 3 (March 2021) . - pp 2231 - 2244 Titre : Pan-sharpening via multiscale dynamic convolutional neural network Type de document : Article/Communication Auteurs : Jianwen Hu, Auteur ; Pei Hu, Auteur ; Xudong Kang, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 2231 - 2244 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] données multiéchelles [Termes IGN] image Geoeye [Termes IGN] image multibande [Termes IGN] image panchromatique [Termes IGN] image Quickbird [Termes IGN] image Worldview [Termes IGN] pansharpening (fusion d'images) [Termes IGN] reconstruction d'image Résumé : (Auteur) Pan-sharpening is an effective method to obtain high-resolution multispectral images by fusing panchromatic (PAN) images with fine spatial structure and low-resolution multispectral images with rich spectral information. In this article, a multiscale pan-sharpening method based on dynamic convolutional neural network is proposed. The filters in dynamic convolution are generated dynamically and locally by the filter generation network which is different from the standard convolution and strengthens the adaptivity of the network. The dynamic filters are adaptively changed according to the input images. The proposed multiscale dynamic convolutions extract detail feature of PAN image at different scales. Multiscale network structure is beneficial to obtain effective detail features. The weights obtained by the weight generation network are used to adjust the relationship among the detail features in each scale. The GeoEye-1, QuickBird, and WorldView-3 data are used to evaluate the performance of the proposed method. Compared with the widely used state-of-the-art pan-sharpening approaches, the experimental results demonstrate the superiority of the proposed method in terms of both objective quality indexes and visual performance. Numéro de notice : A2021-216 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3007884 date de publication en ligne : 16/07/2020 En ligne : https://doi.org/10.1109/TGRS.2020.3007884 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97206 [article]

Elevation models for reproducible evaluation of terrain representation / Patrick Kennelly in Cartography and Geographic Information Science, vol 48 n° 1 (January 2021)  

Public [article]  inCartography and Geographic Information Science > vol 48 n° 1 (January 2021) . - pp 63 - 77 Titre : Elevation models for reproducible evaluation of terrain representation Type de document : Article/Communication Auteurs : Patrick Kennelly, Auteur ; Tom Patterson, Auteur ; Bernhard Jenny, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 63 - 77 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] altitude [Termes IGN] données multiéchelles [Termes IGN] figuré du terrain [Termes IGN] modèle numérique de surface [Termes IGN] réalité de terrain [Termes IGN] relief [Termes IGN] représentation du relief [Termes IGN] reproductibilité [Termes IGN] visualisation de données Résumé : (auteur) This paper proposes elevation models to promote, evaluate, and compare various terrain representation techniques. Our goal is to increase the reproducibility of terrain rendering algorithms and techniques across different scales and landscapes. We introduce elevation models of varying terrain types, available to the user at no cost, with minimal common data imperfections such as missing data values, resampling artifacts, and seams. Three multiscale elevation models are available, each consisting of a set of elevation grids, centered on the same geographic location, with increasing cell sizes and spatial extents. We also propose a collection of single-scale elevation models of archetypal landforms including folded ridges, a braided riverbed, active and stabilized sand dunes, and a volcanic caldera. An inventory of 78 publications with a total of 155 renderings illustrating terrain visualization techniques guided the selection of landform types in the elevation models. The benefits of using the proposed elevation models include straightforward comparison of terrain representation methods across different publications and better documentation of the source data, which increases the reproducibility of terrain representations. Numéro de notice : A2021-719 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/15230406.2020.1830856 date de publication en ligne : 04/11/2020 En ligne : https://doi.org/10.1080/15230406.2020.1830856 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96459 [article]

Exploring multiscale object-based convolutional neural network (multi-OCNN) for remote sensing image classification at high spatial resolution / Vitor Martins in ISPRS Journal of photogrammetry and remote sensing, vol 168 (October 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 168 (October 2020) . - pp 56 - 73 Titre : Exploring multiscale object-based convolutional neural network (multi-OCNN) for remote sensing image classification at high spatial resolution Type de document : Article/Communication Auteurs : Vitor Martins, Auteur ; Amy L. Kaleita, Auteur ; Brian K. Gelder, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 56 - 73 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse d'image orientée objet [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] données multiéchelles [Termes IGN] étiquetage sémantique [Termes IGN] hétérogénéité environnementale [Termes IGN] image à haute résolution [Termes IGN] occupation du sol [Termes IGN] reconnaissance d'objets [Termes IGN] segmentation d'image [Termes IGN] squelettisation Résumé : (auteur) Convolutional Neural Network (CNN) has been increasingly used for land cover mapping of remotely sensed imagery. However, large-area classification using traditional CNN is computationally expensive and produces coarse maps using a sliding window approach. To address this problem, object-based CNN (OCNN) becomes an alternative solution to improve classification performance. However, previous studies were mainly focused on urban areas or small scenes, and implementation of OCNN method is still needed for large-area classification over heterogeneous landscape. Additionally, the massive labeling of segmented objects requires a practical approach for less computation, including object analysis and multiple CNNs. This study presents a new multiscale OCNN (multi-OCNN) framework for large-scale land cover classification at 1-m resolution over 145,740 km2. Our approach consists of three main steps: (i) image segmentation, (ii) object analysis with skeleton-based algorithm, and (iii) application of multiple CNNs for final classification. Also, we developed a large benchmark dataset, called IowaNet, with 1 million labeled images and 10 classes. In our approach, multiscale CNNs were trained to capture the best contextual information during the semantic labeling of objects. Meanwhile, skeletonization algorithm provided morphological representation (“medial axis”) of objects to support the selection of convolutional locations for CNN predictions. In general, proposed multi-OCNN presented better classification accuracy (overall accuracy ~87.2%) compared to traditional patch-based CNN (81.6%) and fixed-input OCNN (82%). In addition, the results showed that this framework is 8.1 and 111.5 times faster than traditional pixel-wise CNN16 or CNN256, respectively. Multiple CNNs and object analysis have proved to be essential for accurate and fast classification. While multi-OCNN produced a high-level of spatial details in the land cover product, misclassification was observed for some classes, such as road versus buildings or shadow versus lake. Despite these minor drawbacks, our results also demonstrated the benefits of IowaNet training dataset in the model performance; overfitting process reduces as the number of samples increases. The limitations of multi-OCNN are partially explained by segmentation quality and limited number of spectral bands in the aerial data. With the advance of deep learning methods, this study supports the claim of multi-OCNN benefits for operational large-scale land cover product at 1-m resolution. Numéro de notice : A2020-634 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.08.004 date de publication en ligne : 13/08/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.08.004 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96057 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020101	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020103	DEP-RECP	Revue	LaSTIG	Dépôt en unité	Exclu du prêt
081-2020102	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Designing multi-scale maps: lessons learned from existing practices / Marion Dumont in International journal of cartography, Vol 6 n° 1 (March 2020)  

Public [article]  inInternational journal of cartography > Vol 6 n° 1 (March 2020) . - pp 121 - 151 Titre : Designing multi-scale maps: lessons learned from existing practices Type de document : Article/Communication Auteurs : Marion Dumont , Auteur ; Guillaume Touya , Auteur ; Cécile Duchêne , Auteur Année de publication : 2020 Projets : MapMuxing / Christophe, Sidonie Article en page(s) : pp 121 - 151 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse visuelle [Termes IGN] carte interactive [Termes IGN] cognition [Termes IGN] données multiéchelles [Termes IGN] échelle cartographique [Termes IGN] géomatique web [Termes IGN] niveau d'abstraction [Termes IGN] niveau de détail [Termes IGN] représentation multiple [Termes IGN] Web Map Tile Service [Termes IGN] zoom [Vedettes matières IGN] Généralisation Résumé : (Auteur) Mapping applications display multi-scale maps where zooming in and out triggers the display of different maps at different scales. Multi-scale maps strongly augmented the potential uses of maps, compared to the traditional single-scaled paper maps. But the exploration of the multi-scale maps can be cognitively difficult for users because the content of the maps can be very different at different scales. This paper seeks to identify the factors in the design of map content and style that increase or decrease the exploration cognitive load, in order to improve multi-scales map design. We studied sixteen existing examples of multi-scale maps to identify these factors that influence a fluid zooming interaction. Several different analyses were conducted on these sixteen multi-scale maps. We first conducted a guided visual exploration of the maps, and a detailed study of the scales of the maps, to identify general trends of good practices (e.g. the WMTS standard that defines zoom levels is widely used) and potential ways of improvement (e.g. a same map is often used at multiple successive zoom levels). Then, we focused on the visual complexity of the multi-scale maps by analyzing how it varies, continuously or not, across scales, using clutter measures, which showed a peak of complexity at zoom level 12 of the WMTS standard. Finally, we studied how buildings and roads are subject to abstraction changes across scales (e.g. at what zoom level individual buildings turn into built-up areas), which can be one of the causes of exploration difficulties. We identified some good practices to reduce the impact of abstraction changes, for instance by mixing different levels of abstraction in the same map. Numéro de notice : A2020-060 Affiliation des auteurs : LaSTIG COGIT (2012-2019) Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/23729333.2020.1717832 date de publication en ligne : 28/01/2020 En ligne : https://doi.org/10.1080/23729333.2020.1717832 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94571 [article]

Rendu et représentation graphiques d’informations spatio-temporelles / Sidonie Christophe (2019)    

Permalink

Recherche en matière d’inventaire forestier [Introduction] / Jean-Daniel Bontemps (2018) 

Permalink

Progressive visualization of complex 3D models over the internet / Jing Chen in Transactions in GIS, vol 20 n° 6 (December 2016)  

Permalink

The impact of land use/land cover scale on modelling urban ecosystem services / Darren R. Grafius in Landscape ecology, vol 31 n° 7 (September 2016)  

Permalink

Adding intermediate representations in a multi-scale map to enable a smooth zooming / Marion Dumont (2015)    

Permalink

Managing Germany's big imagery data / Mladen Stojic in GEO: Geoconnexion international, vol 13 n° 2 (february 2014)

Permalink

Fully automated generalization of a 1:50k map from 1:10k data / Jantien E. Stoter in Cartography and Geographic Information Science, vol 41 n° 1 (January 2014)  

Permalink

Le ScaleMaster 2.0 : Une extension du modèle ScaleMaster pour gérer des généralisations multi-échelles automatiques / Guillaume Touya in Cartes & Géomatique, n° 217 (septembre 2013)    

Permalink

Boundary-constrained multi-scale segmentation method for remote sensing images / Xueliang Zhang in ISPRS Journal of photogrammetry and remote sensing, vol 78 (April 2013)

Permalink

Fast construction of global pyramids for very large satellite images / Longgang Xiang in Transactions in GIS, vol 17 n° 2 (April 2013)  

Permalink