Centre dedocumentation
scientifique

A deep multi-modal learning method and a new RGB-depth data set for building roof extraction / Mehdi Khoshboresh Masouleh in Photogrammetric Engineering & Remote Sensing, PERS, vol 87 n° 10 (October 2021)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 87 n° 10 (October 2021) . - pp 759 - 766 Titre : A deep multi-modal learning method and a new RGB-depth data set for building roof extraction Type de document : Article/Communication Auteurs : Mehdi Khoshboresh Masouleh, Auteur ; Reza Shah-Hosseini, Auteur Année de publication : 2021 Article en page(s) : pp 759 - 766 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage automatique [Termes IGN] détection du bâti [Termes IGN] données multisources [Termes IGN] effet de profondeur cinétique [Termes IGN] empreinte [Termes IGN] extraction automatique [Termes IGN] extraction de traits caractéristiques [Termes IGN] image RVB [Termes IGN] Indiana (Etats-Unis) [Termes IGN] réseau neuronal convolutif [Termes IGN] réseau neuronal profond [Termes IGN] segmentation d'image [Termes IGN] superpixel [Termes IGN] toit Résumé : (Auteur) This study focuses on tackling the challenge of building mapping in multi-modal remote sensing data by proposing a novel, deep superpixel-wise convolutional neural network called DeepQuantized-Net, plus a new red, green, blue (RGB)-depth data set named IND. DeepQuantized-Net incorporated two practical ideas in segmentation: first, improving the object pattern with the exploitation of superpixels instead of pixels, as the imaging unit in DeepQuantized-Net. Second, the reduction of computational cost. The generated data set includes 294 RGB-depth images (256 training images and 38 test images) from different locations in the state of Indiana in the U.S., with 1024 × 1024 pixels and a spatial resolution of 0.5 ftthat covers different cities. The experimental results using the IND data set demonstrates the mean F1 scores and the average Intersection over Union scores could increase by approximately 7.0% and 7.2% compared to other methods, respectively. Numéro de notice : A2021-677 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.21-00007R2 Date de publication en ligne : 01/10/2021 En ligne : https://doi.org/10.14358/PERS.21-00007R2 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98878 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2021101	SL	Revue	Centre de documentation	Revues en salle	Disponible

Stochastic super-resolution for downscaling time-evolving atmospheric fields with a generative adversarial network / Jussi Leinonen in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 9 (September 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > Vol 59 n° 9 (September 2021) . - pp 7211 - 7223 Titre : Stochastic super-resolution for downscaling time-evolving atmospheric fields with a generative adversarial network Type de document : Article/Communication Auteurs : Jussi Leinonen, Auteur ; Daniele Nerini, Auteur ; Alexis Berne, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 7211 - 7223 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] données météorologiques [Termes IGN] épaisseur de nuage [Termes IGN] image à basse résolution [Termes IGN] image GOES [Termes IGN] modèle atmosphérique [Termes IGN] précipitation [Termes IGN] processus stochastique [Termes IGN] réduction d'échelle [Termes IGN] réseau antagoniste génératif [Termes IGN] réseau neuronal convolutif [Termes IGN] Suisse Résumé : (auteur) Generative adversarial networks (GANs) have been recently adopted for super-resolution, an application closely related to what is referred to as “downscaling” in the atmospheric sciences: improving the spatial resolution of low-resolution images. The ability of conditional GANs to generate an ensemble of solutions for a given input lends itself naturally to stochastic downscaling, but the stochastic nature of GANs is not usually considered in super-resolution applications. Here, we introduce a recurrent, stochastic super-resolution GAN that can generate ensembles of time-evolving high-resolution atmospheric fields for an input consisting of a low-resolution sequence of images of the same field. We test the GAN using two data sets: one consisting of radar-measured precipitation from Switzerland; the other of cloud optical thickness derived from the Geostationary Earth Observing Satellite 16 (GOES-16). We find that the GAN can generate realistic, temporally consistent super-resolution sequences for both data sets. The statistical properties of the generated ensemble are analyzed using rank statistics, a method adapted from ensemble weather forecasting; these analyses indicate that the GAN produces close to the correct amount of variability in its outputs. As the GAN generator is fully convolutional, it can be applied after training to input images larger than the images used to train it. It is also able to generate time series much longer than the training sequences, as demonstrated by applying the generator to a three-month data set of the precipitation radar data. The source code to our GAN is available at https://github.com/jleinonen/downscaling-rnn-gan. Numéro de notice : A2021-645 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3032790 Date de publication en ligne : 02/11/2020 En ligne : https://doi.org/10.1109/TGRS.2020.3032790 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98349 [article]

Unsupervised representation high-resolution remote sensing image scene classification via contrastive learning convolutional neural network / Fengpeng Li in Photogrammetric Engineering & Remote Sensing, PERS, vol 87 n° 8 (August 2021)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 87 n° 8 (August 2021) . - pp 577 - 591 Titre : Unsupervised representation high-resolution remote sensing image scene classification via contrastive learning convolutional neural network Type de document : Article/Communication Auteurs : Fengpeng Li, Auteur ; Jiabao Li, Auteur ; Wei Han, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 577 - 591 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 [Termes IGN] grande échelle [Termes IGN] image à haute résolution [Termes IGN] image aérienne [Termes IGN] moyenne échelle [Termes IGN] petite échelle [Termes IGN] régression linéaire [Termes IGN] réseau neuronal convolutif Résumé : (Auteur) Inspired by the outstanding achievement of deep learning, supervised deep learning representation methods for high-spatial-resolution remote sensing image scene classification obtained state-of-the-art performance. However, supervised deep learning representation methods need a considerable amount of labeled data to capture class-specific features, limiting the application of deep learning-based methods while there are a few labeled training samples. An unsupervised deep learning representation, high-resolution remote sensing image scene classification method is proposed in this work to address this issue. The proposed method, called contrastive learning, narrows the distance between positive views: color channels belonging to the same images widens the gaps between negative view pairs consisting of color channels from different images to obtain class-specific data representations of the input data without any supervised information. The classifier uses extracted features by the convolutional neural network (CNN)-based feature extractor with labeled information of training data to set space of each category and then, using linear regression, makes predictions in the testing procedure. Comparing with existing unsupervised deep learning representation high-resolution remote sensing image scene classification methods, contrastive learning CNN achieves state-of-the-art performance on three different scale benchmark data sets: small scale RSSCN7 data set, midscale aerial image data set, and large-scale NWPU-RESISC45 data set. Numéro de notice : A2021-670 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.87.8.577 Date de publication en ligne : 01/08/2021 En ligne : https://doi.org/10.14358/PERS.87.8.577 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98806 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2021081	SL	Revue	Centre de documentation	Revues en salle	Disponible

A convolutional neural network approach to predict non‐permissive environments from moderate‐resolution imagery / Seth Goodman in Transactions in GIS, Vol 25 n° 2 (April 2021)  

Public [article]  inTransactions in GIS > Vol 25 n° 2 (April 2021) . - pp 674 - 691 Titre : A convolutional neural network approach to predict non‐permissive environments from moderate‐resolution imagery Type de document : Article/Communication Auteurs : Seth Goodman, Auteur ; Ariel BenYishay, Auteur ; Daniel Runfola, Auteur Année de publication : 2021 Article en page(s) : pp 674 - 691 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] conflit [Termes IGN] image Landsat-8 [Termes IGN] implémentation (informatique) [Termes IGN] Nigéria [Termes IGN] prédiction [Termes IGN] réseau neuronal convolutif Résumé : (Auteur) Convolutional neural networks (CNNs) trained with satellite imagery have been successfully used to generate measures of development indicators, such as poverty, in developing nations. This article explores a CNN‐based approach leveraging Landsat 8 imagery to predict locations of conflict‐related deaths. Using Nigeria as a case study, we use the Armed Conflict Location & Event Data (ACLED) dataset to identify locations of conflict events that did or did not result in a death. Imagery for each location is used as an input to train a CNN to distinguish fatal from non‐fatal events. Using 2014 imagery, we are able to predict the result of conflict events in the following year (2015) with 80% accuracy. While our approach does not replace the need for causal studies into the drivers of conflict death, it provides a low‐cost solution to prediction that requires only publicly available imagery to implement. Findings suggest that the information contained in moderate‐resolution imagery can be used to predict the likelihood of a death due to conflict at a given location in Nigeria the following year, and that CNN‐based methods of estimating development‐related indicators may be effective in applications beyond those explored in the literature. Numéro de notice : A2021-361 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12661 Date de publication en ligne : 13/07/2020 En ligne : https://doi.org/10.1111/tgis.12661 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97625 [article]

Can graph convolution networks learn spatial relations? / Azelle Courtial (2021)  

Public Titre : Can graph convolution networks learn spatial relations? Type de document : Article/Communication Auteurs : Azelle Courtial , Auteur ; Guillaume Touya , Auteur ; Xiang Zhang, Auteur Editeur : Paris, ... [Suède] : International Cartographic Association ICA - Association cartographique internationale ACI Année de publication : 2021 Collection : Abstracts of the ICA num. 3 Projets : 1-Pas de projet / Conférence : ICC 2021, 30th ICA international cartographic conference 14/12/2021 18/12/2021 Florence Italie Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] alignement [Termes IGN] bati [Termes IGN] objet géographique [Termes IGN] relation spatiale [Termes IGN] réseau neuronal convolutif [Termes IGN] réseau neuronal de graphes [Termes IGN] réseau routier [Vedettes matières IGN] Généralisation Résumé : (auteur) [introduction] Maps are composed of spatially related geographic objects. Spatial relations are key information for human as they support the description of relative locations: the house is to the east of the city centre, near the interchange, or at the end of the path. Consequently, preserving these spatial relations is important during map generalisation. For example, building typification is a generalisation operation that seeks to reduce the quantity of building while preserving relation between and within homogeneous buildings groups (Regnauld, 2001). Building or road patterns are remarkable distributions of elements in the map from which high-level concepts and semantics (e.g. landuse types and urban morphology) can be inferred. Such patterns can be characterized by spatial relations (e.g. proximity, similarity and continuity of these elements) and hence are visually easy to identify by a human. To identify these patterns automatically is important for automated map generalisation (Christophe and Ruas, 2002). However, it remains challenging to devise algorithms that can resemble the human level performance. The goal of this paper is to illustrate the potential of graph convolutional networks (GCN) for the identification of patterns and relations important for map generalisation with two use cases: building patterns detection, and road segment selection. Both tasks require some degree of understanding of the spatial relations between map objects. Hence, our experiments constitute a first step in exploring the capability of deep neural network for learning representations of spatial relations. Numéro de notice : C2021-045 Affiliation des auteurs : UGE-LASTIG (2020- ) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.5194/ica-abs-3-60-2021 Date de publication en ligne : 13/12/2021 En ligne : https://doi.org/10.5194/ica-abs-3-60-2021 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99420

Understanding the role of individual units in a deep neural network / David Bau in Proceedings of the National Academy of Sciences of the United States of America PNAS, vol 117 n° 48 (December 2020)  

Permalink

Learning sequential slice representation with an attention-embedding network for 3D shape recognition and retrieval in MLS point clouds / Zhipeng Luo in ISPRS Journal of photogrammetry and remote sensing, vol 161 (March 2020)  

Permalink

A convolutional neural network approach for counting and geolocating citrus-trees in UAV multispectral imagery / Lucas Prado Osco in ISPRS Journal of photogrammetry and remote sensing, vol 160 (February 2020)  

Permalink

Transferring deep learning models for cloud detection between Landsat-8 and Proba-V / Gonzalo Mateo-García in ISPRS Journal of photogrammetry and remote sensing, vol 160 (February 2020)  

Permalink

Remote sensing based building extraction / Mohammad Awrangjeb (2020)  

Permalink

Representation learning for natural language processing / Zhiyuan Liu (2020)  

Permalink

SpiNNaker: A spiking neural network architecture / Steve Furber (2020)  

Permalink

Système de traitement d’images temps réel dédié à la mesure de champs denses de déplacements et de déformations / Seyfeddine Boukhtache (2020)  

Permalink

Using a U-net convolutional neural network to map woody vegetation extent from high resolution satellite imagery across Queensland, Australia / Neil Flood in International journal of applied Earth observation and geoinformation, vol 82 (October 2019)  

Permalink

Addressing overfitting on point cloud classification using Atrous XCRF / Hasan Asy’ari Arief in ISPRS Journal of photogrammetry and remote sensing, vol 155 (September 2019)  

Permalink