Descripteur



Etendre la recherche sur niveau(x) vers le bas
A graph-based semi-supervised approach to classification learning in digital geographies / Pengyuan Liu in Computers, Environment and Urban Systems, vol 86 (March 2021)
![]()
[article]
Titre : A graph-based semi-supervised approach to classification learning in digital geographies Type de document : Article/Communication Auteurs : Pengyuan Liu, Auteur ; Stefano de Sabbata, Auteur Année de publication : 2021 Article en page(s) : n° 101583 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web
[Termes descripteurs IGN] analyse contextuelle
[Termes descripteurs IGN] apprentissage profond
[Termes descripteurs IGN] approche participative
[Termes descripteurs IGN] classification par réseau neuronal convolutif
[Termes descripteurs IGN] classification semi-dirigée
[Termes descripteurs IGN] données spatiotemporelles
[Termes descripteurs IGN] étiquetage sémantique
[Termes descripteurs IGN] partage de données localisées
[Termes descripteurs IGN] réseau social
[Termes descripteurs IGN] Time-geographyRésumé : (auteur) As the distinction between online and physical spaces rapidly degrades, social media have now become an integral component of how many people's everyday experiences are mediated. As such, increasing interest has emerged in exploring how the content shared through those online platforms comes to contribute to the collaborative creation of places in physical space at the urban scale. Exploring digital geographies of social media data using methods such as qualitative coding (i.e., content labelling) is a flexible but complex task, commonly limited to small samples due to its impracticality over large datasets. In this paper, we propose a new tool for studies in digital geographies, bridging qualitative and quantitative approaches, able to learn a set of arbitrary labels (qualitative codes) on a small, manually-created sample and apply the same labels on a larger set. We introduce a semi-supervised, deep neural network approach to classify geo-located social media posts based on their textual and image content, as well as geographical and temporal aspects. Our innovative approach is rooted in our understanding of social media posts as augmentations of the time-space configurations that places are, and it comprises a stacked multi-modal autoencoder neural network to create joint representations of text and images, and a spatio-temporal graph convolution neural network for semi-supervised classification. The results presented in this paper show that our approach performs the classification of social media content with higher accuracy than traditional machine learning models as well as two state-of-art deep learning frameworks. Numéro de notice : A2021-024 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1016/j.compenvurbsys.2020.101583 date de publication en ligne : 16/12/2020 En ligne : https://doi.org/10.1016/j.compenvurbsys.2020.101583 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96608
in Computers, Environment and Urban Systems > vol 86 (March 2021) . - n° 101583[article]Land cover harmonization using Latent Dirichlet Allocation / Zhan Li in International journal of geographical information science IJGIS, vol 35 n° 2 (February 2021)
![]()
[article]
Titre : Land cover harmonization using Latent Dirichlet Allocation Type de document : Article/Communication Auteurs : Zhan Li, Auteur ; Joanne C. White, Auteur ; Michael A. Wulder, Auteur Année de publication : 2021 Article en page(s) : pp 348 - 374 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale
[Termes descripteurs IGN] allocation de Dirichlet latente
[Termes descripteurs IGN] Canada
[Termes descripteurs IGN] carte d'occupation du sol
[Termes descripteurs IGN] chevauchement
[Termes descripteurs IGN] erreur de classification
[Termes descripteurs IGN] étiquetage sémantique
[Termes descripteurs IGN] harmonisation des données
[Termes descripteurs IGN] matrice d'erreur
[Termes descripteurs IGN] matrice de co-occurrence
[Termes descripteurs IGN] utilisation du solRésumé : (auteur) Large-area land cover maps are produced to satisfy different information needs. Land cover maps having partial or complete spatial and/or temporal overlap, different legends, and varying accuracies for similar classes, are increasingly common. To address these concerns and combine two 30-m resolution land cover products, we implemented a harmonization procedure using a Latent Dirichlet Allocation (LDA) model. The LDA model used regionalized class co-occurrences from multiple maps to generate a harmonized class label for each pixel by statistically characterizing land attributes from the class co-occurrences. We evaluated multiple harmonization approaches: using the LDA model alone and in combination with more commonly used information sources for harmonization (i.e. error matrices and semantic affinity scores). The results were compared with the benchmark maps generated using simple legend crosswalks and showed that using LDA outputs with error matrices performed better and increased harmonized map overall accuracy by 6–19% for areas of disagreement between the source maps. Our results revealed the importance of error matrices to harmonization, since excluding error matrices reduced overall accuracy by 4–20%. The LDA-based harmonization approach demonstrated in this paper is quantitative, transparent, portable, and efficient at leveraging the strengths of multiple land cover maps over large areas. Numéro de notice : A2021-027 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1796131 date de publication en ligne : 27/07/2020 En ligne : https://doi.org/10.1080/13658816.2020.1796131 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96701
in International journal of geographical information science IJGIS > vol 35 n° 2 (February 2021) . - pp 348 - 374[article]Automated labeling of schematic maps by optimization with knowledge acquired from existing maps / Tian Lan in Transactions in GIS, Vol 24 n° 6 (December 2020)
![]()
[article]
Titre : Automated labeling of schematic maps by optimization with knowledge acquired from existing maps Type de document : Article/Communication Auteurs : Tian Lan, Auteur ; Zhilin Li, Auteur ; Qian Peng, Auteur ; Xinyu Gong, Auteur Année de publication : 2020 Article en page(s) : pp 1722 - 1739 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cartographie thématique
[Termes descripteurs IGN] automatisation
[Termes descripteurs IGN] calcul d'itinéraire
[Termes descripteurs IGN] Chine
[Termes descripteurs IGN] données cartographiques
[Termes descripteurs IGN] étiquetage sémantique
[Termes descripteurs IGN] Hong-Kong
[Termes descripteurs IGN] optimisation (mathématiques)
[Termes descripteurs IGN] réseau métropolitainRésumé : (Auteur) Schematic maps are simplified representations of line networks, aiming to help people quickly and accurately perform route planning and orientation tasks. The automated generation of such maps is generally treated as an optimization problem. Most researchers prefer to optimize network layouts and name labels separately, because optimizing them simultaneously is still intractable. It is found that optimizing network layouts is extensively studied, while optimizing name labels is rarely considered. In the optimization of name labels, constraints can be established with rules from cartographic experts, literature (e.g., specification and technical documents), and/or existing maps. However, some rules from experts and literature cannot be explicitly and mathematically expressed. This study aims to develop an automated labeling method with rules from existing maps. We first acquire the rules (i.e., the potential positions and the preferences of these positions) from some existing schematic maps and then integrate them into an optimization algorithm. Experimental evaluation is conducted by a questionnaire in terms of “ease level of finding name labels,” “congestion level,” and “satisfaction level” using Tianjin and Hong Kong metro schematic maps and the labels of our method. The results show that the proposed method can automatically generate effective labels. Numéro de notice : A2020-769 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12671 date de publication en ligne : 06/08/2020 En ligne : https://doi.org/10.1111/tgis.12671 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96661
in Transactions in GIS > Vol 24 n° 6 (December 2020) . - pp 1722 - 1739[article]High-resolution remote sensing image scene classification via key filter bank based on convolutional neural network / Fengpeng Li in IEEE Transactions on geoscience and remote sensing, vol 58 n° 11 (November 2020)
![]()
[article]
Titre : High-resolution remote sensing image scene classification via key filter bank based on convolutional neural network Type de document : Article/Communication Auteurs : Fengpeng Li, Auteur ; Ruyi Feng, Auteur ; Wei Han, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 8077 - 8092 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes descripteurs IGN] apprentissage profond
[Termes descripteurs IGN] classification par réseau neuronal convolutif
[Termes descripteurs IGN] étiquetage sémantique
[Termes descripteurs IGN] extraction de traits caractéristiques
[Termes descripteurs IGN] filtrage numérique d'image
[Termes descripteurs IGN] image à haute résolution
[Termes descripteurs IGN] jeu de données
[Termes descripteurs IGN] test statistiqueRésumé : (auteur) High-resolution remote sensing (HRRS) image scene classification has attracted an enormous amount of attention due to its wide application in a range of tasks. Due to the rapid development of deep learning (DL), models based on convolutional neural network (CNN) have made competitive achievements on HRRS image scene classification because of the excellent representation capacity of DL. The scene labels of HRRS images extremely depend on the combination of global information and information from key regions or locations. However, most existing models based on CNN tend only to represent the global features of images or overstate local information capturing from key regions or locations, which may confuse different categories. To address this issue, a key region or location capturing method called key filter bank (KFB) is proposed in this article, and KFB can retain global information at the same time. This method can combine with different CNN models to improve the performance of HRRS imagery scene classification. Moreover, for the convenience of practical tasks, an end-to-end model called KFBNet where KFB combined with DenseNet-121 is proposed to compare the performance with existing models. This model is evaluated on public benchmark data sets, and the proposed model makes better performance on benchmarks than the state-of-the-art methods. Numéro de notice : A2020-683 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2987060 date de publication en ligne : 23/04/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2987060 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96208
in IEEE Transactions on geoscience and remote sensing > vol 58 n° 11 (November 2020) . - pp 8077 - 8092[article]River ice segmentation with deep learning / Abhineet Singh in IEEE Transactions on geoscience and remote sensing, vol 58 n° 11 (November 2020)
![]()
[article]
Titre : River ice segmentation with deep learning Type de document : Article/Communication Auteurs : Abhineet Singh, Auteur ; Hayden Kalke, Auteur ; Mark Loewen, Auteur Année de publication : 2020 Article en page(s) : pp 7570 - 7579 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes descripteurs IGN] apprentissage non-dirigé
[Termes descripteurs IGN] apprentissage profond
[Termes descripteurs IGN] Canada
[Termes descripteurs IGN] classification par réseau neuronal convolutif
[Termes descripteurs IGN] classification par séparateurs à vaste marge
[Termes descripteurs IGN] étiquetage sémantique
[Termes descripteurs IGN] glace
[Termes descripteurs IGN] image captée par drone
[Termes descripteurs IGN] rivière
[Termes descripteurs IGN] segmentation d'image
[Termes descripteurs IGN] segmentation sémantiqueRésumé : (auteur) This article deals with the problem of computing surface concentrations for two types of river ice from digital images acquired during freeze-up. It presents the results of attempting to solve this problem using several state-of-the-art semantic segmentation methods based on deep convolutional neural networks (CNNs). This task presents two main challenges—very limited availability of labeled training data and presence of noisy labels due to the great difficulty of visually distinguishing between the two types of ice, even for human experts. The results are used to analyze the extent to which some of the best deep learning methods currently in existence can handle these challenges. The code and data used in the experiments are made publicly available to facilitate further work in this domain. Numéro de notice : A2020-674 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2981082 date de publication en ligne : 13/04/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2981082 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96165
in IEEE Transactions on geoscience and remote sensing > vol 58 n° 11 (November 2020) . - pp 7570 - 7579[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)
PermalinkUnsupervised semantic and instance segmentation of forest point clouds / Di Wang in ISPRS Journal of photogrammetry and remote sensing, vol 165 (July 2020)
PermalinkSemantic signatures for large-scale visual localization / Li Weng in Multimedia tools and applications, vol inconnu (2020)
PermalinkDirectionally constrained fully convolutional neural network for airborne LiDAR point cloud classification / Congcong Wen in ISPRS Journal of photogrammetry and remote sensing, vol 162 (April 2020)
PermalinkModelling discontinuous terrain from DSMs using segment labelling, outlier removal and thin-plate splines / Kassel Hingee in ISPRS Journal of photogrammetry and remote sensing, vol 155 (September 2019)
Permalink3D hyperspectral point cloud generation: Fusing airborne laser scanning and hyperspectral imaging sensors for improved object-based information extraction / Maximilian Brell in ISPRS Journal of photogrammetry and remote sensing, vol 149 (March 2019)
PermalinkAn exploratory analysis of usability of Flickr tags for land use/land cover attribution / Yingwei Yan in Geo-spatial Information Science, vol 22 n° 1 (March 2019)
PermalinkIntegration of lidar data and GIS data for point cloud semantic enrichment at the point level / Harith Aljumaily in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 1 (January 2019)
PermalinkA cross-analysis framework for multi-source volunteered, crowdsourced, and authoritative geographic information : The case study of volunteered personal traces analysis against transport network data / Gloria Bordogna in Geo-spatial Information Science, vol 21 n° 3 (October 2018)
PermalinkOpenStreetMap data quality enrichment through awareness raising and collective action tools—experiences from a European project / Amin Mobasheri in Geo-spatial Information Science, vol 21 n° 3 (October 2018)
Permalink