Centre de documentation
scientifique

Deriving map images of generalised mountain roads with generative adversarial networks / Azelle Courtial in International journal of geographical information science IJGIS, vol 37 n° 3 (March 2023)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 37 n° 3 (March 2023) . - pp 499 - 528 Titre : Deriving map images of generalised mountain roads with generative adversarial networks Type de document : Article/Communication Auteurs : Azelle Courtial , Auteur ; Guillaume Touya , Auteur ; Xiang Zhang, Auteur Année de publication : 2023 Article en page(s) : pp 499 - 528 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse comparative [Termes IGN] apprentissage dirigé [Termes IGN] apprentissage non-dirigé [Termes IGN] carte routière [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] généralisation cartographique automatisée [Termes IGN] montagne [Termes IGN] réseau antagoniste génératif [Vedettes matières IGN] Généralisation Résumé : (auteur) Map generalisation is a process that transforms geographic information for a cartographic at a specific scale. The goal is to produce legible and informative maps even at small scales from a detailed dataset. The potential of deep learning to help in this task is still unknown. This article examines the use case of mountain road generalisation, to explore the potential of a specific deep learning approach: generative adversarial networks (GAN). Our goal is to generate images that depict road maps generalised at the 1:250k scale, from images that depict road maps of the same area using un-generalised 1:25k data. This paper not only shows the potential of deep learning to generate generalised mountain roads, but also analyses how the process of deep learning generalisation works, compares supervised and unsupervised learning and explores possible improvements. With this experiment we have exhibited an unsupervised model that is able to generate generalised maps evaluated as good as the reference and reviewed some possible improvements for deep learning-based generalisation, including training set management and the definition of a new road connectivity loss. All our results are evaluated visually using a four questions process and validated by a user test conducted on 113 individuals. Numéro de notice : A2023-073 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2022.2123488 Date de publication en ligne : 20/10/2022 En ligne : https://doi.org/10.1080/13658816.2022.2123488 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101901 [article]

Domain adaptation in segmenting historical maps: A weakly supervised approach through spatial co-occurrence / Sidi Wu in ISPRS Journal of photogrammetry and remote sensing, vol 197 (March 2023)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 197 (March 2023) . - pp 199 - 211 Titre : Domain adaptation in segmenting historical maps: A weakly supervised approach through spatial co-occurrence Type de document : Article/Communication Auteurs : Sidi Wu, Auteur ; Konrad Schindler, Auteur ; Magnus Heitzler, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 199 - 211 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] carte ancienne [Termes IGN] cartographie historique [Termes IGN] classification dirigée [Termes IGN] détection de changement [Termes IGN] données anciennes [Termes IGN] matrice de co-occurrence [Termes IGN] réseau antagoniste génératif [Termes IGN] segmentation d'image [Termes IGN] vision par ordinateur Résumé : (auteur) Historical maps depict past states of the Earth’s surface and make it possible to trace the natural or anthropogenic evolution of geographic objects back through time. However, the state of the depicted reality is not the only source of change: maps of varying age can differ in terms of graphical design, and also in terms of storage conditions, physical ageing of pigments, and the scanning process for digitization. Consequently, a computer vision system learned from a specific (source) map series will often not generalize well to older or newer (target) maps, calling for domain adaptation. In the present paper we examine – to our knowledge for the first time – domain adaptation for segmenting historical maps. We argue that for geo-spatial data like maps, which are geo-localized by definition, the spatial co-occurrence of geographical objects provides a supervision signal for domain adaptation. Since only a subset of all mapped objects co-occur, and even those are not perfectly aligned due to both real topographic changes and variations in map generalization/production, they only provide weak supervision — still they can bring a substantial benefit over completely unsupervised domain adaptation methods. The core of our proposed method is a novel self-supervised co-occurrence network that detects co-occurring objects across maps (specifically, domains) with a novel loss function that allows for object changes and spatial misalignment. Experiments show that, for the task of segmenting hydrological objects such as rivers, lakes and wetlands, our system significantly outperforms two state-of-art baselines, even with limited supervision (e.g., 5%). The source code is publicly available at https://github.com/sian-wusidi/spatialcooccurrence. Numéro de notice : A2023-146 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2023.01.021 Date de publication en ligne : 14/02/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2023.01.021 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102804 [article]

Exploring the potential of deep learning for map generalization / Azelle Courtial (2023)  

Public Titre : Exploring the potential of deep learning for map generalization Type de document : Thèse/HDR Auteurs : Azelle Courtial , Auteur ; Guillaume Touya , Directeur de thèse ; Xiang Zhang, Directeur de thèse Editeur : Champs-sur-Marne [France] : Université Gustave Eiffel Année de publication : 2023 Importance : 216 p. Note générale : bibliographie Doctoral thesis from Université Gustave Eiffel, Doctoral school MSTIC, Specialty "Geographic information sciences" Langues : Anglais (eng) Descripteur : [Termes IGN] généralisation automatique de données [Termes IGN] généralisation cartographique automatisée [Termes IGN] relation spatiale [Termes IGN] réseau antagoniste génératif [Termes IGN] réseau neuronal profond [Vedettes matières IGN] Généralisation Index. décimale : THESE Thèses et HDR Résumé : (auteur) Map generalization is a process that aims to adapt the level of detail of geographic information for cartography at a small scale. Automating the process is complex but essential in map production. We think this research field could benefit from the recent advances in deep learning that make it possible to solve more and more complex tasks, using numerous training examples. This thesis proposes exploring the potential of deep learning for map generalization. This exploration is built upon three map generalization use cases: recognition of spatial relations, graphic generalization of mountain roads, and generalization of topographic maps at medium scales. These three use cases enable us to address research questions relative to the concrete implementation of deep learning models for map generalization (including dataset creation and architecture), the evaluation of such models and their integration in existing generalization processes. In addition to the models and training set adapted for each of our case studies already mentioned, we propose evaluation methods adapted to the challenges of cartographic generalization by deep learning. Finally, we propose a partitioning of the cartographic generalization into sub-problems facilitating the resolution by learning and allowing the generation of generalized map images. Note de contenu : Introduction Part 1 A new paradigm for map generalization Chapter A. Literature review Chapter B. Formulating map generalization as a deep learning task Chapter C. Designing a framework for deep learning based map generalization Part 2 Exploration of deep learning for map generalization Chapter D. Can graph neural networks model spatial relations? Chapter E. CNN for the generalization of roads Chapter F. The generation of topographic map with several themes Part III The future of map generalization with deep learning Chapter G. Usages of deep learning models for map generalization Chapter H. Evaluation of deep learning predictions Conclusion Numéro de notice : 17752 Affiliation des auteurs : UGE-LASTIG (2020- ) Thématique : GEOMATIQUE Nature : Thèse française Organisme de stage : LASTIG (IGN) nature-HAL : Thèse DOI : sans Date de publication en ligne : 05/05/2023 En ligne : https://theses.hal.science/tel-04089883v1 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103186

Prototype-guided multitask adversarial network for cross-domain LiDAR point clouds semantic segmentation / Zhimin Yuan in IEEE Transactions on geoscience and remote sensing, vol 61 n° 1 (January 2023)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 61 n° 1 (January 2023) . - n° 5700613 Titre : Prototype-guided multitask adversarial network for cross-domain LiDAR point clouds semantic segmentation Type de document : Article/Communication Auteurs : Zhimin Yuan, Auteur ; Ming Cheng, Auteur ; Wankang Zeng, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 5700613 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] alignement des données [Termes IGN] apprentissage non-dirigé [Termes IGN] compression de données [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] extraction de traits caractéristiques [Termes IGN] réseau antagoniste génératif [Termes IGN] segmentation sémantique [Termes IGN] semis de points Résumé : (auteur) Unsupervised domain adaptation (UDA) segmentation aims to leverage labeled source data to make accurate predictions on unlabeled target data. The key is to make the segmentation network learn domain-invariant representations. In this work, we propose a prototype-guided multitask adversarial network (PMAN) to achieve this. First, we propose an intensity-aware segmentation network (IAS-Net) that leverages the private intensity information of target data to substantially facilitate feature learning of the target domain. Second, the category-level cross-domain feature alignment strategy is introduced to flee the side effects of global feature alignment. It employs the prototype (class centroid) and includes two essential operations: 1) build an auxiliary nonparametric classifier to evaluate the semantic alignment degree of each point based on the prediction consistency between the main and auxiliary classifiers and 2) introduce two class-conditional point-to-prototype learning objectives for better alignment. One is to explicitly perform category-level feature alignment in a progressive manner, and the other aims to shape the source feature representation to be discriminative. Extensive experiments reveal that our PMAN outperforms state-of-the-art results on two benchmark datasets. Numéro de notice : A2023-118 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2023.3234542 Date de publication en ligne : 05/01/2023 En ligne : https://doi.org/10.1109/TGRS.2023.3234542 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102489 [article]

A deep learning framework based on generative adversarial networks and vision transformer for complex wetland classification using limited training samples / Ali Jamali in International journal of applied Earth observation and geoinformation, vol 115 (December 2022)  

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 115 (December 2022) . - n° 103095 Titre : A deep learning framework based on generative adversarial networks and vision transformer for complex wetland classification using limited training samples Type de document : Article/Communication Auteurs : Ali Jamali, Auteur ; Masoud Mahdianpari, Auteur ; fariba Mohammadimanesh, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 103095 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage profond [Termes IGN] Canada [Termes IGN] carte thématique [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR [Termes IGN] réseau antagoniste génératif [Termes IGN] zone humide Résumé : (auteur) Wetlands have long been recognized among the most critical ecosystems globally, yet their numbers quickly diminish due to human activities and climate change. Thus, large-scale wetland monitoring is essential to provide efficient spatial and temporal insights for resource management and conservation plans. However, the main challenge is the lack of enough reference data for accurate large-scale wetland mapping. As such, the main objective of this study was to investigate the efficient deep-learning models for generating high-resolution and temporally rich training datasets for wetland mapping. The Sentinel-1 and Sentinel-2 satellites from the European Copernicus program deliver radar and optical data at a high temporal and spatial resolution. These Earth observations provide a unique source of information for more precise wetland mapping from space. The second objective was to investigate the efficiency of vision transformers for complex landscape mapping. As such, we proposed a 3D Generative Adversarial Network (3D GAN) to best achieve these two objectives of synthesizing training data and a Vision Transformer model for large-scale wetland classification. The proposed approach was tested in three different study areas of Saint John, Sussex, and Fredericton, New Brunswick, Canada. The results showed the ability of the 3D GAN to stimulate and increase the number of training data and, as a result, increase the accuracy of wetland classification. The quantitative results also demonstrated the capability of jointly using data augmentation, 3D GAN, and Vision Transformer models with overall accuracy, average accuracy, and Kappa index of 75.61%, 73.4%, and 71.87%, respectively, using a disjoint data sampling strategy. Therefore, the proposed deep learning method opens a new window for large-scale remote sensing wetland classification. Numéro de notice : A2022-828 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.jag.2022.103095 Date de publication en ligne : 08/11/2022 En ligne : https://doi.org/10.1016/j.jag.2022.103095 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102012 [article]

Semi-supervised adversarial recognition of refined window structures for inverse procedural façade modelling / Han Hu in ISPRS Journal of photogrammetry and remote sensing, vol 192 (October 2022)  

Permalink

Single-image super-resolution for remote sensing images using a deep generative adversarial network with local and global attention mechanisms / Yadong Li in IEEE Transactions on geoscience and remote sensing, vol 60 n° 10 (October 2022)  

Permalink

Deep image deblurring: A survey / Kaihao Zhang in International journal of computer vision, vol 130 n° 9 (September 2022)  

Permalink

Segmentation and sampling method for complex polyline generalization based on a generative adversarial network / Jiawei Du in Geocarto international, vol 37 n° 14 ([20/07/2022])  

Permalink

GANmapper: geographical data translation / Abraham Noah Wu in International journal of geographical information science IJGIS, vol 36 n° 7 (juillet 2022)  

Permalink

Adversarial defenses for object detectors based on Gabor convolutional layers / Abdollah Amirkhani in The Visual Computer, vol 38 n° 6 (June 2022)  

Permalink

A GAN-based approach toward architectural line drawing colorization prototyping / Qian (Chayn) Sun in The Visual Computer, vol 38 n° 4 (April 2022)  

Permalink

PolGAN: A deep-learning-based unsupervised forest height estimation based on the synergy of PolInSAR and LiDAR data / Qi Zhang in ISPRS Journal of photogrammetry and remote sensing, vol 186 (April 2022)  

Permalink

Aboveground biomass of salt-marsh vegetation in coastal wetlands: Sample expansion of in situ hyperspectral and Sentinel-2 data using a generative adversarial network / Chen Chen in Remote sensing of environment, vol 270 (March 2022)  

Permalink

Neural map style transfer exploration with GANs / Sidonie Christophe in International journal of cartography, vol 8 n° 1 (March 2022)  

Permalink