Centre de documentation
scientifique

Research on map emotional semantics using deep learning approach / Daping Xi in Cartography and Geographic Information Science, Vol 50 n° 5 (June 2023)  

Public [article]  inCartography and Geographic Information Science > Vol 50 n° 5 (June 2023) . - pp 465 - 480 Titre : Research on map emotional semantics using deep learning approach Type de document : Article/Communication Auteurs : Daping Xi, Auteur ; Xini Hu, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 465 - 480 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] apprentissage profond [Termes IGN] émotion [Termes IGN] réseau neuronal profond Résumé : (auteur) The main purpose of the research on map emotional semantics is to describe and express the emotional responses caused by people observing images through computer technology. Nowadays, map application scenarios tend to be diversified, and the increasing demand for emotional information of map users bring new challenges for cartography. However, the lack of evaluation of emotions in the traditional map drawing process makes it difficult for the resulting maps to reach emotional resonance with map users. The core of solving this problem is to quantify the emotional semantics of maps, it can help mapmakers to better understand map emotions and improve user satisfaction. This paper aims to perform the quantification of map emotional semantics by applying transfer learning methods and the efficient computational power of convolutional neural networks (CNN) to establish the correspondence between visual features and emotions. The main contributions of this paper are as follows: (1) a Map Sentiment Dataset containing five discrete emotion categories; (2) three different CNNs (VGG16, VGG19, and InceptionV3) are applied for map sentiment classification task and evaluated by accuracy performance; (3) six different parameter combinations to conduct experiments that would determine the best combination of learning rate and batch size; and (4) the analysis of visual variables that affect the sentiment of a map according to the chart and visualization results. The experimental results reveal that the proposed method has good accuracy performance (around 88%) and that the emotional semantics of maps have some general rules. Numéro de notice : A2023-235 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/15230406.2023.2172081 Date de publication en ligne : 21/02/2023 En ligne : https://doi.org/10.1080/15230406.2023.2172081 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103594 [article]

DeepSim-Nets: Deep Similarity Networks for stereo image matching / Mohamed Ali Chebbi (2023)  

Public Titre : DeepSim-Nets: Deep Similarity Networks for stereo image matching Type de document : Article/Communication Auteurs : Mohamed Ali Chebbi, Auteur ; Ewelina Rupnik , Auteur ; Marc Pierrot-Deseilligny , Auteur ; Paul Lopes, Auteur Editeur : Computer vision foundation CVF Année de publication : 2023 Conférence : CVPR 2023, IEEE Conference on Computer Vision and Pattern Recognition 18/06/2023 22/06/2023 Vancouver Colombie britannique - Canada OA Proceedings Importance : pp 2096 - 2104 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] appariement d'images [Termes IGN] chaîne de traitement [Termes IGN] géométrie de l'image [Termes IGN] géométrie épipolaire [Termes IGN] réseau neuronal profond Index. décimale : 35.20 Traitement d'image Résumé : (auteur) We present three multi-scale similarity learning architectures, or DeepSim networks. These models learn pixel-level matching with a contrastive loss and are agnostic to the geometry of the considered scene. We establish a middle ground between hybrid and end-to-end approaches by learning to densely allocate all corresponding pixels of an epipolar pair at once. Our features are learnt on large image tiles to be expressive and capture the scene's wider context. We also demonstrate that curated sample mining can enhance the overall robustness of the predicted similarities and improve the performance on radiometrically homogeneous areas. We run experiments on aerial and satellite datasets. Our DeepSim-Nets outperform the baseline hybrid approaches and generalize better to unseen scene geometries than end-to-end methods. Our flexible architecture can be readily adopted in standard multi-resolution image matching pipelines. The code is available at https://github.com/DaliCHEBBI/DeepSimNets. Numéro de notice : C2023-007 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE/INFORMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : https://openaccess.thecvf.com/content/CVPR2023W/EarthVision/html/Chebbi_DeepSim- [...] Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103281

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

A hierarchical deformable deep neural network and an aerial image benchmark dataset for surface multiview stereo reconstruction / Jiayi Li 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° 5600812 Titre : A hierarchical deformable deep neural network and an aerial image benchmark dataset for surface multiview stereo reconstruction Type de document : Article/Communication Auteurs : Jiayi Li, Auteur ; Xin Huang, Auteur ; Yujin Feng, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 5600812 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] approche hiérarchique [Termes IGN] carte de profondeur [Termes IGN] déformation d'objet [Termes IGN] effet de profondeur cinétique [Termes IGN] extraction de traits caractéristiques [Termes IGN] image aérienne [Termes IGN] jeu de données [Termes IGN] modèle numérique de surface [Termes IGN] modèle stéréoscopique [Termes IGN] reconstruction d'image [Termes IGN] réseau neuronal profond [Termes IGN] segmentation sémantique Résumé : (auteur) Multiview stereo (MVS) aerial image depth estimation is a research frontier in the remote sensing field. Recent deep learning-based advances in close-range object reconstruction have suggested the great potential of this approach. Meanwhile, the deformation problem and the scale variation issue are also worthy of attention. These characteristics of aerial images limit the applicability of the current methods for aerial image depth estimation. Moreover, there are few available benchmark datasets for aerial image depth estimation. In this regard, this article describes a new benchmark dataset called the LuoJia-MVS dataset ( https://irsip.whu.edu.cn/resources/resources_en_v2.php ), as well as a new deep neural network known as the hierarchical deformable cascade MVS network (HDC-MVSNet). The LuoJia-MVS dataset contains 7972 five-view images with a spatial resolution of 10 cm, pixel-wise depths, and precise camera parameters, and was generated from an accurate digital surface model (DSM) built from thousands of stereo aerial images. In the HDC-MVSNet network, a new full-scale feature pyramid extraction module, a hierarchical set of 3-D convolutional blocks, and “true 3-D” deformable 3-D convolutional layers are specifically designed by considering the aforementioned characteristics of aerial images. Overall and ablation experiments on the WHU and LuoJia-MVS datasets validated the superiority of HDC-MVSNet over the current state-of-the-art MVS depth estimation methods and confirmed that the newly built dataset can provide an effective benchmark. Numéro de notice : A2023-117 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2023.3234694 En ligne : https://doi.org/10.1109/TGRS.2023.3234694 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102488 [article]

Flash-flood hazard susceptibility mapping in Kangsabati River Basin, India / Rabin Chakrabortty in Geocarto international, vol 37 n° 23 ([15/10/2022])  

Public [article]  inGeocarto international > vol 37 n° 23 [15/10/2022] . - pp 6713 - 6735 Titre : Flash-flood hazard susceptibility mapping in Kangsabati River Basin, India Type de document : Article/Communication Auteurs : Rabin Chakrabortty, Auteur ; Subodh Chandra Pal, Auteur ; Fatemeh Rezaie, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 6713 - 6735 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] cartographie des risques [Termes IGN] Inde [Termes IGN] inondation [Termes IGN] mousson [Termes IGN] optimisation par essaim de particules [Termes IGN] réseau neuronal artificiel [Termes IGN] réseau neuronal profond [Termes IGN] risque naturel [Termes IGN] vulnérabilité Résumé : (auteur) Flood-susceptibility mapping is an important component of flood risk management to control the effects of natural hazards and prevention of injury. We used a remote-sensing and geographic information system (GIS) platform and a machine-learning model to develop a flood susceptibility map of Kangsabati River Basin, India where flash flood is common due to monsoon precipitation with short duration and high intensity. And in this subtropical region, climate change’s impact helps to influence the distribution of rainfall and temperature variation. We tested three models-particle swarm optimization (PSO), an artificial neural network (ANN), and a deep-leaning neural network (DLNN)-and prepared a final flood susceptibility map to classify flood-prone regions in the study area. Environmental, topographical, hydrological, and geological conditions were included in the models, and the final model was selected based on the relations between potentiality of causative factors and flood risk based on multi-collinearity analysis. The model results were validated and evaluated using the area under receiver operating characteristic (ROC) curve (AUC), which is an indicator of the current state of the environment and a value >0.95 implies a greater risk of flash floods. The AUC values for ANN, DLNN, and PSO for training datasets were 0.914, 0.920, and 0.942, respectively. Among these three models, PSO showed the best performance with an AUC value of 0.942. The PSO approach is applicable for flood susceptibility mapping of the eastern part of India, a subtropical region, to allow flood mitigation and help to improve risk management in this region. Numéro de notice : A2022-750 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2021.1953618 Date de publication en ligne : 26/07/2021 En ligne : https://doi.org/10.1080/10106049.2021.1953618 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101742 [article]

HyperNet: A deep network for hyperspectral, multispectral, and panchromatic image fusion / Kun Li in ISPRS Journal of photogrammetry and remote sensing, vol 188 (June 2022)  

Permalink

Interactive semantic segmentation of aerial images with deep neural networks / Gaston Lenczner (2022)  

Permalink

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)  

Permalink

A deep translation (GAN) based change detection network for optical and SAR remote sensing images / Xinghua Li in ISPRS Journal of photogrammetry and remote sensing, vol 179 (September 2021)  

Permalink

Two hidden layer neural network-based rotation forest ensemble for hyperspectral image classification / Laxmi Narayana Eeti in Geocarto international, vol 36 n° 16 ([01/09/2021])  

Permalink

Simulating multi-exit evacuation using deep reinforcement learning / Dong Xu in Transactions in GIS, Vol 25 n° 3 (June 2021)  

Permalink

Deep convolutional neural networks for scene understanding and motion planning for self-driving vehicles / Abdelhak Loukkal (2021)  

Permalink

Exploration of reinforcement learning algorithms for autonomous vehicle visual perception and control / Florence Carton (2021)  

Permalink

Representing shape collections with alignment-aware linear models / Romain Loiseau (2021)  

Permalink

A deep learning architecture for semantic address matching / Yue Lin in International journal of geographical information science IJGIS, vol 34 n° 3 (March 2020)  

Permalink