Centre de documentation
scientifique

Improving deep learning on point cloud by maximizing mutual information across layers / Di Wang in Pattern recognition, vol 131 (November 2022)  

Public [article]  inPattern recognition > vol 131 (November 2022) . - n° 108892 Titre : Improving deep learning on point cloud by maximizing mutual information across layers Type de document : Article/Communication Auteurs : Di Wang, Auteur ; Lulu Tang, Auteur ; Xu Wang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 108892 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] détection d'objet [Termes IGN] entropie de Shannon [Termes IGN] information sémantique [Termes IGN] segmentation sémantique [Termes IGN] semis de points [Termes IGN] transformation géométrique [Termes IGN] vision par ordinateur [Termes IGN] visualisation 3D Résumé : (auteur) It is a fundamental and vital task to enhance the perception capability of the point cloud learning network in 3D machine vision applications. Most existing methods utilize feature fusion and geometric transformation to improve point cloud learning without paying enough attention to mining further intrinsic information across multiple network layers. Motivated to improve consistency between hierarchical features and strengthen the perception capability of the point cloud network, we propose exploring whether maximizing the mutual information (MI) across shallow and deep layers is beneficial to improve representation learning on point clouds. A novel design of Maximizing Mutual Information (MMI) Module is proposed, which assists the training process of the main network to capture discriminative features of the input point clouds. Specifically, the MMI-based loss function is employed to constrain the differences of semantic information in two hierarchical features extracted from the shallow and deep layers of the network. Extensive experiments show that our method is generally applicable to point cloud tasks, including classification, shape retrieval, indoor scene segmentation, 3D object detection, and completion, and illustrate the efficacy of our proposed method and its advantages over existing ones. Our source code is available at https://github.com/wendydidi/MMI.git. Numéro de notice : A2022-780 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : https://doi.org/10.1016/j.patcog.2022.108892 Date de publication en ligne : 08/07/2022 En ligne : https://doi.org/10.1016/j.patcog.2022.108892 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101859 [article]

Experiencing virtual geographic environment in urban 3D participatory e-planning: A user perspective / Thibaud Chassin in Landscape and Urban Planning, vol 224 (August 2022)  

Public [article]  inLandscape and Urban Planning > vol 224 (August 2022) . - n° 104432 Titre : Experiencing virtual geographic environment in urban 3D participatory e-planning: A user perspective Type de document : Article/Communication Auteurs : Thibaud Chassin, Auteur ; Jens Ingensand, Auteur ; Sidonie Christophe , Auteur ; Guillaume Touya , Auteur Année de publication : 2022 Projets : 3-projet - voir note / Article en page(s) : n° 104432 Note générale : bibliographie This study was partly funded by the Computers & Geosciences Research Scholarships co-sponsored by Elsevier and the International Association for Mathematical Geosciences (IAMG). Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] approche participative [Termes IGN] cognition [Termes IGN] environnement géographique virtuel [Termes IGN] projet urbain [Termes IGN] urbanisme [Termes IGN] utilisateur [Termes IGN] visualisation 3D Résumé : (auteur) The adoption of technology in urban participatory planning with tools such as Virtual Geographic Environments (VGE) promises a broader engagement of urban dwellers, which should ultimately lead to the creation of better cities. However, the authorities and urban experts show hesitancy in endorsing these tools in their practices. Indeed, several parameters must be wisely considered in the design of VGE; if misjudged, their impact could be damaging for the participatory approach and the related urban project. The objective of this study is to engage participants (N = 107) with common tasks conducted in participatory sessions, in order to evaluate the users’ performance when manipulating a VGE. We aimed at assessing three crucial parameters: (1) the VGE representation, (2) the participants’ idiosyncrasies, and (3) the nature of the VGE format. The results demonstrate that the parameters did not affect the same aspect of users’ performance in terms of time, inputs, and correctness. The VGE representation impacts only the time needed to fulfill a task. The participants’ idiosyncrasies, namely age, gender and frequency of 3D use also induce an alteration in time, but spatial abilities seem to impact all characteristics of users’ performance, including correctness. Lastly, the nature of the VGE format significantly alters the time and correctness of users interactions. The results of this study highlight concerns about the inadequacies of the current VGE practices in participatory sessions. Moreover, we suggest guidelines to improve the design of VGE, which could enhance urban participatory planning processes, in order to create better cities. Numéro de notice : A2022-439 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : GEOMATIQUE/INFORMATIQUE/URBANISME Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.landurbplan.2022.104432 Date de publication en ligne : 18/04/2022 En ligne : https://doi.org/10.1016/j.landurbplan.2022.104432 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100758 [article]

Building Information Modelling (BIM) for property valuation: A new approach for Turkish Condominium Ownership / Nida Celik Simsek in Survey review, vol 54 n° 384 (May 2022)  

Public [article]  inSurvey review > vol 54 n° 384 (May 2022) . - pp 187 - 208 Titre : Building Information Modelling (BIM) for property valuation: A new approach for Turkish Condominium Ownership Type de document : Article/Communication Auteurs : Nida Celik Simsek, Auteur ; Bayram Uzun, Auteur Année de publication : 2022 Article en page(s) : pp 187 - 208 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cadastre étranger [Termes IGN] cadastre étranger [Termes IGN] évaluation foncière [Termes IGN] lever cadastral [Termes IGN] modélisation 3D du bâti BIM [Termes IGN] propriété foncière [Termes IGN] Turquie [Termes IGN] valeur économique [Termes IGN] visualisation 3D Résumé : (auteur) In Turkey, calculation of the factors affecting the value of the condominium units of a building via 2D architectural project data leads to problems. One of the biggest problem is the land share calculation. The aim of this study was to establish a mechanism by which the properties of the factors affecting the value can be determined mathematically and to arrive at a value-based land share. For this purpose, the study utilized a 3D virtual Building Information Modelling (BIM) model. The value factors and weights were determined via a questionnaire, 3D BIM model of the structure was created, metric values of the factors were calculated and the nominal values of the condominium units were calculated. This study demonstrate that a building nonexistent in the real world can be represented in a virtual environment and comparable information source can be presented to the expert who will carry out the valuation process. Numéro de notice : A2022-354 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/00396265.2021.1905251 Date de publication en ligne : 02/04/2021 En ligne : https://doi.org/10.1080/00396265.2021.1905251 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100552 [article]

3D geovisualization for visual analysis of urban climate / Sidonie Christophe in Cybergeo, European journal of geography, vol 2022 ([01/01/2022])  

Public [article]  inCybergeo, European journal of geography > vol 2022 [01/01/2022] . - n° 1008 Titre : 3D geovisualization for visual analysis of urban climate Titre original : Géovisualisation en 3D pour l'analyse visuelle du climat urbain Type de document : Article/Communication Auteurs : Sidonie Christophe , Auteur ; Jacques Gautier , Auteur ; Paul Chapron , Auteur ; Luke Riley, Auteur ; Valéry Masson, Auteur Année de publication : 2022 Projets : URCLIM / Masson, Valéry Article en page(s) : n° 1008 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse visuelle [Termes IGN] climat urbain [Termes IGN] données météorologiques [Termes IGN] données topographiques [Termes IGN] ilot thermique urbain [Termes IGN] morphologie urbaine [Termes IGN] visualisation 3D [Vedettes matières IGN] Géovisualisation Résumé : (Auteur) This paper is about the relevance of proposing geovisualization methods to visually integrate, co-visualize and interact with urban and meteorological data into a 3D environment, in order to support the visual analysis of the urban climate. Meteorological experts and researchers already face meteorological data and climate models analysis issues, at larger scales into the city: yet even if they have existing practices and tools to address these issues, they could take benefit from the knowledge and the methods from the Geovisualization domain, to complement these analyses by a visuospatial reasoning approach. In this paper, based on the knowledge of the expectations of the meteorological experts we are working with, we brought climate analysis into the city and visuospatial reasoning closer, on both heterogeneous urban and air temperature data(1). We reviewed the existing works regarding geovisualization of spatio-temporal phenomena and visualization of meteorological data (2). We then presented the different approaches we fulfilled to provide a 3D geovisualization environment and graphic representations, visually integrating both meteorological and spatial data. One provides style and interaction capacities on those data, enabling the interactive 3D exploration of their spatial and value distributions, throughout the city. Another geovisualization-design experiment is presented as a co-visualization of meteorological data and morphological indicators on 2.5D maps (3). These complementary approaches are presented and discussed with the meteorological experts, based on their relevance to tackle climate analysis at a larger scale and on the refinements required to extend their exploration capacities (4). Numéro de notice : A2022-270 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : GEOMATIQUE/IMAGERIE/URBANISME Nature : Article nature-HAL : ArtAvecCL-RevueNat DOI : 10.4000/cybergeo.38518 Date de publication en ligne : 17/03/2022 En ligne : https://doi.org/10.4000/cybergeo.38518 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100206 [article]

ALEGORIA: Joint multimodal search and spatial navigation into the geographic iconographic heritage / Florent Geniet (2022)  

Public Titre : ALEGORIA: Joint multimodal search and spatial navigation into the geographic iconographic heritage Type de document : Article/Communication Auteurs : Florent Geniet, Auteur ; Valérie Gouet-Brunet , Auteur ; Mathieu Brédif , Auteur Editeur : New York [Etats-Unis] : Association for computing machinery ACM Année de publication : 2022 Projets : Alegoria / Gouet-Brunet, Valérie Conférence : MM 2022, 30th ACM International Conference on Multimedia 10/10/2022 14/10/2022 Lisbonne Portugal Proceedings ACM Importance : pp 6982 - 6984 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] géolocalisation [Termes IGN] image ancienne [Termes IGN] moteur de recherche [Termes IGN] photographie aérienne oblique [Termes IGN] plateforme logicielle [Termes IGN] visualisation 3D Résumé : (auteur) In this article, we present two online platforms developed for the structuring and valorization of old geographical iconographic collections: a multimodal search engine for their indexing, retrieval and interlinking, and a 3D navigation platform for their visualization in spatial context. In particular, we show how the joint use of these functionalities, guided by geolocation, brings structure and knowledge to the manipulated collections. In the demonstrator, they consist of 54,000 oblique aerial photographs from several French providers (national archives, a museum and a mapping agency). Numéro de notice : C2022-042 Affiliation des auteurs : UGE-LASTIG (2020- ) Autre URL associée : vers HAL Thématique : GEOMATIQUE/IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1145/3503161.3547746 Date de publication en ligne : 10/10/2022 En ligne : https://doi.org/10.1145/3503161.3547746 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101906

Visualisation spatio-temporelle de données COVID-19 / Aymeric Dutremble (2022) 

Permalink

A web GIS-based integration of 3D digital models with linked open data for cultural heritage exploration / Ikrom Nishanbaev in ISPRS International journal of geo-information, vol 10 n° 10 (October 2021)  

Permalink

Mise en place d'un dispositif expérimental numérique pour l'enseignement des risques naturels avec le jeu vidéo Minetest / Jérôme Staub in Cartes & Géomatique, n° 245-246 (septembre - décembre 2021)

Permalink

Digital camera calibration for cultural heritage documentation: the case study of a mass digitization project of religious monuments in Cyprus / Evagoras Evagorou in European journal of remote sensing, vol 54 sup 1 (2021)  

Permalink

La géovisualisation de données massives sur le Web : entre avancées technologiques et évolutions cartographiques / Boris Mericskay in Mappemonde, n° 131 (juillet 2021)  

Permalink

Imaging the subsurface: How different visualizations of cross-sections affect the sense of uncertainty / Ane Bang-Kittilsen in Journal of Geovisualization and Spatial Analysis, vol 5 n° 1 (June 2021)  

Permalink

Walking through the forests of the future: using data-driven virtual reality to visualize forests under climate change / Jiawei Huang in International journal of geographical information science IJGIS, vol 35 n° 6 (June 2021)  

Permalink

Restituer les bidonvilles de Nanterre : l’apport d’un outil de visualisation 3D à un projet de sciences sociales / Paul Lecat in Humanités numériques, n° 3 (2021)  

Permalink

Web‐based real‐time visualization of large‐scale weather radar data using 3D tiles / Mingyue Lu in Transactions in GIS, Vol 25 n° 1 (February 2021)  

Permalink

Conception d’un outil de visualisation 3D et de visite virtuelle orienté web / Elisa Lembert (2021)  

Permalink