Centre de documentation
scientifique

Generating urban morphologies at large scales / Juste Raimbault (2019)    

Public Titre : Generating urban morphologies at large scales Type de document : Article/Communication Auteurs : Juste Raimbault, Auteur ; Julien Perret , Auteur Editeur : Cambridge [Massachusetts - Etats-Unis] : MIT Press Année de publication : 2019 Projets : DynamiCity / Conférence : Alife 2019, Conference on Artificial life 29/07/2019 02/08/2019 Newcastle Royaume-Uni Open Access Proceedings Importance : 8 p. Format : 21 x 30 cm Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] Europe (géographie politique) [Termes IGN] grande échelle [Termes IGN] indicateur [Termes IGN] modèle numérique [Termes IGN] modélisation de processus [Termes IGN] morphologie mathématique [Termes IGN] morphologie urbaine [Termes IGN] OpenStreetMap [Termes IGN] reconnaissance de formes [Termes IGN] zone urbaine Résumé : (Auteur) At large scales, typologies of urban form and corresponding generating processes remain an open question with important implications regarding urban planning policies and sustainability. We propose in this paper to generate urban configurations at large scales, typically of districts, with morphogene-sis models, and compare these to real configurations according to morphological indicators. Real values are computed on a large sample of districts taken in European urban areas. We calibrate each model and show their complementarity to approach the variety of real urban configurations, paving the way to multi-model approaches of urban morphogenesis. Numéro de notice : C2019-013 Affiliation des auteurs : LASTIG COGIT+Ext (2012-2019) Autre URL associée : vers HAL Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1162/isal_a_00159 En ligne : https://doi.org/10.1162/isal_a_00159 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93262

Documents numériques

en open access Generating urban morphologies at large scales - pdf auteur Adobe Acrobat PDF

Deep learning / Ian Goodfellow (2016)  

Public Titre : Deep learning Type de document : Guide/Manuel Auteurs : Ian Goodfellow, Auteur ; Yoshua Bengio, Auteur ; Aaron Courville, Auteur Editeur : Cambridge [Massachusetts - Etats-Unis] : MIT Press Année de publication : 2016 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle [Termes IGN] algèbre linéaire [Termes IGN] apprentissage profond [Termes IGN] inférence [Termes IGN] méthode de Monte-Carlo [Termes IGN] réseau neuronal artificiel [Termes IGN] réseau neuronal convolutif Résumé : (auteur) The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular. The online version of the book is now complete and will remain available online for free. Numéro de notice : 17527 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Manuel de cours En ligne : http://www.deeplearningbook.org Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90631

Pose imagery and automated three-dimensional modeling of urban environments / Satyan R. Coorg (1998)

Public Titre : Pose imagery and automated three-dimensional modeling of urban environments Type de document : Thèse/HDR Auteurs : Satyan R. Coorg, Auteur Editeur : Cambridge [Massachusetts - Etats-Unis] : MIT Press Année de publication : 1998 Importance : 121 p. Format : 21 x 30 cm Note générale : bibliographie Thesis submitted to the Department of Electrical Engineering and Computer Science in Partial fulfillment of the requirements for the degree of Doctor of Philosophy at the Massachusetts Institute of Technology Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] estimation de pose [Termes IGN] extraction automatique [Termes IGN] façade [Termes IGN] modélisation 3D [Termes IGN] monde virtuel [Termes IGN] mosaïque d'images [Termes IGN] positionnement par GPS [Termes IGN] vision par ordinateur [Termes IGN] zone urbaine Résumé : (auteur) Three-dimensional (3-D) modeling of urban environments has numerous applications, including virtual environments, urban planning, and physical simulation. Construct-ing 3-D models from photographs (images) is thus an important area of research in computer vision, and increasingly, computer graphics. However, despite many years of research, a system that automatically recovers realistic 3-D models remains elusive; most practical systems require significant human input. Unlike automatic algorithms, human-assisted systems are not scalable, both in terms of the number of images processed and the complexity of the generated 3-D model. This thesis describes novel techniques to automatically extract textured 3-D mod-els of urban environments from pose imagery, i.e., images annotated with camera position and orientation in a single global coordinate system. Physical instruments (e.g., surveying, Global Positioning System (GPS), inertial sensors, etc.) are used to provide accurate initial pose estimates to the proposed algorithms. As these es-timates are not perfect, I first describe two optimization techniques that refine pose estimates using information present in the images: spherical mosaicing recovers rel-ative rotations between images taken from a single position, and mosaic registration accurately locates mosaics in a global coordinate system. Next, I describe an algo-rithm that extracts vertical facades from mosaics annotated with accurate pose. The algorithm employs horizontal line segments to detect likely facade orientations and locates these facades using a space-sweep technique. Textures are robustly computed for the facades by combining information from several mosaics using median statistics. I present results for a large pose image dataset (consisting of about four thousand images taken from eighty-one positions) of an urban office complex. These techniques were successful in recovering all significant vertical facades in the complex, as well as several neighboring facades. Numéro de notice : 25546 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : PhD Thesis : Electrical Engineering and Computer Science : Cambridge : Etats-Unis : 1998 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94426

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
25546-01	K321	Livre	Saint-Mandé	Dépôt en unité	Exclu du prêt