Descripteur
Termes IGN > informatique > génie logiciel
génie logicielSynonyme(s)Ingénierie logicielle ;ingénierie du logiciel génie du logicielVoir aussi |
Documents disponibles dans cette catégorie (906)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Data-driven feature learning for high resolution urban land-cover classification / Piotr Andrzej Tokarczyk (2015)
Titre : Data-driven feature learning for high resolution urban land-cover classification Type de document : Thèse/HDR Auteurs : Piotr Andrzej Tokarczyk, Auteur Editeur : Zurich : Eidgenossische Technische Hochschule ETH - Ecole Polytechnique Fédérale de Zurich EPFZ Année de publication : 2015 Collection : Dissertationen ETH num. 22544 Format : 21 x 30 cm Note générale : bibliographie
A thesis submitted to attain the degree of doctor of sciences of ETH ZurichLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] analyse en composantes principales
[Termes IGN] classification dirigée
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] environnement de développement
[Termes IGN] image à très haute résolution
[Termes IGN] image à ultra haute résolution
[Termes IGN] milieu urbain
[Termes IGN] occupation du sol
[Termes IGN] prise en compte du contexte
[Termes IGN] ruissellement
[Termes IGN] surface imperméable
[Termes IGN] théorie de Dempster-ShaferRésumé : (auteur) Automated classification of aerial and satellite images is one of the fundamental challenges in remote sensing research. Over the last 30 years, researchers have tried to overcome the tedious and time consuming manual interpretation of images. With the advent of digital technologies, classification approaches facilitating image interpretation have emerged. They were quickly embraced, and nowadays classification of remote sensing imagery is a mature field with many well-established methods. However, a major yet largely unsolved problem is the design and selection of features, that would be appropriate for a specific classification task. Usually, it is not known in advance which image features would help separating object classes in an optimal way and manual feature by trial and error is still a common practice. In the last decade rapid development of remote sensing sensors gave the end-user access to very high resolution imagery. At a ground sampling distance below a meter, small objects and ne-grained texture of larger objects emerge. Thus, to properly exploit the information that these images contain, additional contextual and textural properties of objects should be extracted. Unfortunately, classification of such images is often performed using features tailored to low- and medium resolution sensors: raw pixel values, usually augmented with either simple band ratios (e.g. in form of vegetation indices), or specific texture filter banks (e.g. Gabor filters).
In this thesis, we consider the problem of feature design and selection for classification of urban land-cover from very high resolution (VHR) remote sensing images. To appropriately capture characteristic object patterns, we propose a set of simple and efficient features, called random quasi-exhaustive (RQE) feature bank. It consists of a multitude of multiscale texture features computed efficiently via integral images inside a sliding window. At the same time, we propose to sidestep manual feature selection, and let a boosting classifier choose only those features from a RQE feature bank that are able to efficiently discriminate between different object classes in a specific classification task. We believe that the proposed feature set is fairly generic to many urban remote sensing datasets, such that the features selected by the classifier can be adapted to the characteristics of a certain image: different lighting or different scene structures.
We start with presenting the developed framework for supervised classification of land-cover in urban environments. We demonstrate the efficiency of a boosting classifier used in conjunction with the RQE feature databank on five different very high resolution remote sensing datasets. Next, we move from supervised feature learning to unsupervised methods. Using random forest classifier, we investigate the performance of features extracted using data-driven methods, such as principal component analysis (PCA) or Deep Belief Networks (DBN). We show that, at least in our study, complex unsupervised and non-linear feature learning did not improve classification accuracy over standard linear baseline methods. Finally, we use the developed supervised classification framework for an application in the field of urban hydrology. We produce imperviousness maps, which are then used to model rainfall-runoff processes in urban catchments. We show that the proposed method yields results superior over state-of-the-art methods in the field of urban hydrology. Furthermore, we perform an end-to-end comparison, in which different image data sources produced using different classification methods are used as an input for a hydraulic sewer model.Numéro de notice : 17202 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : Doctoral thesis : Sciences : ETH Zurich : 2015 En ligne : http://dx.doi.org/10.3929/ethz-a-010414770 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81178
Titre : Data structures and algorithms with Python Type de document : Guide/Manuel Auteurs : Kent D. Lee, Auteur ; Steve Hubbard, Auteur Editeur : Berlin, Heidelberg, Vienne, New York, ... : Springer Année de publication : 2015 Collection : Undergraduate Topics in Computer Science UTICS, ISSN 2197-1781 Importance : 363 p. ISBN/ISSN/EAN : 978-3-319-13072-9 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Informatique
[Termes IGN] algorithmique
[Termes IGN] modèle logique de données
[Termes IGN] programmation informatique
[Termes IGN] Python (langage de programmation)Résumé : (Editeur) This clearly structured and easy to read textbook explains the concepts and techniques required to write programs that can handle large amounts of data efficiently. Project-oriented and classroom-tested, the book presents a number of important algorithms supported by motivating examples that bring meaning to the problems faced by computer programmers. The idea of computational complexity is also introduced, demonstrating what can and cannot be computed efficiently so that the programmer can make informed judgements about the algorithms they use. The text assumes some basic experience in computer programming and familiarity in an object-oriented language, but not necessarily with Python.
Topics and features: Includes both introductory and advanced data structures and algorithms topics, with suggested chapter sequences for those respective courses provided in the preface
Provides learning goals, review questions and programming exercises in each chapter, as well as numerous illustrative examples
Offers downloadable programs and supplementary files at an associated website, with instructor materials available from the author
Presents a primer on Python for those coming from a different language background
Reviews the use of hashing in sets and maps, along with an examination of binary search trees and tree traversals, and material on depth first search of graphs
Discusses topics suitable for an advanced course, such as membership structures, heaps, balanced binary search trees, B-trees and heuristic search
Students of computer science will find this clear and concise textbook to be invaluable for undergraduate courses on data structures and algorithms, at both introductory and advanced levels. The book is also suitable as a refresher guide for computer programmers starting new jobs working with Python.Numéro de notice : 26287 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE/MATHEMATIQUE Nature : Manuel informatique DOI : 10.1007/978-3-319-13072-9 En ligne : https://doi.org/10.1007/978-3-319-13072-9 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94946 Detection and correction of inconsistencies between river networks and contour data by spatial constraint knowledge / Tinghua Ai in Cartography and Geographic Information Science, Vol 42 n° 1 (January 2015)
[article]
Titre : Detection and correction of inconsistencies between river networks and contour data by spatial constraint knowledge Type de document : Article/Communication Auteurs : Tinghua Ai, Auteur ; Min Yang, Auteur ; Xiang Zhang, Auteur ; Jing Tian, Auteur Année de publication : 2015 Article en page(s) : pp 79 - 93 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique
[Termes IGN] cohérence des données
[Termes IGN] programmation par contraintes
[Termes IGN] réseau fluvialRésumé : (auteur) In the representation of topographic data, the distribution of hydrographic networks should be constrained by the contour model’s landform features. During the integration of topographic databases, however, spatial conflicts may destroy these constraints, generating inconsistencies. This study presents a method to detect and correct inconsistencies between river networks and contour data by spatial knowledge. First, structured terrain features are extracted from the contour-based geometric representation and matching relationships between rivers and contours are constructed based on spatial knowledge of the distribution of rivers and talwegs. We then propose a distance metric for measuring differences and identifying inconsistencies between the matched river and contour features. Three correction approaches are provided for different inconsistency situations, including river adjustment referenced to the contour, contour adjustment referenced to the river and adjustment of both river and contour to middle positions. We apply the proposed method to the integration and maintenance of national topographic infrastructure in order to demonstrate its effectiveness. Numéro de notice : A2015-235 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/15230406.2014.956673 En ligne : https://doi.org/10.1080/15230406.2014.956673 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=76228
in Cartography and Geographic Information Science > Vol 42 n° 1 (January 2015) . - pp 79 - 93[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 032-2015011 RAB Revue Centre de documentation En réserve L003 Disponible Detection of potential updates of authoritative spatial databases by fusion of Volunteered Geographical Information from different sources / Stefan Ivanovic (2015)
Titre : Detection of potential updates of authoritative spatial databases by fusion of Volunteered Geographical Information from different sources Type de document : Article/Communication Auteurs : Stefan Ivanovic (1988 - 2020) , Auteur ; Ana-Maria Olteanu-Raimond , Auteur ; Sébastien Mustière , Auteur ; Thomas Devogele , Auteur Editeur : Milan : Politechnico di Milano Année de publication : 2015 Collection : Geomatics workbooks (Laboratorio di geomatica), ISSN 1591-092X num. 12 Conférence : FOSS4G 2015 Europe conference, Free and open-source software for geospatial 15/07/2015 17/07/2015 Como Italie open access abstracts Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées
[Termes IGN] analyse comparative
[Termes IGN] appariement automatique
[Termes IGN] détection automatique
[Termes IGN] données localisées de référence
[Termes IGN] données localisées des bénévoles
[Termes IGN] Géoxygène (plateforme de généralisation)
[Termes IGN] mise à jour de base de données
[Termes IGN] PostgreSQL
[Termes IGN] précision de localisation
[Termes IGN] qualité des données
[Termes IGN] sport
[Termes IGN] trace GPSRésumé : (auteur) Nowadays, needs for very up to date referential spatial data increase significantly. Thus, a continuous update of authoritative spatial databases becomes highly demanding task in both aspects, technical and financial. In the same time, alternative sources of spatial data, such as Volunteered Geographical Information – VGI (Goodchild, 2007) seems to be suitable solution. This data is easy available and is being collected in almost every moment somewhere in the world. The main objective of our research is proposing a method for identifying potential updates in authoritative spatial databases using VGI data, more precisely GPS tracks. We identified walkway and tractor as very challenging types of roads for continuous update due to their intermittent nature (e.g. they appear and disappear very often) and various landscape (e.g. forest, high mountains, seashore, etc.). Even though, these types of roads are not of the highest priority for a national mapping agency, they are still very important for production of touristic maps and for other different applications such as defense, sport activities, etc. That is why we have focused on GPS traces obtained in sport activities. To detect potential update, links between similar features need to be defined. This step consists in applying a data matching algorithm in order to match VGI and authoritative data. Then, the question of VGI tracks quality arises. Furthermore, VGI traces are collected without any specified procedures, less or inexistent metadata, usually by low class GPS devices. Hence, heterogeneity of data is very high as well as spatial inaccuracy. In this work we focus on examination of data quality, especially on its spatial and temporal aspects. First, we present an overview of VGI data sources (websites) and the heterogeneities that characterize them. In terms of data, we can rely on spatiotemporal data (i.e. coordinates and sometimes elevation and timestamps) as well as on a variety of descriptive information in text format such as: type of activity, difficulty, trace description etc. Second, providing a comprehensive analysis of elements which affect GPS data quality is necessary. Sources of errors related to technical aspect of GPS data collection are partially important for our work. Since we use data obtained by low class GPS receivers, which positional accuracy is at meter level, we are not concerned about the sources that affect the accuracy at sub-meter level. Therefore, our attention is directed to identifying and classifying sources of errors according to which extent they affect positional accuracy of GPS tracks. Finally, we are interested in evaluation of data quality by analyzing VGI data itself, without comparing it to referential data. Thus, we tend to obtain the more statistical indicators of data quality that we can, such as indicators of: spatial dispersion, precision, reliability, correlation between data etc. As a result, a process of automatic collection of GPS traces from web-sites and storing them into PostgreSQL database was created. Evaluation of data quality is conducted by using an open source platform GeOxygene, developed by COGIT laboratory. Numéro de notice : C2015-040 Affiliation des auteurs : LASTIG COGIT+Ext (2012-2019) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComSansActesPubliés-Unpublished DOI : sans En ligne : http://geomatica.como.polimi.it/workbooks/n12/ Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83204 Documents numériques
en open access
Detection of potential updates - résuméAdobe Acrobat PDF Détermination GNSS de bornes de la frontière de la Guyane française dans le cadre du « raid des 7 bornes », version 1 / Samuel Branchu (2015)
Titre : Détermination GNSS de bornes de la frontière de la Guyane française dans le cadre du « raid des 7 bornes », version 1 Type de document : Rapport Auteurs : Samuel Branchu, Auteur Mention d'édition : Version 1 Editeur : Saint-Mandé : Institut national de l'information géographique et forestière - IGN (2012-) Année de publication : 2015 Collection : Publications techniques en géodésie Sous-collection : Rapports techniques num. 28547 Importance : 10 p. Format : 21 x 30 cm Langues : Français (fre) Descripteur : [Vedettes matières IGN] Systèmes de référence et réseaux
[Termes IGN] Bernese
[Termes IGN] borne géodésique
[Termes IGN] Brésil
[Termes IGN] délimitation de frontière
[Termes IGN] Guyane française
[Termes IGN] positionnement par GNSS
[Termes IGN] réseau géodésique français de Guyane 1995Résumé : (auteur) Ce document présente les calculs GNSS réalisés à l'IGN pour déterminer les coordonnées de bornes observées dans le cadre du « raid des 7 bornes » pour la délimitation de la frontière terrestre entre le Brésil et la Guyane française, dirigé par François-Michel Le Tourneau, directeur de recherche au CNRS. Note de contenu : 1. Introduction
2. Les sessions d'observations GNSS
3. Les traitements
3.1. Données de référence
3.2. Paramétrage du Bernese pour une session
4. les résultats
4.1. Qualité des observations et des résultats
4.2. Coordonnées RGFG95Numéro de notice : 19736 Affiliation des auteurs : IGN (2012-2019) Thématique : POSITIONNEMENT Nature : Rapport de mission Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84076 Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 19736-01 7D Livre SGM K001 Exclu du prêt Documents numériques
peut être téléchargé
Détermination GNSS de bornes de la frontière de la Guyane française dans le cadre du « raid des 7 bornes »Adobe Acrobat PDF Determination of precise satellite orbits and geodetic parameters using satellite laser ranging / Krzysztof Sosnica (2015)PermalinkDomain-driven co-location mining / Frédéric Flouvat in Geoinformatica, vol 19 n° 1 (January - March 2015)PermalinkPermalinkEnjeux et problématiques de conception d’un jeu sérieux pour la prise de décision / Thomas Constant in Ingénierie des systèmes d'information, ISI : Revue des sciences et technologies de l'information, RSTI, vol 20 n° 1 (janvier - février 2015)PermalinkGéodésie multi-technique pour la surveillance haute fréquence de glissements de terrains / Pierre Boetzle (2015)PermalinkL’institut national de l’information géographique et forestière / Institut national de l'information géographique et forestière (2012 -) (2015)PermalinkIntégration et enrichissement des données de génie civil RATP avec l’API Géoportail / Baptiste Gomot (2015)PermalinkPermalinkLand cover dynamics monitoring with Landsat data in Kunming, China: a cost-effective sampling and modelling scheme using Google Earth imagery and random forests / Ning Lu in Geocarto international, vol 30 n° 1 - 2 (January - February 2015)PermalinkA method based on graphic entity for visualizing complex map symbols on the web / Jinqu Zhang in Cartography and Geographic Information Science, Vol 42 n° 1 (January 2015)Permalink