Descripteur
Termes IGN > mathématiques > statistique mathématique > régression > méthode des moindres carrés
méthode des moindres carrésSynonyme(s)moindres carrés |
Documents disponibles dans cette catégorie (389)
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
Etude de méthodes d'inversion des données du Tams (télémètre laser aéroporté à champ large) pour la surveillance des mouvements verticaux du sol / Luc Mathis (2002)
Titre : Etude de méthodes d'inversion des données du Tams (télémètre laser aéroporté à champ large) pour la surveillance des mouvements verticaux du sol Type de document : Mémoire Auteurs : Luc Mathis, Auteur Editeur : Champs-sur-Marne : Ecole nationale des sciences géographiques ENSG Année de publication : 2002 Importance : 81 p. Format : 21 x 30 cm Note générale : Bibliographie
Rapport de stage pluridisciplinaire, cycle des ingénieurs diplômés de l'ENSG 2ème année IT2Langues : Français (fre) Descripteur : [Vedettes matières IGN] Analyse numérique
[Termes IGN] algorithme de Gauss-Newton
[Termes IGN] convolution (signal)
[Termes IGN] déconvolution
[Termes IGN] inversion
[Termes IGN] méthode des moindres carrés
[Termes IGN] optimisation (mathématiques)
[Termes IGN] précision millimétrique
[Termes IGN] télémètre laser aéroporté
[Termes IGN] télémétrie laser aéroporté
[Termes IGN] traitement du signalIndex. décimale : PROJET Mémoires : Rapports de projet - stage des ingénieurs de 2e année Résumé : (Auteur) Le Laboratoire LOEMI de l'IGN a développé un télémètre laser aéroporté, à champ large, pour la surveillance des mouvements verticaux du sol (TAMS). Il permet de faire des mesures simultanées de distances depuis un avion ayant une altitude de 1000 à 10000 m d'altitude sur une zone de 100 réflecteurs répartis sur 10 à 100 km2. L'objectif est d'obtenir une précision millimétrique sur la composante verticale des cibles pour des durées de vol de 2 heures. Le traitement actuel des données comprend deux phases d'inversion par moindres carrés : l'estimation des distances avion-cibles à partir des signaux laser (déconvolutions des signaux) et l'estimation des coordonnées des cibles à partir de ces distances (multilatération). L'objectif du stage est d'étudier la première inversion, avec une analyse théorique et des simulations numériques qui utilisent un algorithme de moindres carrés non linéaires (Gauss-Newton), afin d'évaluer la précision de la méthode actuelle et de l'améliorer. La précision sur les distances obtenues après améliorations de la méthode (échantillonnage, critères de convergence, poids sur les paramètres, étude des échos superposés) et filtrage des données est de l'ordre de 3 cm pour un RSB de 10. Numéro de notice : 18106 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE Nature : Mémoire de projet pluridisciplinaire Organisme de stage : LOEMI (IGN) Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=50647 Réservation
Réserver ce documentExemplaires(2)
Code-barres Cote Support Localisation Section Disponibilité 18106-01 PROJET Livre Centre de documentation Travaux d'élèves Disponible 18106-02 PROJET Livre Centre de documentation Travaux d'élèves Disponible
Titre : Fast precise GPS positioning in the presence of ionospheric delays Type de document : Thèse/HDR Auteurs : Dennis Odijk, Auteur Editeur : Delft : Netherlands Geodetic Commission NGC Année de publication : 2002 Collection : Netherlands Geodetic Commission Publications on Geodesy, ISSN 0165-1706 num. 52 Importance : 242 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-90-6132-278-8 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale
[Termes IGN] ambiguïté entière
[Termes IGN] correction ionosphérique
[Termes IGN] correction troposphérique
[Termes IGN] données GPS
[Termes IGN] interpolation
[Termes IGN] krigeage
[Termes IGN] mesurage de phase
[Termes IGN] méthode des moindres carrés
[Termes IGN] modèle de Gauss-Markov
[Termes IGN] modèle ionosphérique
[Termes IGN] modèle stochastique
[Termes IGN] propagation ionosphérique
[Termes IGN] propagation troposphérique
[Termes IGN] réfraction atmosphérique
[Termes IGN] résolution d'ambiguïté
[Termes IGN] signal GPS
[Termes IGN] station virtuelle
[Termes IGN] traitement de données GNSS
[Termes IGN] traitement du signalIndex. décimale : 30.61 Systèmes de Positionnement par Satellites du GNSS Résumé : (Auteur) This thesis deals about geodetic applications of the Global Positioning System (GPS), in which the position of the GPS receiver must be determined with cm precision. This requires a relative measurement setup, together with an advanced processing strategy based on observations of the carrierphase of the signal. To keep it economically interesting, this CPS technique should be based on relatively short time spans in which the satellite observations are collected. The key to precise positioning using short time spans is to take advantage of the integer property of the ambiguities of the phase observations in the processing.
The above procedure has been applied in a successful way for the last decade to applications in which the distance between the receivers is restricted to about 10 km (the socalled rapidstatic and realtime kinematic GPS techniques over short distances). Above this distance, it is known that certain errors in the GPS observations start to significantly bias the computed receiver position when they are not taken care of. The aim of this research therefore is to develop a processing procedure, taking into account the errors in GPS observations due to propagation of the signals through the ionosphere, the atmospheric layer above about 80 kill. Although other errors (due to troposphere and satellite orbit) are of relevance as well, the research is restricted to an improved modelling of the ionospheric error. since it is by far the largest error. For the other errors standard modelling techniques are applied in this research. Using the procedure, it should be possible to determine the desired receiver positions with cmprecision using a short tinle span. The research is restricted to GPS receivers with a mutual distance of a few hundred km (mediumdistance baselines), located in midlatitude regions.
To facilitate a modelling of the ionospheric error, using the theor ' y of atmospheric refraction it is possible to decompose this error into a firstorder effect, which contains the gross of the error, plus some higherorder effects and a term due to bending of the signal path. Under worstcase conditions. the firstorder term may range up to about 80 m (on the GPS L2 frequency), whereas the accumulated effect of higherorder and bending terms can be tip to 4 cm (for L2). For the future L5 frequency (from 2008) these effects are even larger. Fortunately, because of the relative setup and the assumed medium distances, it is proved for this research it is allowed to neglect the higherorder and bending errors.
In the procedure a stochastic modelling of the firstorder ionospheric errors (referred to as ionospheric delays) is chosen. This means that the ionospheric delays are not modelled as completely unknown parameters, but that stochastic prior information is incorporated by means of ionospheric pseudoobservations. This model is referred to as the ionosphereweighted model: The weight of the ionospheric information can be tuned by the a priori standard deviation of the pseudoobservations. When this standard deviation is chosen zero, the ionosphereweighted model reduces to the ionospherefixed model, which is the usual processing model for shortdistance baselines (for which the ionospheric delays may be neglected). On the other hand, with an infinitely large ionospheric standard deviation, the model will be equivalent to the ionospherefloat model, in which the ionospheric delays are assumed as completely unknown parameters. This latter model is closely related to the ionospherefree combination, for which it is known that it cannot be used to achieve fast positioning results. It is shown that the ionosphereweighted model is only suitable for fast ambiguity resolution (and consequently positioning), when the ionospheric standard deviation is small. This requires very precise a priori ionospheric information.
The developed procedure consists of three steps. It is required that a user collects CPS observations in the vicinity of a network of permanent GPS stations. In the first step, the observations at the network stations are processed simultaneously using the ionosphereweighted model. Since in this research the goal is precise positioning within the shortest time span possible, i.e. instantaneous or singleepoch positioning, it is required that the network data is also processed instantaneously. To make instantaneous resolution of the network ambiguities possible, the sample values of the ionospheric pseudoobservations are temporal predictions based on estimates of previous epochs. Test computations using a network with a station spacing of more than 100 km demonstrated that in this way high network ambiguity success rates (close to 100%) can be obtained. In the second step, precise ambiguityfixed network ionospheric delays are spatially interpolated at the approximate location of the user's receiver. In the procedure for this purpose the concept of virtual reference station (VRS) observations is used. In this concept the network estimates (ionospheric delays and other parameters) are transformed to VRS observations. which should correspond to the data a real receiver would have collected at the user's location. The processing of the user's observations relative to this VRS is the third step of the procedure. Because of the presence of possible residual ionospheric delays also in this step the ionosphereweighted model is applied. The difference with the application in the network processing is that the sample values of the pseudoobservations are now taken zero. and the ionospheric standard deviation is computed as a function of the distance to the closest real network station. Using this, test computations demonstrated that instantaneous ambiguity success rates of 90% are feasible. When the ionospherefixed model would be applied, the success rates would not be higher than about 60%.Numéro de notice : 13101 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Thèse étrangère DOI : sans En ligne : https://www.ncgeo.nl/downloads/52Odijk.pdf Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=54884 Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 13101-01 30.61 Livre Centre de documentation Géodésie Disponible Inverse Probleme bei der Gravitationsfelsbestimmung mittels SST- und SGG-Satellitenmissionen Darstellungen / J. Kusche (2002)
Titre : Inverse Probleme bei der Gravitationsfelsbestimmung mittels SST- und SGG-Satellitenmissionen Darstellungen Titre original : [Problème inverse lors de la détermination du champ de gravitation au moyen des missions satellitaires SST et SGG] Type de document : Thèse/HDR Auteurs : J. Kusche, Auteur Editeur : Munich : Bayerische Akademie der Wissenschaften Année de publication : 2002 Collection : DGK - C Sous-collection : Dissertationen num. 548 Importance : 79 p. Format : 21 x 30 cm ISBN/ISSN/EAN : 978-3-7696-9585-4 Note générale : Bibliographie Langues : Allemand (ger) Descripteur : [Vedettes matières IGN] Géodésie physique
[Termes IGN] champ de gravitation
[Termes IGN] champ de pesanteur terrestre
[Termes IGN] covariance
[Termes IGN] fonction spline
[Termes IGN] gradiométrie
[Termes IGN] itération
[Termes IGN] méthode des moindres carrés
[Termes IGN] mission spatiale
[Termes IGN] problème inverseIndex. décimale : 30.40 Géodésie physique Résumé : (Auteur) We investigate certain problems of downward continuation, which arise in the context of modern SST- and SGG-satellite missions designed for geopotential field recovery, in a generalized context. Fast solution techniques are presented and analyzed.
First the mathematical foundations of the treatment of inverse and ill-posed problems are reviewed. Then we begin with the definition of SST and SGG model problems, whose ill-posedness or, more precisely, ill-conditioning will be quantified using the spectrum of the normal equations. Different representations of the anomalous gravity field lead to different degrees of ill-conditioning. Our focus is oil representation techniques with space-localizing properties, rather than studying the familiar frequency-localizing spherical harmonics. Tykhonov-regularization as an essential tool for computing reasonable solutions in ill-posed problems is extensively studied within this thesis, including the implementation of a posteriori strategies for the determination of the regularization parameter.
After that we consider iterative methods for the solution of the regularized normal equations, which emerge from Galerkin discretizations. Two of the fastest techniques - conjugate gradients and multigrid iterations are presented first within an abstract setting, but in the sequel we give matrix algorithms for multigrid standalone iteration as well as multigrid preconditioning for CG. For the first time in this application, convergence properties are evaluated theoretically using the model problems. Finally, we consider the implementation of a posteriori parameter choice rules for Tykhonov-regularization in the framework of our iterative solvers.Numéro de notice : 13098 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Thèse étrangère Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=54881 Réservation
Réserver ce documentExemplaires(2)
Code-barres Cote Support Localisation Section Disponibilité 13098-01 30.40 Livre Centre de documentation Géodésie Disponible 13098-02 30.40 Livre Centre de documentation Géodésie Disponible Mapping Dilution of Precision (MDOP) and map-matched GPS / Geoffrey Blewitt in International journal of geographical information science IJGIS, vol 16 n° 1 (january 2002)
[article]
Titre : Mapping Dilution of Precision (MDOP) and map-matched GPS Type de document : Article/Communication Auteurs : Geoffrey Blewitt, Auteur ; Georges E. Taylor, Auteur Année de publication : 2002 Article en page(s) : pp 55 - 67 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Navigation et positionnement
[Termes IGN] affaiblissement géométrique de la précision
[Termes IGN] appariement de cartes
[Termes IGN] correction
[Termes IGN] erreur de positionnement
[Termes IGN] GPS assisté pour la navigation (technologies)
[Termes IGN] GPS en mode différentiel
[Termes IGN] méthode des moindres carrés
[Termes IGN] navigation automobile
[Termes IGN] positionnement différentiel
[Termes IGN] véhicule automobileRésumé : (Auteur) A novel method of map matching using the Global Positioning System (GPS) has been developed which uses digital mapping and height data to augment point position computation. This method reduces the error in position, which is a sum from several sources, including signal delay due to the ionosphere and atmosphere and until recently from 'selective availability' (S/A). S/A was imposed by the US military to degrade purposefully the accuracy of GPS, but was switched off on 2 May 2000, and is to be replaced with 'regional denial capabilities in lieu of global degradation' (Interagency GPS Executive Board, 2000). Taylor et al. (2001) describe the Road Reduction Filter (RRF) in detail. RRF is a method of detecting the correct road on which a vehicle is travelling. In the work described here, the position error vector is estimated in a formal least squares procedure, as the vehicle is moving. This estimate is a map-matched correction, that provides an autonomous alternative to DGPS for in-car navigation and fleet management. In this paper, a formula is derived for 'Mapped Dilution of Precision' (MDOP), defined as the theoretical ratio of position precision using map-matched corrections to that using perfect Differential GPS (DGPS) correction. This is shown to be purely a function of route geometry, and is computed for examples of basic road shapes. MDOP is favourable unless the route has less than a few degrees curvature for several kilometres. MDOP can thus provide an objective estimate of positioning precision to a vehicle driver. Precision estimates using MDOP are shown to agree well with 'true' positioning errors determined using high precision (cm) GPS carrier phase techniques. The exact location of a vehicle on a road is essential for accurate surveying applications. These include close range photogrammetry using digital video or still cameras and the verification of digital mapping by measured (GPS and other sensors) trajectories. Numéro de notice : A2002-004 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.1080/13658810110075996 En ligne : https://doi.org/10.1080/13658810110075996 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=21921
in International journal of geographical information science IJGIS > vol 16 n° 1 (january 2002) . - pp 55 - 67[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 079-02011 RAB Revue Centre de documentation En réserve L003 Disponible Improving area-based matching by using surface gradients in the pixel co-ordinate transformation / M. Mustaffar in ISPRS Journal of photogrammetry and remote sensing, vol 56 n° 1 (May - June 2001)
[article]
Titre : Improving area-based matching by using surface gradients in the pixel co-ordinate transformation Type de document : Article/Communication Auteurs : M. Mustaffar, Auteur ; H.L. Mitchell, Auteur Année de publication : 2001 Article en page(s) : pp 42 - 52 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] appariement de formes
[Termes IGN] géométrie affine
[Termes IGN] méthode des moindres carrés
[Termes IGN] modèle géométrique
[Termes IGN] photogrammétrie métrologiqueRésumé : (Auteur) Area-based least squares matching has existed since the 1980s, and its development may therefore be regarded by some photogrammetrists as complete. However, this is a relatively short time in a rapidly changing discipline, and the method does have scope for further refinement. This paper aims to enhance the fidelity of the fundamental mathematical model, which relates pixel positions in area-based matching. If successful, its benefit is seen to lie within close-range photogrammetry, in which object undulations, convergent camera directions and large image scales can introduce significant levels of perspective distortion. It is hypothesised that a model, which takes into account the surface shape within the match window, would provide a pixel position relationship which is applicable across larger windows than those which are applicable with the conventional matching model, based on an affine transformation. The use of larger windows for the image matching increases the redundancy. Revised co-ordinate transformations, based on mathematical surface models across the windows, are proposed in this paper. When tested on the measurement of real objects, even simple surface models are found to increase the complexity of the matching mathematics, but when compared with the traditional affine transformation solution using three test objects, precision improved noticeably. Generally, accuracy also improved, but the improvements were not as distinct as they were for precision. Quicker convergence with fewer iterations was usually obtained, and this is seen as particularly indicative of a more faithful model. Yet more rigorous surface modelling may be worth developing, but the means of choosing the most appropriate models for different objects also remains a question deserving to be pursued. Copyright ISPRS Numéro de notice : A2001-219 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/S0924-2716(01)00034-X En ligne : https://doi.org/10.1016/S0924-2716(01)00034-X Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=21913
in ISPRS Journal of photogrammetry and remote sensing > vol 56 n° 1 (May - June 2001) . - pp 42 - 52[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 081-01021 SL Revue Centre de documentation Revues en salle Disponible An optimisation approach to cartographic generalisation / Lars Harrie (2001)PermalinkAnalysis of refraction influences in geodesy using image processing and turbulence models / Philipp Flach (2001)PermalinkClose range photogrammetry and machine vision / Keith B. Atkinson (2001)PermalinkEstimation par moindres carrés / Patrick Sillard (2001)PermalinkIntegrierte Modelle zur physikalischen Interpretation geodätischer Deformationsuntersuchungen / I. Milev (2001)PermalinkIntroduction to modern photogrammetry / E.M. Mikhail (2001)PermalinkParticipation à l'analyse des séries temporelles du système international de référence terrestre ITRS / G. Moujally (2001)PermalinkPermalinkError propagation modeling in raster GIS: adding and ratioing operations / Guiseppe Arbia in Cartography and Geographic Information Science, vol 26 n° 4 (October 1999)PermalinkEstimation par moindres carrés / Patrick Sillard (1998)Permalink