Descripteur
Termes IGN > mathématiques > statistique mathématique > probabilités > stochastique > méthode de Monte-Carlo > méthode de Monte-Carlo par chaînes de Markov
méthode de Monte-Carlo par chaînes de Markov |
Documents disponibles dans cette catégorie (18)
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
Titre : Robust hand pose recognition from stereoscopic capture Type de document : Thèse/HDR Auteurs : Rilwan Remilekun Basaru, Auteur Editeur : Londres : University of London Press Année de publication : 2018 Importance : 200 p. Format : 21 x 30 cm Note générale : bibliographie
A thesis submitted in fulfillment of the requirements for the degree of Doctor of Philosophy, Department of Computer Science, City, University of LondonLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] estimation de pose
[Termes IGN] image RVB
[Termes IGN] méthode de Monte-Carlo par chaînes de Markov
[Termes IGN] régression
[Termes IGN] réseau neuronal convolutif
[Termes IGN] réseau neuronal siamoisRésumé : (auteur) Hand pose is emerging as an important interface for human-computer interaction. The problem of hand pose estimation from passive stereo inputs has received less attention in the literature compared to active depth sensors. This thesis seeks to address this gap by presenting a data-driven method to estimate a hand pose from a stereoscopic camera input, with experimental results comparable to more expensive active depth sensors. The frameworks presented in this thesis are based on a two camera stereo rig capture as it yields a simpler and cheaper set-up and calibration. Three frameworks are presented, describing the sequential steps taken to solve the problem of depth and pose estimation of hands.
The first is a data-driven method to estimate a high quality depth map of a hand from a stereoscopic camera input by introducing a novel regression framework. The method first computes disparity using a robust stereo matching technique. Then, it applies a machine learning technique based on Random Forest to learn the mapping between the estimated disparity and depth given ground truth data. We introduce Eigen Leaf Node Features (ELNFs) that perform feature selection at the leaf nodes in each tree to identify features that are most discriminative for depth regression. The system provides a robust method for generating a depth image with an inexpensive stereo camera.
The second framework improves on the task of hand depth estimation from stereo capture by introducing a novel superpixel-based regression framework that takes advantage of the smoothness of the depth surface of the hand. To this end, it introduces Conditional Regressive Random Forest (CRRF), a method that combines a Conditional Random Field (CRF) and a Regressive Random Forest (RRF) to model the mapping from a stereo RGB image pair to a depth image. The RRF provides a unary term that adaptively selects different stereo-matching measures as it implicitly determines matching pixels in a coarse-to-fine manner. While the RRF makes depth prediction for each super-pixel independently, the CRF unifies the prediction of depth by modeling pair-wise interactions between adjacent superpixels.
The final framework introduces a stochastic approach to propose potential depth solutions to the observed stereo capture and evaluate these proposals using two convolutional neural networks (CNNs). The first CNN, configured in a Siamese network architecture, evaluates how consistent the proposed depth solution is to the observed stereo capture. The second CNN estimates a hand pose given the proposed depth. Unlike sequential approaches that reconstruct pose from a known depth, this method jointly optimizes the hand pose and depth estimation through Markov-chain Monte Carlo (MCMC) sampling. This way, pose estimation can correct for errors in depth estimation, and vice versa.
Experimental results using an inexpensive stereo camera show that the proposed system measures pose more accurately than competing methods. More importantly, it presents the possibility of pose recovery from stereo capture that is on par with depth based pose recovery.Numéro de notice : 17505 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère En ligne : https://openaccess.city.ac.uk/19938/ Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90396 Inverting Glacial Isostatic Adjustment signal using Bayesian framework and two linearly relaxing rheologies / Lambert Caron in Geophysical journal international, vol 209 n° 2 (May 2017)
[article]
Titre : Inverting Glacial Isostatic Adjustment signal using Bayesian framework and two linearly relaxing rheologies Type de document : Article/Communication Auteurs : Lambert Caron, Auteur ; Laurent Métivier , Auteur ; Marianne Greff-Lefftz, Auteur ; Luce Fleitout, Auteur ; Hélène Rouby , Auteur Année de publication : 2017 Projets : TOSCA / Article en page(s) : pp 1126 - 1147 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale
[Termes IGN] anomalie de pesanteur
[Termes IGN] calotte glaciaire
[Termes IGN] élasticité
[Termes IGN] gravimétrie spatiale
[Termes IGN] manteau terrestre
[Termes IGN] méthode de Monte-Carlo par chaînes de Markov
[Termes IGN] rebond post-glaciaire
[Termes IGN] rhéologieRésumé : (Auteur) Glacial Isostatic Adjustment (GIA) models commonly assume a mantle with a viscoelastic Maxwell rheology and a fixed ice history model. Here, we use a Bayesian Monte Carlo approach with a Markov chain formalism to invert the global GIA signal simultaneously for the mechanical properties of the mantle and the volumes of the ice sheets, using as starting ice models two previously published ice histories. Two stress relaxing rheologies are considered: Burgers and Maxwell linear viscoelasticities. A total of 5720 global palaeo sea level records are used, covering the last 35 kyr. Our goal is not only to seek the model best fitting this data set, but also to determine and display the range of possible solutions with their respective probability of explaining the data. In all cases, our a posteriori probability maps exhibit the classic character of solutions for GIA-determined mantle viscosity with two distinct peaks. What is new in our treatment is the presence of the bi-viscous Burgers rheology and the fact that we invert rheology jointly with ice history, in combination with the greatly expanded palaeo sea level records. The solutions tend to be characterized by an upper-mantle viscosity of around 5 × 1020 Pa s with one preferred lower-mantle viscosities at 3 × 1021 Pa s and the other more than 2 × 1022 Pa s, a rather classical pairing. Best-fitting models depend upon the starting ice history and the stress relaxing law. A first peak (P1) has the highest probability only in the case with a Maxwell rheology and ice history based on ICE-5G, while the second peak (P2) is favoured for ANU-based ice history or Burgers stress relaxation. The latter solution also may satisfy lower-mantle viscosity inferences from long-term geodynamics and gravity gradient anomalies over Laurentia. P2 is also consistent with large Laurentian and Fennoscandian ice-sheet volumes at the Last Glacial Maximum (LGM) and smaller LGM Antarctic ice volume than in either ICE-5G or ANU. Exploration of a bi-viscous linear relaxing rheology in GIA now seems logical due to a new set of requirements to satisfy observations of transient post-seismic flow seen so ubiquitously in space gravimetry and other global geodetic data. Numéro de notice : A2017-402 Affiliation des auteurs : LASTIG LAREG+Ext (2012-mi2018) Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1093/gji/ggx083 Date de publication en ligne : 27/02/2017 En ligne : https://doi.org/10.1093/gji/ggx083 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86108
in Geophysical journal international > vol 209 n° 2 (May 2017) . - pp 1126 - 1147[article]
Titre : Bayesian inference Type de document : Monographie Auteurs : Javier Prieto Tejedor, Éditeur scientifique Editeur : London [UK] : IntechOpen Année de publication : 2017 Importance : 378 p. Format : 19 x 27 cm ISBN/ISSN/EAN : 978-953-51-3578-4 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques
[Termes IGN] estimation bayesienne
[Termes IGN] filtrage bayésien
[Termes IGN] inférence statistique
[Termes IGN] méthode de Monte-Carlo par chaînes de Markov
[Termes IGN] régression
[Termes IGN] réseau bayesienRésumé : (éditeur) The range of Bayesian inference algorithms and their different applications has been greatly expanded since the first implementation of a Kalman filter by Stanley F. Schmidt for the Apollo program. Extended Kalman filters or particle filters are just some examples of these algorithms that have been extensively applied to logistics, medical services, search and rescue operations, or automotive safety, among others. This book takes a look at both theoretical foundations of Bayesian inference and practical implementations in different fields. It is intended as an introductory guide for the application of Bayesian inference in the fields of life sciences, engineering, and economics, as well as a source document of fundamentals for intermediate Bayesian readers. Note de contenu : 1- Bayesian inference application
2- Node-level conflict measures in Bayesian hierarchical models based on directed acyclic graphs
3- Classifying by Bayesian method and some applications
4- Hypothesis testing for high-dimensional problems
5- Bayesian vs frequentist power functions to determine the optimal sample size: testing one sample binomial proportion using exact methods
6- Converting graphic relationships into conditional probabilities in Bayesian network
7- Bayesian estimation of multivariate autoregressive hidden Markov model with application to breast cancer biomarker modeling
8- Bayesian model averaging and compromising in dose-response studies
9- Two examples of Bayesian evidence synthesis with the hierarchical meta-regression approach
10- Bayesian modeling in genetics and genomicsvvv
11- Bayesian two-stage robust causal modeling with instrumental variables using student's t distributions
12- Bayesian hypothesis testing: an alternative to null hypothesis significance testing (NHST) in psychology and social sciences
13- Bayesian inference and compressed sensing
14- Sparsity in Bayesian signal estimation
15- Dynamic Bayesian network for time-dependent classification problems in robotics
16- A Bayesian model for investment decisions in early ventures
17- Recent advances in nonlinear filtering with a financial application to derivatives hedging under incomplete information
18- Airlines content recommendations based on passengers' choice using Bayesian belief networksNuméro de notice : 25957 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE Nature : Recueil / ouvrage collectif DOI : 10.5772/66264 En ligne : https://doi.org/10.5772/66264 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96464 Modeling spatial and temporal variabilities in hyperspectral image unmixing / Pierre-Antoine Thouvenin (2017)
Titre : Modeling spatial and temporal variabilities in hyperspectral image unmixing Type de document : Thèse/HDR Auteurs : Pierre-Antoine Thouvenin, Auteur ; Nicolas Dobigeon, Directeur de thèse ; Jean-Yves Tourneret, Directeur de thèse Editeur : Toulouse : Université de Toulouse Année de publication : 2017 Importance : 191 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse en vue de l'obtention du Doctorat de l'Université de Toulouse, Spécialité Signal, Image, Acoustique et OptimisationLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] amplitude
[Termes IGN] analyse des mélanges spectraux
[Termes IGN] données multitemporelles
[Termes IGN] image hyperspectrale
[Termes IGN] méthode de Monte-Carlo par chaînes de Markov
[Termes IGN] optimisation (mathématiques)
[Termes IGN] processus stochastique
[Termes IGN] séparation aveugle de source
[Termes IGN] signature spectrale
[Termes IGN] variabilitéIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Acquired in hundreds of contiguous spectral bands, hyperspectral (HS) images have received an increasing interest due to the significant spectral information they convey about the materials present in a given scene. However, the limited spatial resolution of hyperspectral sensors implies that the observations are mixtures of multiple signatures corresponding to distinct materials. Hyperspectral unmixing is aimed at identifying the reference spectral signatures composing the data – referred to as endmembers – and their relative proportion in each pixel according to a predefined mixture model. In this context, a given material is commonly assumed to be represented by a single spectral signature. This assumption shows a first limitation, since endmembers may vary locally within a single image, or from an image to another due to varying acquisition conditions, such as declivity and possibly complex interactions between the incident light and the observed materials. Unless properly accounted for, spectral variability can have a significant impact on the shape
and the amplitude of the acquired signatures, thus inducing possibly significant estimation errors during the unmixing process. A second limitation results from the significant size of HS data, which may preclude the use of batch estimation procedures commonly used in the literature, i.e., techniques exploiting all the available data at once. Such computational considerations notably become prominent to characterize endmember variability in multi-temporal HS (MTHS) images, i.e., sequences of HS images acquired over the same area at different time instants. The main objective of this thesis consists in introducing new models and unmixing procedures to account for spatial and temporal endmember variability. Endmember variability is addressed by considering an explicit variability model reminiscent of the total least squares problem, and later extended to account for time-varying signatures. The variability is first estimated using an unsupervised deterministic optimization procedure based on the Alternating Direction Method of Multipliers (ADMM). Given the sensitivity of this approach to abrupt spectral variations, a robust model formulated within a Bayesian framework is introduced. This formulation enables smooth spectral variations to be described in terms of spectral variability, and abrupt changes in terms of outliers. Finally, the computational restrictions induced by the size of the data is tackled by an online estimation algorithm. This work further investigates an asynchronous distributed estimation procedure to estimate the parameters of the proposed models.Note de contenu : Introduction
1- Hyperspectral unmixing with spectral variability using a perturbed linear mixing model
2- A Bayesian model accounting for endmember variability and abrupt spectral changes to unmix multitemporal hyperspectral images
3- Online unmixing of multitemporal hyperspectral images
4- A partially asynchronous distributed unmixing algorithm
Conclusions et perspectivesNuméro de notice : 25812 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Spécialité : Signal, Image, Acoustique et Optimisation : Toulouse : 2017 Organisme de stage : Institut de Recherche en Informatique de Toulouse (I.R.I.T.) nature-HAL : Thèse DOI : sans En ligne : http://www.theses.fr/2017INPT0068 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95075
contenu dans ICC 2017, the 28th International Cartographic Conference, à Washington, USA, 2–7 July 2017, proceedings / International cartographic association = association cartographique internationale (2017)
Titre : RJMCMC based text placement to optimize label placement and quantity Type de document : Article/Communication Auteurs : Guillaume Touya , Auteur ; Thibaud Chassin, Auteur Editeur : International Cartographic Association ICA - Association cartographique internationale ACI Année de publication : 2017 Autre Editeur : Göttingen : Copernicus publications Collection : Proceedings of the ICA Conférence : ICC 2017, 28th International Cartographic Conference ICA 02/07/2017 07/07/2017 Washington DC Etats-Unis OA Proceedings of the ICA Importance : 5 p. Format : 21 x 30 cm Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Rédaction cartographique
[Termes IGN] méthode de Monte-Carlo par chaînes de Markov
[Termes IGN] optimisation (mathématiques)
[Termes IGN] placement automatique des écrituresRésumé : (Auteur) Label placement is a tedious task in map design, and its automation has long been a goal for researchers in cartography, but also in computational geometry. Methods that search for an optimal or nearly optimal solution that satisfies a set of constraints, such as label overlapping, have been proposed in the literature. Most of these methods mainly focus on finding the optimal position for a given set of labels, but rarely allow the removal of labels as part of the optimization. This paper proposes to apply an optimization technique called Reversible-Jump Markov Chain Monte Carlo that enables to easily model the removal or addition during the optimization iterations. The method, quite preliminary for now, is tested on a real dataset, and the first results are encouraging. Numéro de notice : C2017-008 Affiliation des auteurs : LASTIG COGIT (2012-2019) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.5194/ica-proc-1-116-2018 Date de publication en ligne : 16/05/2018 En ligne : http://dx.doi.org/10.5194/ica-proc-1-116-2018 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86207 Documents numériques
en open access
RJMCMC based text placement - pdf éditeurAdobe Acrobat PDF en open access
RJMCMC based text placement to ... - pdf éditeur nouvelle versionAdobe Acrobat PDF Generative models for road network reconstruction / Colin Kuntzsch in International journal of geographical information science IJGIS, vol 30 n° 5-6 (May - June 2016)PermalinkPermalinkLandmark based localization: LBA refinement using MCMC-optimized projections of RJMCMC-extracted road marks / Bahman Soheilian (2016)PermalinkLocalisation à base d’amers visuels : Cartographie et mise en correspondance de marquages au sol et intégration dans LBA / Bahman Soheilian (2016)PermalinkImproving soil moisture profile prediction with the particle Filter-Markov chain Monte Carlo method / Hongxiang Yan in IEEE Transactions on geoscience and remote sensing, vol 53 n° 11 (November 2015)PermalinkRoad marking extraction using a model&data-driven RJ-MCMC / Alexandre Hervieu in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol II-3 W4 (March 2015)PermalinkPermalinkA stochastic method for the generation of optimized building-layouts respecting urban regulation / Shuang He (oct 2014)PermalinkEvaluation of bayesian despeckling and texture extraction methods based on Gauss–Markov and auto-binomial gibbs random fields: Application to TerraSAR-X data / D. Espinoza Molina in IEEE Transactions on geoscience and remote sensing, vol 50 n° 5 Tome 2 (May 2012)PermalinkPermalink