Centre dedocumentation
scientifique

Analysis of pedestrian movements and gestures using an on-board camera to predict their intentions / Joseph Gesnouin (2022)  

Public Titre : Analysis of pedestrian movements and gestures using an on-board camera to predict their intentions Titre original : Analyse des mouvements et gestes des piétons via caméra embarquée pour la prédiction de leurs intentions Type de document : Thèse/HDR Auteurs : Joseph Gesnouin, Auteur ; Fabien Moutarde, Directeur de thèse Editeur : Paris : Université Paris Sciences et Lettres Année de publication : 2022 Importance : 171 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de doctorat de l'Université Paris Sciences et Lettres, Préparée à MINES ParisTech, Spécialité Informatique temps réel, robotique et automatique Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle [Termes IGN] apprentissage profond [Termes IGN] attention (apprentissage automatique) [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] estimation de pose [Termes IGN] image RVB [Termes IGN] instrument embarqué [Termes IGN] navigation autonome [Termes IGN] piéton [Termes IGN] reconnaissance de gestes [Termes IGN] réseau neuronal de graphes [Termes IGN] squelettisation [Termes IGN] trajectoire (véhicule non spatial) [Termes IGN] vision par ordinateur Index. décimale : THESE Thèses et HDR Résumé : (auteur) The autonomous vehicle (AV) is a major challenge for the mobility of tomorrow. Progress is being made every day to achieve it; however, many problems remain to be solved to achieve a safe outcome for the most vulnerable road users (VRUs). One of the major challenge faced by AVs is the ability to efficiently drive in urban environments. Such a task requires interactions between autonomous vehicles and VRUs to resolve traffic ambiguities. In order to interact with VRUs, AVs must be able to understand their intentions and predict their incoming actions. In this dissertation, our work revolves around machine learning technology as a way to understand and predict human behaviour from visual signals and more specifically pose kinematics. Our goal is to propose an assistance system to the AV that is lightweight, scene-agnostic that could be easily implemented in any embedded devices with real-time constraints. Firstly, in the gesture and action recognition domain, we study and introduce different representations for pose kinematics, based on deep learning models as a way to efficiently leverage their spatial and temporal components while staying in an euclidean grid-space. Secondly, in the autonomous driving domain, we show that it is possible to link the posture, the walking attitude and the future behaviours of the protagonists of a scene without using the contextual information of the scene (zebra crossing, traffic light...). This allowed us to divide by a factor of 20 the inference speed of existing approaches for pedestrian intention prediction while keeping the same prediction robustness. Finally, we assess the generalization capabilities of pedestrian crossing predictors and show that the classical train-test sets evaluation for pedestrian crossing prediction, i.e., models being trained and tested on the same dataset, is not sufficient to efficiently compare nor conclude anything about their applicability in a real-world scenario. To make the research field more sustainable and representative of the real advances to come. We propose new protocols and metrics based on uncertainty estimates under domain-shift in order to reach the end-goal of pedestrian crossing behavior predictors: vehicle implementation. Note de contenu : 1- Introduction 2- Human activity recognition with pose-driven deep learning models 3- From action recognition to pedestrian discrete intention prediction 4- Assessing the generalization of pedestrian crossing predictors 5- Conclusion Numéro de notice : 24066 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique temps réel, robotique et automatique : Paris Sciences et Lettres : 2022 DOI : sans En ligne : https://tel.hal.science/tel-03813520 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102091

3D urban scene understanding by analysis of LiDAR, color and hyperspectral data / David Duque-Arias (2021)  

Public Titre : 3D urban scene understanding by analysis of LiDAR, color and hyperspectral data Type de document : Thèse/HDR Auteurs : David Duque-Arias, Auteur ; Beatriz Marcotegui, Directeur de thèse ; Jean-Emmanuel Deschaud, Directeur de thèse Editeur : Paris : Université Paris Sciences et Lettres Année de publication : 2021 Importance : 191 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de Doctorat de l'Université PSL, Spécialité : Morphologie Mathématique Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] analyse de scène 3D [Termes IGN] apprentissage profond [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] graphe [Termes IGN] image hyperspectrale [Termes IGN] image optique [Termes IGN] modélisation géométrique de prise de vue [Termes IGN] monde virtuel [Termes IGN] morphologie mathématique [Termes IGN] navigation autonome [Termes IGN] scène urbaine [Termes IGN] segmentation sémantique [Termes IGN] semis de points [Termes IGN] traitement d'image Index. décimale : THESE Thèses et HDR Résumé : (auteur) Point clouds have attracted the interest of the research community over the last years. Initially, they were mostly used for remote sensing applications. More recently, thanks to the development of low-cost sensors and the publication of some open source libraries, they have become very popular and have been applied to a wider range of applications. One of them is the autonomous vehicle where many efforts have been made in the last century to make it real. A very important bottleneck nowadays for the autonomous vehicle is the evaluation of the proposed algorithms. Due to the huge number of possible scenarios, it is not feasible to perform it in real life. An alternative is to simulate virtual environments where all possible configurations can be set up beforehand. However, they are not as realistic as the real world is. In this thesis, we studied the pertinence of including hyperspectral images in the creation of new virtual environments. Furthermore, we proposed new methods to improve 3D scene understanding for autonomous vehicles. During this research, we addressed the following topics. Firstly, we analyzed the spectrum in color and hyperspectral images because it provides a description about the electromagnetic radiation at different frequencies. Some applications rely only on visible colors. In other cases, such as the characterization of materials, the study of the invisible range is required. For this purpose, we proposed a simplified spectrum representation that preserves its diversity, the Graph-based color lines (GCL) model. Secondly, we studied the integration of hyperspectral images, color images and point clouds in urban scenes. The analysis was carried out by using the data acquired during this thesis in the context of the REPLICA project FUI 24. We inspected spectral signatures of different objects and reflectance histograms of the images. The obtained results demonstrate that urban scenes are challenging scenarios for current technology of hyperspectral cameras due to the presence of uncontrolled light conditions and moving actors. Thirdly, we worked with 3D point clouds from urban scenes that have proved to be a reliable type of data, much less sensitive to illumination variations than cameras. They are more accurate than color images and permit to obtain precise 3D models of urban environments. Deep learning techniques are very popular in this domain. A key element of these techniques is the loss function that drives the optimization process. We proposed two new loss functions to perform semantic segmentation tasks: power Jaccard loss and hierarchical loss. They obtained a higher performance in evaluated scenarios than classical losses not only in 3D point clouds but also in color and gray scale images. Moreover, we proposed a new dataset (Paris Carla 3D Dataset) composed of synthetic and real point clouds from urban scenes. It is expected to be used by the research community for different automatic tasks such as semantic segmentation, instance segmentation and scene completion. Finally, we conducted a detailed analysis of the influence of RGB features in semantic segmentation of urban point clouds. We compared several training scenarios and identified that color systematically improves the performance in certain classes. It demonstrates that including a more detailed description of the spectrum, when the hyperspectral cameras technology increases its sensitivity, can be useful to improve scene description of urban scenes. Note de contenu : 1- Introduction 2- Data used in this thesis 3- Graph based color lines (GCL) 4- Study of REPLICA data 5- Power Jaccard losses for semantic segmentation 6- Segmentation of point clouds 7- Conclusions and perspectives Numéro de notice : 28464 Affiliation des auteurs : non IGN Thématique : IMAGERIE/MATHEMATIQUE/URBANISME Nature : Thèse française Note de thèse : Thèse de Doctorat : Morphologie Mathématique : Paris sciences et lettres : 2021 Organisme de stage : Centre de Morphologie Mathématique DOI : sans En ligne : https://pastel.archives-ouvertes.fr/tel-03434199/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99076

Contributions to graph-based hierarchical analysis for images and 3D point clouds / Leonardo Gigli (2021)  

Public Titre : Contributions to graph-based hierarchical analysis for images and 3D point clouds Type de document : Thèse/HDR Auteurs : Leonardo Gigli, Auteur ; Beatriz Marcotegui, Directeur de thèse Editeur : Paris : Université Paris Sciences et Lettres Année de publication : 2021 Importance : 177 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de Doctorat de l'Université PSL, Spécialité : Morphologie Mathématique Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] analyse de groupement [Termes IGN] apprentissage automatique [Termes IGN] arbre aléatoire minimum [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] extraction de traits caractéristiques [Termes IGN] extraction du réseau routier [Termes IGN] morphologie mathématique [Termes IGN] processus de hiérarchisation analytique [Termes IGN] réseau neuronal de graphes [Termes IGN] segmentation d'image [Termes IGN] semis de points [Termes IGN] texture d'image [Termes IGN] théorie des graphes Index. décimale : THESE Thèses et HDR Résumé : (auteur) Graphs are powerful mathematical structures representing a set of objects and the underlying links between pairs of objects somehow related. They are becoming increasingly popular in data science in general and in particular in image or 3D point cloud analysis. Among the wide spectra of applications, they are involved in most of the hierarchical approaches.Hierarchies are particularly important because they allow us to efficiently organize the information required and to analyze the problems at different levels of detail. In this thesis, we address the following topics. Many morphological hierarchical approaches rely on the Minimum Spanning Tree (MST). We propose an algorithm for MST computation in streaming based on a graph decomposition strategy. Thanks to this decomposition, larger images can be processed or can benefit from partial reliable information while the whole image is not completely available.Recent LiDAR developments are able to acquire large-scale and precise 3D point clouds. Many applications, such as infrastructure monitoring, urban planning, autonomous driving, precision forestry, environmental assessment, archaeological discoveries, to cite a few, are under development nowadays. We introduce a ground detection algorithm and compare it with the state of the art. The impact of reducing the point cloud density with low-cost scanners is studied, in the context of an autonomous driving application. Finally, in many hierarchical methods similarities between points are given as input. However, the metric used to compute similarities influences the quality of the final results. We exploit metric learning as a complementary tool that helps to improve the quality of hierarchies. We demonstrate the capabilities of these methods in two contexts. The first one,a texture classification of 3D surfaces. Our approach ranked second in a task organized by SHREC’20 international challenge. The second one learning the similarity function together with the optimal hierarchical clustering, in a continuous feature-based hierarchical clustering formulation. Note de contenu : Introduction 1- Graph theory and clustering 2- Point clouds 3- Ground and road detection 4- Minimum spanning tree for data streams 5- Metric learning 6- Towards Morphological Convolutions on Graphs Conclusions Numéro de notice : 28623 Affiliation des auteurs : non IGN Thématique : IMAGERIE/MATHEMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Morphologie Mathématique : Paris Sciences et Lettres : 2021 Organisme de stage : Centre de Morphologie Mathématique DOI : sans En ligne : https://pastel.archives-ouvertes.fr/tel-03512298/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99543

Unsupervised vision methods based on image perceptual information / Eric Bazan (2021)  

Public Titre : Unsupervised vision methods based on image perceptual information Type de document : Thèse/HDR Auteurs : Eric Bazan, Auteur ; Petr Dokladal, Directeur de thèse ; Eva Dokladalova, Directeur de thèse Editeur : Paris : Université Paris Sciences et Lettres Année de publication : 2021 Importance : 227 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de doctorat de l'Université Paris Sciences et Lettres, Préparée à MINES ParisTech, spécialité Morphologie Mathématique Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage automatique [Termes IGN] apprentissage non-dirigé [Termes IGN] compréhension de l'image [Termes IGN] contour [Termes IGN] couleur (variable spectrale) [Termes IGN] décomposition spectrale [Termes IGN] filtre de Gabor [Termes IGN] image captée par drone [Termes IGN] segmentation d'image [Termes IGN] texture d'image [Termes IGN] vision Index. décimale : THESE Thèses et HDR Résumé : (auteur) This thesis work deals with extracting features and low-level primitives from perceptual image information to understand scenes. Motivated by the needs and problems in Unmanned Aerial Vehicles (UAVs) vision based navigation, we propose novel methods focusing on image understanding problems. This work explores three main pieces of information in an image: intensity, color, and texture. In the first chapter of the manuscript, we work with the intensity information through image contours. We combine this information with human perception concepts, such as the Helmholtz principle and the Gestalt laws, to propose an unsupervised framework for object detection and identification. We validate this methodology in the last stage of the drone navigation, just before the landing. In the following chapters of the manuscript, we explore the color and texture information contained in the images. First, we present an analysis of color and texture as global distributions of an image. This approach leads us to study the Optimal Transport theory and its properties as a true metric for color and texture distributions comparison. We review and compare the most popular similarity measures between distributions to show the importance of a metric with the correct properties such as non-negativity and symmetry. We validate such concepts in two image retrieval systems based on the similarity of color distribution and texture energy distribution. Finally, we build an image representation that exploits the relationship between color and texture information. The image representation results from the image’s spectral decomposition, which we obtain by the convolution with a family of Gabor filters. We present in detail the improvements to the Gabor filter and the properties of the complex color spaces. We validate our methodology with a series of segmentation and boundary detection algorithms based on the computed perceptual feature space. Numéro de notice : 15285 Affiliation des auteurs : non IGN Thématique : IMAGERIE/MATHEMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Morphologie Mathématique : Paris Sciences et Lettres : 2021 Organisme de stage : Centre de Morphologie Mathématique DOI : sans En ligne : https://hal.science/tel-03690309 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101418

Smoothing algorithms for navigation, localisation and mapping based on high-grade inertial sensors / Paul Chauchat (2020)  

Public Titre : Smoothing algorithms for navigation, localisation and mapping based on high-grade inertial sensors Type de document : Thèse/HDR Auteurs : Paul Chauchat, Auteur ; Silvère Bonnabel, Directeur de thèse Editeur : Paris : Université Paris Sciences et Lettres Année de publication : 2020 Importance : 135 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de Doctorat de l'Université Paris Sciences et Lettres, Informatique temps réel, robotique, automatique Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Navigation et positionnement [Termes IGN] cadre conceptuel [Termes IGN] cartographie et localisation simultanées [Termes IGN] centrale inertielle [Termes IGN] filtre de Kalman [Termes IGN] itération [Termes IGN] lissage de données [Termes IGN] navigation inertielle [Termes IGN] robotique Index. décimale : THESE Thèses et HDR Résumé : (auteur) Mobile systems need to locate themselves ever more accurately, and in ever more complex situations. This is in particular true for autonomous systems, for which controlling the position error is a critical safety issue. To this end, they are endowed with various sensors, the data of which are fused to obtain an estimate of the vehicle’s location, either globally (with the GPS for instance), or locally, with respect to its surroundings (with cameras for instance). This thesis investigates algorithms for localisation by sensor fusion, namely filtering and especially smoothing, when the mobile is equipped with high-grade inertial sensors. The first part deals with the nonlinear consequences of the use of high-grade inertial sensors, and demonstrates how the nonlinear structure of both filtering and smoothing algorithms may be improved by leveraging the invariant filtering framework. The second part deals with the problems incurred by the linear solvers that are used at each step of nonlinear smoothing algorithms as a result of having highly precise sensors. It introduces a novel least-squares linear solver that solves the issues. Note de contenu : Introduction I- From Invariant filtering to invariant smoothing II- Navigation with highly precise sensors Conclusion Numéro de notice : 28576 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE/POSITIONNEMENT Nature : Thèse française Note de thèse : thèse de Doctorat : Informatique temps réel, robotique, automatique : Paris Sciences et Lettres : 2020 Organisme de stage : Centre de robotique (Paris) En ligne : https://pastel.archives-ouvertes.fr/tel-02887295/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97843

Machine learning for image segmentation / Kaiwen Chang (2019)  

Permalink

Apport de la prise en compte de la dépendance spatiotemporelle des séries temporelles de positions GNSS à l’estimation d’un système de référence / Clément Benoist (2018)  

Permalink

Utilisation des réseaux de capteurs Géocubes pour la mesure de déformation des volcans en temps réel par GNSS / Mohamed-Amjad Lasri (2018)  

Permalink

Combination of GNSS and SLR measurements : contribution to the realization of the terrestrial reference frame / Sara Bruni (2016)  

Permalink

Spatial machine learning applied to multivariate and multimodal images / Gianni Franchi (2016)  

Permalink