Centre dedocumentation
scientifique

From point clouds to high-fidelity models - advanced methods for image-based 3D reconstruction / Audrey Richard (2021)  

Public Titre : From point clouds to high-fidelity models - advanced methods for image-based 3D reconstruction Type de document : Thèse/HDR Auteurs : Audrey Richard, Auteur Editeur : Zurich : Eidgenossische Technische Hochschule ETH - Ecole Polytechnique Fédérale de Zurich EPFZ Année de publication : 2021 Note générale : bibliographie A thesis submitted to attain the degree of Doctor of Sciences of ETH Zurich Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] chaîne de traitement [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] compréhension de l'image [Termes IGN] démonstration de faisabilité [Termes IGN] discrétisation spatiale [Termes IGN] Dortmund [Termes IGN] Enschede (Pays-Bas) [Termes IGN] jeu de données localisées [Termes IGN] modèle 3D de l'espace urbain [Termes IGN] modélisation sémantique [Termes IGN] optimisation (mathématiques) [Termes IGN] reconstruction 3D [Termes IGN] reconstruction d'objet [Termes IGN] texturage [Termes IGN] Zurich (Suisse) Résumé : (auteur) Capturing automatically a virtual 3D model of an object or a scene from a collection of images is a useful capability with a wide range of applications, including virtual/augmented reality, heritage preservation, consumer digital entertainment, autonomous robotics, navigation, industrial vision or metrology, and many more. Since the early days of photogrammetry and computer vision, it has been a topic of intensive research but has eluded a general solution for it. 3D modeling requires more than reconstructing a cloud of 3D points from images; it requires a high-fidelity representation whose form is often dependent on individual objects. This thesis guides you in the journey of image-based 3D reconstruction through several advanced methods that aims to push its boundaries, from precise and complete geometry to detailed appearance, using both theory with elegant mathematics and more recent breakthroughs in deep learning. To evaluate these methods, thorough experiments are conducted at scene level (and large-scale) where efficiency is of key importance, and at object level where accuracy, completeness and photorealism can be better appreciated. To show the individual potential of each of these methods, as well as the possible wide coverage in terms of applications, different scenarios are considered and serve as a proof-of-concept. Thereby, the journey starts with large-scale city modeling using aerial photography from the cities of Zürich (Switzerland), Enschede (Netherlands) and Dortmund (Germany), followed by single object completion using the synthetic dataset ShapeNet, that includes objects like cars, benches or planes that can be found in every city, to finish with the embellishment of these digital models via high-resolution texture mapping using a multi-view 3D dataset of real and synthetic objects, like for example statues and fountains that also dress the landscape of cities. Combining them together into an incremental pipeline dedicated to a specific application would require further tailoring but is quite possible. Numéro de notice : 17650 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : PhD : Sciences : ETH Zurich : 2021 En ligne : http://dx.doi.org/10.3929/ethz-b-000461735 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97892

Collaborative visual-inertial state and scene estimation / Marco Karrer (2020)  

Public Titre : Collaborative visual-inertial state and scene estimation Type de document : Thèse/HDR Auteurs : Marco Karrer, Auteur ; Margarita Chli, Directeur de thèse Editeur : Zurich : Eidgenossische Technische Hochschule ETH - Ecole Polytechnique Fédérale de Zurich EPFZ Année de publication : 2020 Importance : 151 p. Format : 21 x 30 cm Note générale : bibliographie A thesis submitted to attain the degree of Doctor of Sciences of ETH Zurich in Mechanical Engineering Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Acquisition d'image(s) et de donnée(s) [Termes IGN] Cartographie et localisation simultanées [Termes IGN] centrale inertielle [Termes IGN] compensation par faisceaux [Termes IGN] estimation de pose [Termes IGN] image captée par drone [Termes IGN] reconstruction d'objet [Termes IGN] robotique [Termes IGN] système multi-agents [Termes IGN] vision par ordinateur Index. décimale : THESE Thèses et HDR Résumé : (auteur) The capability of a robot to create a map of its workspace on the fly, while constantly updating it and continuously estimating its motion in it, constitutes one of the central research problems in mobile robotics and is referred to as Simultaneous Localization And Mapping (SLAM) in the literature. Relying solely on the sensor-suite onboard the robot, SLAM is a core building block in enabling the navigational autonomy necessary to facilitate the general use of mobile robots and has been the subject of booming research interest spanning over three decades. With the largest body of related literature addressing the challenge of single-agent SLAM, it is only very recently, with the relative maturity of this field that approaches tackling collaborative SLAM with multiple agents have started appearing. The potential of collaborative multi-agent SLAM is great; not only promising to boost the efficiency of robotic missions by splitting the task at hand to more agents but also to improve the overall robustness and accuracy by boosting the amount of data that each agent’s estimation process has access to. While SLAM can be performed using a variety of different sensors, this thesis is focused on the fusion of visual and inertial cues, as one of the most common combinations of sensing modalities in robotics today. The information richness captured by cameras, along with the high-frequency and metric information provided by Inertial Measurement Units (IMUs) in combination with the low weight and power consumption offered by a visual-inertial sensor suite render this setup ideal for a wide variety of applications and robotic platforms, in particular to resource-constrained platforms such as Unmanned Aerial Vehicles (UAVs). The majority of the state-of-the-art visual-inertial estimators are designed as odometry algorithms, providing only estimates consistent within a limited time-horizon. This lack in global consistency of estimates, however, poses a major hurdle in an effective fusion of data from multiple agents and the practi- cal definition of a common reference frame, which is imperative before collaborative effort can be coordinated. In this spirit, this thesis investigates the potential of global optimization, based on a central access point (server) as a first approach, demonstrating global consistency using only monocular-inertial data. Fusing data from multiple agents, not only consistency can be maintained, but also the accuracy is shown to improve at times, revealing the great potential of collaborative SLAM. Aiming at improving the computational efficiency, in a second approach a more efficient system architecture is employed, allowing a more suitable distribution of the computational load amongst the agents and the server. Furthermore, the architecture implements a two-way communication enabling a tighter collaboration between the agents as they become capable of re-using information captured by other agents through communication with the server, enabling improvements of their onboard pose tracking online, during the mission. In addition to general collaborative SLAM without specific assumptions on the agents’ relative pose configuration, we investigate the potential of a configuration with two agents, carrying one camera each with overlapping fields of view, essentially forming a virtual stereo camera. With the ability of each robotic agent to move independently, the potential to control the stereo baseline according to the scene depth is very promising, for example at high altitudes where all scene points are far away and, therefore, only provide weak constraints on the metric scale in a standard single-agent system. To this end, an approach to estimate the time-varying stereo transformation formed between two agents is proposed, by fusing the egomotion estimates of the individual agents along with the image measurements extracted from the view-overlap in a tightly coupled fashion. Taking this virtual stereo camera idea a step further, a novel collaboration framework is presented, utilizing the view-overlap along with relative distance measurements across the two agents (e.g. obtained via Ultra-Wide Band (UWB) modules), in order to successfully perform state estimation at high altitudes where state-of-the-art single-agent methods fail. In the interest of low-latency pose estimation, each agent holds its own estimate of the map, while consistency between the agents is achieved using a novel consensus-based sliding window bundle adjustment. Despite that in this work, experiments are shown in a two-agent setup, the proposed distributed bundle adjustment scheme holds great potential for scaling up to larger problems with multiple agents, due to the asynchronicity of the proposed estimation process and the high level of parallelism it permits. The majority of the developed approaches in this thesis rely on sparse feature maps in order to allow for efficient and timely pose estimation, however, this translates to reduced awareness of the spatial structure of a robot’s workspace, which can be insufficient for tasks requiring careful scene interaction and manipulation of objects. Equipping a typical visual-inertial sensor suite with an RGB-D camera, an add-on framework is presented that enables the efficient fusion of naturally noisy depth information into an accurate, local, dense map of the scene, providing sufficient information for an agent to plan contact with a surface. With the focus on collaborative SLAM using visual-inertial data, the approaches and systems presented in this thesis contribute towards achieving collaborative Visual-Inertial SLAM (VI-SLAM) deployable in challenging real-world scenarios, where the participating agents’ experiences get fused and processed at a central access point. On the other side, it is shown that taking advantage of specific configurations can push the collaboration amongst the agents towards achieving greater general robustness and accuracy of scene and egomotion estimates in scenarios, where state-of-the-art single-agent systems are otherwise unsuccessful, paving the way towards intelligent robot collaboration. Note de contenu : Introduction 1- Real-time dense surface reconstruction for aerial manipulation 2- Towards globally consistent visual-inertial collaborative SLAM 3- CVI-SLAM – collaborative visual-inertial SLAM 4- Collaborative 6DoF relative pose estimation for two UAVs with overlapping fields of view 5- Distributed variable-baseline stereo SLAM from two UAVs Numéro de notice : 28318 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse étrangère Note de thèse : PhD Thesis : Mechanical Engineering : ETH Zurich : 2020 DOI : sans En ligne : https://www.research-collection.ethz.ch/handle/20.500.11850/465334 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98251

Enhancing knowledge, skills, and spatial reasoning through location-based mobile learning / Christian Sailer (2020)  

Public Titre : Enhancing knowledge, skills, and spatial reasoning through location-based mobile learning Type de document : Thèse/HDR Auteurs : Christian Sailer, Auteur Editeur : Zurich : Eidgenossische Technische Hochschule ETH - Ecole Polytechnique Fédérale de Zurich EPFZ Année de publication : 2020 Collection : Dissertationen ETH num. 26817 Importance : 289 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] analyse géovisuelle [Termes IGN] apprentissage (cognition) [Termes IGN] enseignement secondaire [Termes IGN] plateforme logicielle [Termes IGN] programme interactif [Termes IGN] raisonnement spatial Résumé : (auteur) Location-based mobile learning (LBML) involves learning in and about locations in order to explore, analyze, describe, and evaluate phenomena in authentic learning experiences and incorporate them into the real world. Learners gain an understanding of boththe immediate environment using all the senses and the spatial perception to create a holistic impression of the environmental phenomena. Mobile mapping technologies and location-based services are utilized to link learning contents to specific locations as stories, tasks, or assignments. A large number of research projects on mobile learning have investigated LBML systems and LBML approaches with regard to learner satisfaction, usability and efficiency. The projects achieved predominantly positive results regarding motivation and engagement but only fragmented results regarding the cognitive learning outcomes.This dissertation describes how an LBML system utilizing GIS technology enhances the educational learning outcomes with a special focus on the spatial thinking process. Furthermore, this dissertation describes novel approaches of visual analytics with 2D and 3D map web components to produce new teaching strategies during the activities and new metacognitive strategies to evaluate and reflect the activity. The study presented in this dissertation covers case studies in universities, vocational schools, and informal education environments using design-based research to develop a mobile-friendly interactive mapping platform. Furthermore, the platform includes multimedia capabilities and interfaces to connect external services and content. The main study was conducted in a secondary school under real conditions and evaluated the technology regarding the learning performance and the teaching activities before, during, and after the activity. The results reveal a better cognitive learning outcome in classroom exams when a teaching sequence of several weeks includes an outdoor activity of a double lesson. Moreover, there is potential for enhancing learning beyond the outdoor part to improve spatial reasoning. Long-term self-assessment of the learners, however, resulted in no impact, whether cognitively or affectively. The workload for outdoor teaching compared to classroom teaching is higher mainly due to the profound inspections of the location. The findings and their implications for research and teacher education were discussed in order to corroborate the educational value of LBML to motivate educators using LBML strategies for teaching. Numéro de notice : 17657 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Thèse étrangère En ligne : http://dx.doi.org/10.3929/ethz-b-000458558 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97924

Modelling historical accessibility and its effects in space / Raphaël Fuhrer (2020)  

Public Titre : Modelling historical accessibility and its effects in space Type de document : Thèse/HDR Auteurs : Raphaël Fuhrer, Auteur Editeur : Zurich : Eidgenossische Technische Hochschule ETH - Ecole Polytechnique Fédérale de Zurich EPFZ Année de publication : 2020 Collection : Dissertationen ETH num. 26093 Importance : 187 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] accessibilité [Termes IGN] analyse comparative [Termes IGN] analyse diachronique [Termes IGN] carte ancienne [Termes IGN] corrélation [Termes IGN] données anciennes [Termes IGN] réseau de transport Résumé : (auteur) This thesis deals with the modelling of historical accessibility values, covering Switzerland and neighbouring regions from today until 1720. Changes in transport supply have spatial e ects on environment, society and economy; many of them are persistent. There are methods to quantify, isolate and capture causality. However, related studies are rarely done, one reason for that being missing data. The thesis details methods to reconstruct historical transport networks and corresponding travel system times. The related techniques, relevant conditions in historical transport maps and procedures needed are explained in detail. The associated numbers related to development in transport and travelling are prepared. The thesis shows applications of such results regarding state reach and productivity gains. The accessibility model includes both transport on the main road network as well as the space in-between capturing all relevant transport modes and generating continuous results for long-distance travel. Results show strong border e ects; this might be due to the population distribution model or the rather flat weight function. Results show an increase of accessibility over time, following the networks available at the time and along the central axes. Numéro de notice : 17656 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Thèse étrangère Note de thèse : Doctoral thesis : Sciences : ETH Zurich : 2020 En ligne : http://dx.doi.org/10.3929/ethz-b-000406184 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97916

Point cloud registration and mitigation of refraction effects for geomonitoring using long-range terrestrial laser scanning / Ephraim Friedli (2020)  

Public Titre : Point cloud registration and mitigation of refraction effects for geomonitoring using long-range terrestrial laser scanning Type de document : Thèse/HDR Auteurs : Ephraim Friedli, Auteur Editeur : Zurich : Eidgenossische Technische Hochschule ETH - Ecole Polytechnique Fédérale de Zurich EPFZ Année de publication : 2020 Note générale : bibliographie A dissertation submitted to attain the degree of Doctor of Sciences of ETH Zurich Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] réfraction atmosphérique [Termes IGN] scène [Termes IGN] scène intérieure [Termes IGN] surveillance géologique [Termes IGN] télémétrie laser terrestre Résumé : (auteur) Monitoring of man-made structures and regions posing potential natural hazards plays a pivotal role in preventing human and economic losses and thus, has been a central topic in geodesy for a long time. However, while the monitored objects (e.g. landslides) often are areal phenomena, classic geodetic monitoring still applies point-based measurement systems. Over the past few years, area-based methods (e.g. terrestrial laser scanning) are closing this gap and allow the acquisition of object geometry or surfaces with high spatial resolution and high accuracy. However, with the use of terrestrial laser scanning (TLS) for monitoring, new challenges arise. Two examples of such challenges are the scan registration and the mitigation of time-varying artefacts. When TLS is used for monitoring, scans over a sequence of epochs have to be acquired. The different scans have to be transformed into a common stable reference frame before changes between epochs can be analysed. This process is called registration and well-established solutions exist for scanning at close-range or scenes without changes between the scans. However, the standard approaches are not applicable for scenes with significant deformations and observed from long-range, a scenario typically encountered in the monitoring of natural hazards. Thus, in such monitoring cases, the need for other approaches exists. Furthermore, when scanning over long ranges, time-varying artefacts affect the resulting point clouds. These artefacts can be caused e.g. by atmospheric refraction and may result in apparent displacements of up to a few decimetres. Due to the temporarily and spatially varying air density distribution during the time required for the individual scan acquisition, the resulting point clouds are distorted systematically, but non-linearly. To tackle these two challenges, a data-driven registration algorithm for scan pairs of scenes with significant changes between epochs and an investigation of the time-varying artifacts are presented. The core of the registration approach is a data-driven classification of the scene into stable and unstable areas and a registration based on the stable areas only. The proposed registration algorithm is successfully applied to two different scenarios (an indoor and an outdoor scene). For both scenarios, the algorithm performs well with a sensibly chosen set of parameters. In addition, the algorithm is successfully applied to scans from an experimental study carried out in the scope of the investigation of the time-varying artefacts. This investigation focuses on atmospheric refraction and is based on numerical simulation and an experimental study, that allows a clear detection and analysis of the atmospheric effects. The numerical simulation demonstrates that these effects can cause apparent displacements on a decimeter-level, resulting from a combination of the measurement ray curvature and the terrain inclination. The results are corroborated by the experimental study. Additionally, the data from the experiment show that the magnitude of the effects from atmospheric refraction varies with time of the day. Currently, there is no solution to a data-driven or forward-modeling based compensation available but the study herein indicates that the effects might be mostly negligible when using only scans acquired at certain times in the evening. Numéro de notice : 17655 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : Doctoral thesis : Sciences : ETH Zurich : 2020 En ligne : http://dx.doi.org/10.3929/ethz-b-000409052 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97915

Realistic modeling of power transmission lines with geographic information systems / Joram Schito (2020)  

Permalink

Convolutional neural network for traffic signal inference based on GPS traces / Yann Méneroux (2018) 

Permalink

Spatial big data and machine learning in GIScience, Workshop at GIScience 2018, Melbourne, Australia, 28 August 2018 / Martin Raubal (2018)    

Permalink

Monitoring rock glaciers by combining photogrammetric and GNSS-based methods / Fabian Neyer (2017)  

Permalink

Advanced modeling and algorithms for high-precision GNSS analysis / Kan Wang (2016)  

Permalink

Autonomous navigation in complex nonplanar environments based on laser ranging / Philipp Andreas Krüsi (2016)  

Permalink

Co-location of geodetic observation techniques in space / Benjamin Männel (2016)  

Permalink

Real-time depth-image-based rendering for viewpoint-variable display on mobile devices / Shuoran Yang (2016)  

Permalink

Study and development of a laser based alignment system for the compact linear collider / Guillaume Stern (2016)  

Permalink

Theoretical and practical aspects of high-rate GNSS geodetic observations / Simon Häberling (2016)  

Permalink