Dissertations / Theses on the topic 'Réalité virtuelle et augmentée'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Réalité virtuelle et augmentée.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Rahajaniaina, Andriamasinoro. "La réalité virtuelle et la réalité augmentée pour des systèmes d'informations ubiquitaires dans le travail collaboratif mobile." Toulouse 3, 2010. http://thesesups.ups-tlse.fr/926/.
Full textAugmented Reality is among of the techniques used to allow mobile users who are in different geographical area to share a model 2D/3D as primary tools for collaboration, using the same software on lightweight hardware or mobile computers. In this study, we proposed a modular architecture allowing the management of mobile collaborative Augmented Reality application. This architecture is designed so that the identification and the adaptation to the system are transparent to users. Vision and hybrid based tracking techniques are used to ensure the robustness of our system. The database is replicated in the servers and/or the clients. The technique of load balancing is used so that the communication between the client applications and servers is fault-tolerant
Cassier, Claude Yves. "Application de la réalité virtuelle et augmentée pour la conception et la maintenance de systèmes complexes." Orléans, 2002. http://www.theses.fr/2002ORLEA001.
Full textTison, Charles Henri Alexandre. "Mise en oeuvre et évaluation d'interactions multimodales orientées communication appliquées au déplacement d'objets graphiques 3D." Nancy 1, 2004. http://www.theses.fr/2004NAN10174.
Full textThe experiment described in this thesis concerns the applicability of a modalities combination in order to relocate 3D objects in a virtual reactive environment. The adopted "top-down" approach is initiated through the observation of command expressions modalities that take place during "prototype inspection" activities in the field of cloth design. A selection of a reduced set of user tasks, (3D objects relocation), helps investigate tasks vs input modalities combinations in order to determine an homogeneous set of low level interaction scenarios. The profile definition of relevant devices brings to build, afterwards, a minimal interactive system organised so as to test, with users, the relevancy of such a task modality allocation through an adapted version of an experiment known as "Wizard of Oz". An evaluation of speech variability helps simultaneously to precise the grammar to implement. The results seem to confirm the relevancy of such an interaction style
Otmane, Samir. "Télétravail Robotisé et Réalité Augmentée : Application à la Téléopération via Internet." Phd thesis, Université d'Evry-Val d'Essonne, 2000. http://tel.archives-ouvertes.fr/tel-00682240.
Full textFerretti, Gilbert. "Endoscopie virtuelle des bronches : études pré-cliniques et cliniques." Université Joseph Fourier (Grenoble), 1999. http://www.theses.fr/1999GRE19001.
Full textPoitevin, Dominique. "La conscience augmentée : perception et conscience numériques." Thesis, Rennes 1, 2020. http://www.theses.fr/2020REN1S074.
Full textProteiform and dematerialized, the digital virtual object never stops interacting with our senses and our consciousness in a relationship that is also plural. Whether it is an object of perception by the senses (in virtual reality, for example), or social (in the intentional interactions it contains), consciousness maintains a relationship with the virtual object that oscillates between enriched perception and illusion. The virtual object serves indeed, at the same time, of improved reading of the world tending towards a better comprehension of what surrounds the perceiving consciousness and of denaturation of the real in favor of illusory false pretenses which on the contrary move the consciousness away from the reality . Consciousness is thus torn between two opposing phenomena and must, in this configuration, seek a way to identify the virtual object beyond the illusion that it generates or intentional readings it proposes. The digital virtual object then generates complex relationships from consciousness to reality, both in the aspects of individual and cognitive consciousness and in consciousness immersed in society, to the point of being able to cause a phenomenon of digital servitude
Combe, Emmanuelle. "Perception de la taille : application à un système de réalité virtuelle et augmentée utilisé dans l'ingénierie véhicule." Paris 6, 2009. http://www.theses.fr/2009PA066256.
Full textHavard, Vincent. "Développement de méthodes et outils basés sur la réalité augmentée et virtuelle pour l'assistance ou l'apprentissage d'opérations dans un contexte industriel." Thesis, Normandie, 2018. http://www.theses.fr/2018NORMR001/document.
Full textThe adoption of digital technologies within industries and the evolution of technologies are opening new perspectives for using augmented reality (AR) and virtual reality (VR). Therefore, those technologies can facilitate the operators’ tasks working on complex industrial systems, either by bringing them some contextualised information in AR or by helping them with VR trainings. Thus they would improve their efficiency. However, integrating these new tools into existing processes of the company remains complex, due to the technologies and the data continuum needed, through the identification of use cases and the associated gains and by the diversity of actors and business experts involved in this process: the expert of the industrial system, the operator, the designer and the computer scientist.In order to develop those different industrial problematics, we first study the state of the art of scientific publications and existing technologies. Then, our research work has proposed a data modelling facilitating content authoring of augmented reality operations on industrial system. This work has also allowed to set up an experimental environment based on an educational production line and an augmented reality application developed thanks to that model.In a second part of this work, and in order to evaluate the efficiency of this technology, we have proposed a methodology allowing to evaluate augmented reality usage for maintenance, repair and operations on industrial systems according to performance, satisfaction and behavioural criteria. We analyse two case studies. They shows that contextualisation of information with augmented reality allows the operator to faster understand the task he needs to carry out than with paper instructions while reducing some kind of errors. Moreover we are proposing some guidelines in order to improve the augmented reality information efficiency. Besides, we are identifying which types of operation are improved with augmented reality. The work is also describing the rendering device influence on the use of augmented reality.Finally, and based on the augmented reality modelling, we are proposing an ontology allowing to unify content authoring of augmented and virtual reality so as to train or guide operator in their tasks. We are studying the use of this ontology for exploiting others data and company knowledge, as maintenance. This ontology is used for training scenarios in industrial environment and for guiding operator during their work
Chen, Jiazhou. "Structure d'une image : de la réalité augmentée à la stylisation d'images." Phd thesis, Université Sciences et Technologies - Bordeaux I, 2012. http://tel.archives-ouvertes.fr/tel-00977086.
Full textTrakunsaranakom, Channarong. "Propositions pour une conception de produits manufacturiers collaborative, intuitive et tangible via des environnements de réalité virtuelle et augmentée." Thesis, Université Grenoble Alpes (ComUE), 2017. http://www.theses.fr/2017GREAI022/document.
Full textThe aim of this research introduces general concepts for performance assessment of virtual reality environments which are relevant to the design activity of manufactured products. Moreover, it aims to present also the context of the research respect to the Thai automotive industry, because this thesis expect to build new knowledge for the benefit of Thailand economy. This research covers several contexts of Human-Computer Interaction research as well as evolution of the VR assessment in the industrial and educational sector. The state of the art with direct relevance for the current research includes: user interface, human factor issues but also usability assessment but the wish here is to go a step further towards utility assessment. This research focuses on abstract level assessment criteria including: affordance, ergonomics, intuitiveness, tangibility, and tiredness assessments. We propose and analyse an assessment method of virtual reality for given activities. We are specifically concerned by activities involved at design stage or at manufacturing preparation stage and we have a deep focus on assembly activity and motion simulation. The design of a virtual reality environment and the implementation of a computer application that supports the evaluation of these activities are presented. The main objective of such application remains the assessment of the performance of virtual reality environments to support the tasks of designers and engineers.This research consists of two main activities: The first experience to validate the evaluation and comparison of the performance of the VRES by the use of low basic sensors consisting of docking quality, task duration, and gesture instability sensor. The experimental task is a set of simple screw assemblies allowing the analysis of the basic movements such as translation, rotation, orientation, and insertion into the holes. We have implemented the experiment on four environments and invited 40 participants to our experiment protocol. The second experience was thus organized around a barrel cam mechanism simulation which is operated with a single rotation motion but which provides a complex cam 3D trajectory. Even design experts may have some difficulties to anticipate the behaviour of this system. They usually experience difficulties when tuning design parameters to ensure that the mechanism is working well. It is thus investigated virtual reality capacity to overpass these difficulties. If this capacity is demonstrated, it is also expected to evaluate and compare the performance of the virtual reality environment system by the use of high level abstract assessment technique combined with low level sensors. Thirty participants have been involved in an experience where both basic sensors and high level assessment criteria were captured. Four virtual reality environments including either stereoscopy or haptic force-feedback device were compared respect to a given task
Hamon, Ludovic. "Modélisation et interaction temps réel avec des structures dynamiques de type L-système : application aux plantes virtuelles." Angers, 2011. http://www.theses.fr/2011ANGE0023.
Full textToday, capacities and performance of computers allow rendering of realistic virtual landscapes in realtime and three dimensions. L-systems, a formal grammar developed by Aristide Lindenmayer in 1968, are a model called "generation model" used to produce virtual plants with realistic morphological and physiological aspects and integrate results of rigorous scientific studies. Human interactions in real time on a virtual object are an important feature of virtual reality. This kind of interaction is more and more required for the scientific study of plants, placing man as an important element of model evolution. This manuscript presents a study leading to the creation of an engine called real-time interactive L-system "RTIL" for interacting with virtual plants developed by the L-system formalism. This formalism is extended to propose a new generic method of interaction based on "interaction rules" and respecting this formal grammar. Three experiments are presented to illustrate interaction possibilities. The two first ones are based on an L-system model of the "Lychnis coronaria" plant, with which the user is required to intervene in the evolution process under different visual and haptic feedbacks. The third experiment shows an augmented reality system, introducing young children to basic notions about the evolution of a plant from the germination stage to the flowering stage
Balter, Raphaèle. "Construction d'un maillage 3D évolutif et scalable pour le codage vidéo." Rennes 1, 2005. ftp://ftp.irisa.fr/techreports/theses/2005/balter.pdf.
Full textLoscos, Céline. "Ré-éclairage et remodélisation interactifs des scènes réelles pour la réalité augmentée." Phd thesis, Université Joseph Fourier (Grenoble), 1999. http://tel.archives-ouvertes.fr/tel-00004842.
Full textNiquin, Cédric. "Reconstruction du relief et mixage réel/virtuel par caméras relief multi-points de vues." Thesis, Reims, 2011. http://www.theses.fr/2011REIMS006/document.
Full textThe display in 3D, with or without glasses, becomes more and more popular. The auto-stereoscopic displays contain between 2 and 9 images. The creation, transmission or display of such images correspond to scientific obstacles. Indeed the transmission of the images needs compression methods that exploit information redundancy between frames. The display requires that the same content can be viewed on all screens, which is possible only by using methods of intermediate views rendering. Finally the context of multi-view brings new perspectives in augmented reality, like the projection of shadows and occlusion between real and virtual content. All these applications can be obtained by computing the depths of the scene. Stereovision methods allow depth estimation, but are generic and not well suited to the context of multi-view images or the application mentioned above. We propose in this thesis a pipeline dedicated to the depth reconstruction of a scene in a multi-view context.Through a new expression of the multi-view matching, which involves grouping the pixels representing the same point of the scene in "match" and thus form a partitioning of all pixels, our pipeline finds information redundancies in order to obtain a robust estimation of depths. This expression defines exactly occlusions in the scene, which raises much of the ambiguity in image compression and intermediate views rendering. We also present a new constraint, integrated in our pipeline, which ensures the geometric consistency of the reconstructed depths. This constraint is essential for a consistent mix between virtual and real objects, and is also very useful for intermediate views rendering. Our pipeline consists of four modules : " point cloud generation ", "surface reconstruction ", depth refinement " and " time tracking ".Apart from the first module city, others are optional and their use depends on needs and target applications. Thus, the results of our pipeline are depth maps, a point cloud or a mesh representing the scene. As a proof of the pipeline, we present two implementations of it. The first, called local, is based on fast algorithms to reconstruct the scene in real time. The second implementation is dedicated to post-production applications and generates better quality depth at the expense of longer computation time. We also demonstrate the relevance of our pipeline by providing new methods of multi-view image compression, intermediate views rendering and augmented reality
Naud, Mickaël. "Contribution au développement d'outils d'aide à la conception assistée par la réalité virtuelle et augmentée : Application au domaine du textile/habillement." Phd thesis, Université d'Angers, 2008. http://tel.archives-ouvertes.fr/tel-00451947.
Full textBué, Pascal. "Architecture et réalité augmentée. Une manière d’écrire l’espace : la pensée visuelle instrumentée." Thesis, Sorbonne université, 2021. http://www.theses.fr/2021SORUL001.
Full textThis thesis questions and compares two augmented reality devices, one, UrbaSee, intended for the mediation of urban space during a Concerted Development Zone project, the other, HistoPad, intended for the mediation of urban space. the reconstruction of a historic space. An empirical research jointly combines devices analyzes and ethnographic inquiry through four parts comprised of three chapters each. The first part, establishing our epistemological posture, our methodology of investigation and the definition of fields and cases under study, considers the connection between a semiotics of writing and the anthropology of figuration. The second part questions devices as a poietic technology of seeing. A technosemiotic analysis and a phenomenotechnical approach situate the image of augmented reality between an art image and a scientific image, in which we observe a disproportionate editorial utterance. The third part considers the devices as performative technologies of the imagination, oscillating between a stimulated imagination and a fantasized technology that we analyze through the prism of media variation. Our fourth part shows that these writing strategies mask a process of ownership. The analysis of the belief regimes that these devices give rise to, the creative mediations and the knowledge-power relations between partners and creators of augmented reality devices, reveals the symbolic and economic takeover of the software industry over the projects of others. What our thesis reflects is perhaps the start of a change in the technical, economic and symbolic environment of the practices of the trades in urban and museum spaces
Castro, Miguel. "Navigation endovasculaire augmentée : mise en correspondance d’images pré- et per-opératoires." Rennes 1, 2010. http://www.theses.fr/2010REN1S183.
Full textOur work lies within the scope of the endovascular navigation (catheterization, stenting,. . . ), where complex difficulties related to the anatomical structural deformation arise when they are subjected to the introduction of relatively rigid tools (rigid guides, stent). The contribution of this thesis deals with the optimal use of intraoperative data in order to establish correspondence of preoperative (3D CT) and intraoperative (2D angiography) data within an augmented reality system for angionavigation. The establishment of this correspondence is based on the decomposition of the 3D/2D transformation (projective transformation plus 3D/3D rigid transformation) and algorithms for estimating parameters (intrinsic, extrinsic) under the constraints of the interventional environment. This approach involves a process of calibration for the intrinsic parameters of the C-arm, a decomposition of the 3D/3D rigid transformation into two transformations whereof the two sets of extrinsic parameters are, for one, a registration method restricted to the plane of the operating table, and can be, for the other, given by the imaging device or obtained through a 3D optical tracking system. The readjustment of the 3D model describing the initial nondeformed preoperative patient data is considered through a geometric method estimating deformations due to tool / tissue interactions and based on intraoperative observations. Acquisitions on phantoms under clinical conditions and real data were used to evaluate the proposed approach
Ouramdane, Nassima. "Vers un système d'assistance à l'interaction 3D pour le travail et le télétravail collaboratif dans les environnements de Réalité Virtuelle et Augmentée." Phd thesis, Université d'Evry-Val d'Essonne, 2008. http://tel.archives-ouvertes.fr/tel-00374961.
Full textL'objectif de ce travail est de modéliser, de concevoir, d'implémenter et d'évaluer un système d'assistance à l'interaction 3D mono-utilisateur et multi-utilisateurs. Notre concept est centré sur l'utilisateur et ses intérêts dans le monde virtuel, il est basé sur le principe d'anticipation du geste de l'utilisateur par l'assistance de ce dernier. Notre système d'assistance peut être considéré comme un moyen de contourner les limitations de certaines techniques d'interaction 3D classiques afin de les rendre utilisables dans des contextes différents.
Landrieu, Jeremie. "Apport des réalités virtuelles et augmentées dans la planification et le suivi in situ de travaux de rénovation." Phd thesis, Paris, ENSAM, 2013. http://pastel.archives-ouvertes.fr/pastel-00936702.
Full textVeyret, Morgan. "Un guide virtuel autonome pour la description d’un environnement réel dynamique : interaction entre la peerception et la prise de décision." Brest, 2009. http://www.theses.fr/2009BRES2004.
Full textAugmented reality usually consists in the addition of virtual information to real static objects. Our proposal is to use augmented reality in order to anotate dynamic objects with non-predictable behaviors. We focus on probtems related to the dynamic aspect of the environment : 1/ describing reality (adaptating the explanations provided by the virtual guide to the evolution of the environment) ; 2/ perceiving reality (the real world using video cameras). The description of the reality is achieved through the generation of the virtual guide’s discourse. This generation is based on two aspects : n priori knowledge represented as explanations and the guide’s behavior modeled with a hierarchical state machine. We consider the guided tour as the joint evolution of this behavior and the explanations provided to the visitors. An explanation is a graph describing the organisation of a set of discourse elements for a specific subject. Each discourse element represents an atomic unit describing the use of different modalities (e. G. Speech, gestures, facial expression) as a script. The execution of an explanation graph is done by the guides behavior which manages interruptions. When an explanation process is interrupted, the current subject of the guided tour is re-evaluated. This evaluation is based on a set of experts, each one being able to vote for available explanations according to their point of view. This vote takes into consideration the current contant of tise guided tour (e. G. Tour history, elapsed/remaining time) as well as the state of the real environment. The perception of the reality consists in the creation and update of an environment representation. This is achieved in real-time by multiple cooperating perception routines. The complexity of the observed environment (e. G. Amount of available information, lighting conditions) prevents us from analysing the entire video stream provided by the cameras. We propose to ovorcome this problem by the use of appropriate perception strategies. These strategies are implemented hy specific perception routines which are able to select and parameterize computer vision treatmonts. We present a minimal set of perception routines required to build an environment representation usable by the virtual guide vigilance schedules detection in space and time; tracking updates spatial attributes of existing entities in the representation; recognition identifies existing entitïes. The effectiveness of these perception strategies depends on the interaction between the decision process (discourse generation) and the perception (the building of an environment representation) of our autonomous virtual actor. We propose to implement this interaction using the environment representation and requests of the decision process on this representation. Experiments have been carried on in order to show the different aspects of our proposition and validate it in a controlled environment. This work has been applied to a real world dynamic environment in the ANR project SIRENE. This application exhibits problems related to our issue and demonstrates the relevance of our approach in the context of the guided tour for a marine aquarium in Océanopolis
Ajaj, Rami. "TEAMViz : systèmes multi-dispositifs, multi-vues et multi-surfaces pour la visualisation interactive de scènes 3D." Phd thesis, Université Paris Sud - Paris XI, 2009. http://tel.archives-ouvertes.fr/tel-00617855.
Full textMoreau, Guillaume. "Représentation et construction des systèmes d'information par l'image." Habilitation à diriger des recherches, Université de Nantes, 2009. http://tel.archives-ouvertes.fr/tel-00488770.
Full textEynard, Rémy. "Investigation de l’impact de l’interaction sociale vocale sur l’expérience utilisateur dans les environnements 3D temps-réel immersif." Thesis, Paris, ENSAM, 2016. http://www.theses.fr/2016ENAM0013/document.
Full textUser experience has recently become a central issue regarding to the design of products or services. With the democratization of Virtual Reality (VR), more and more economic actors start to being aware of the potential of VR in their respective sectors.In this increasingly dynamic context, user experience (UX) allows the anticipation of users’ and designers’ expectations in order to offer the most satisfying experience as possible. In addition, through the anticipation of user experience, we are able to predict more precisely the adoption level of a technological solution by future users. We have understood today that the only technological dimension is no longer enough to ensure the success of a hardware and/or software product. However, this must fit to the use that user will have of it, and more, it must provide a unique experience, through sensations, perceptions, emotions and thinking, inducing the highest satisfaction possible.A consensus has been established since a long time about the fact that play, create, learn together are more effective and fun than a lonely activity. Share and communicate is a primary need, it is through social interactions with our peers that we are able to fulfill many of our needs, from the most pragmatic to the most ethereal. We have, through the empirical study conducted as part of this thesis, brought a better understanding of the impact of social interactions (vocal mode) on the user experience process in a 3D-IVE (3D Immersive Virtual Environment). Through a literature review based on existing studies of the impact of social interaction on virtual presence (feeling of being there) or on users’ engagement (flow), we propose a more holistic view of this impact by a study focused on the overall user experience.With this aim, we have conducted three experiments immersing pairs of users in a 3D-IVE. By the division of participants into two samples, one being able to vocally communicate, the other not being so, we were able to compare quantitative and qualitative data to highlight the impact of social interactions (voice) on the user experience. Obtained quantitative results have confirmed our assumptions regarding the beneficial impact of social interaction (voice) on user performance. Surprisingly, we also observed that the perceived virtual presence tended to be higher when participants that were not able to communicate vocally, relied on the natural phenomenon of “translucence”. However, we had to balance these results, given to focus groups that have arisen differences regarding to the apprehension of performances, virtual and social presence. This triangulation between objective quantitative, subjective quantitative and qualitative data has confirmed the variable nature of the UX (depending on the user and time) and the strong influence of the nature of the activity of the experimentation.Our studies have validated the ability of simple immersive environments (Minecraft game software) to generate a high level of virtual presence and engagement, and in general, a high level of satisfaction among users. We also provide an insight into methods to be used in this type of context regarding to the design of tasks. Indeed, the same task presented differently can induce a quite dissimilar experience. Despite the difficulty to generalize a result due to the highly variable nature of user experience, we believe that our work will contribute to a greater understanding of the impact of vocal social interactions on UX in 3D-IVEs
Bouali, Anis. "Métatechnologies : interdépendance entre le niveau d'hypermédiatisation et la prise en compte (écosophique) du vivant." Paris 8, 2012. http://octaviana.fr/document/185435416#?c=0&m=0&s=0&cv=0.
Full textBy seeking some meanings of the neologism “metatechnology”, we were struck to see that its realization could to be considered, the such advent of “all-digital” like that of a totalitarian process. Did Lewis Munford (Mumford, transl. 1973, p. 2) deliberately give this opinion like “against-Utopia” or, following the example of 1984 of Orwell, in reaction to waiting’s utopians disappointed in 1948? The year under review constitutes an index of the economic situation: 1967, one year before the memorable year 1968. Consequently, in a situation which moves away more and more from the linearity, it appears that Science Information and Communication Technologies (S. I. T. C), can be considered as instrumental improvements insofar as their technicality is based jointly on an ascending knowledge of the social sciences. With the threshold criticizes that they reached, they restructure not only the field of the technologies, but the whole of our individual and collective actions, on all the levels and in all fields. One of the principal objectives of our research is to lucidly apprehend in what technologies contribute to release the human being but, also, to leave to condition it and to control it. Also our man-metatechnology-machine project is entitled significantly “HandiTech”
Abdel-Razek, Abdul-Rahman. "Impacts des technologies immersives sur Prototypage de services : Examiner les performances, l'expérience et l'acceptation des différentes formes de prototype de service." Thesis, Paris, HESAM, 2020. http://www.theses.fr/2020HESAE038.
Full textNowadays, prototyping is widely used in the industry for exploring design alternatives by engaging all project stakeholders. This is especially true at the earlier stage of the design process during both co-creation and exploration activities. However, prototypes have different forms, such as: physical forms like mock-ups, often based on 3D-printing, or virtual forms based on immersive technologies like Virtual Reality (VR), Augmented Reality (AR) or even Mixed Reality (MR). The main advantage of prototyping has been synthesized in a simple sentence, expressed by John Meada, a former MIT professor: “If a picture is worth a thousand words, a prototype is worth a thousand meetings”, cited by Banfield et al. (2017). More recently, the service sector has started to also adopt prototyping for exploring service design alternatives (Blomkvist, 2014). This involves different levels of service complexity, such as: online consultancy, machine configurators, and simulators for the training of machine operators or more simply assembly and disassembly guidance. Nevertheless, the current body of knowledge on Service Prototyping is lacking comparison among Service Prototype (SP) forms - conventional versus immersive - that would help businesses in the service sector to select the most appropriate SP form. In this context of the service sector, our investigation aims to bring new knowledge about the potential impact of immersive technologies on SP. Overall, it would help service organizations to experience a service idea even before this service really exists or to foresee which SP form is the most appropriate according to their specific context and degree of service complexity.A literature review was carried out in order to identify potential objective and subjective impact factors. Our created theoretical SP adoption model allows comparing different forms of Service Prototypes according to their respective performance in terms of completion, errors, and usage perception. This model was used to design an experiment, which involves mixed methods, allowing collecting a sufficient amount of quantitative data for running a statistical analysis formative approach for validating our SP adoption model. First of all, our empirical study has allowed validating our SP adoption model. Secondly, it has unveiled the positive impact of immersive technologies on service prototyping for getting an anticipated experience before a service is implemented. Thirdly, it has revealed the higher performance of AR- and MR-SP forms compared to VR and conventional SP forms. Finally, besides the obvious fact that only AR- and MR-SP forms allow to simultaneously learn a service operation, the VR-SP form is the one exhibiting the highest immersiveness and adoption score, especially because it allows exploring a service before it really exists
Braux-Zin, Jim. "Contributions aux problèmes de l'étalonnage extrinsèque d'affichages semi-transparents pour la réalité augmentée et de la mise en correspondance dense d'images." Thesis, Clermont-Ferrand 1, 2014. http://www.theses.fr/2014CLF1MM13/document.
Full textAugmented reality is the process of inserting virtual elements into a real scene, observed through a screen. Augmented Reality systems can take different forms to get the desired balance between three criteria: accuracy, latency and robustness. Three main components can be identified: localization, reconstruction and display. The contributions of this thesis are focused on display and reconstruction. Most augmented reality systems use non-transparent screens as they are widely available. However, for critical applications such as surgery or driving assistance, the user cannot be ever isolated from reality. We answer this problem by proposing a new “augmented tablet” system with a semi-transparent screen. Such a system needs a suitable calibration scheme:to correctly align the displayed augmentations and reality, one need to know at every moment the poses of the user and the observed scene with regard to the screen. Two tracking devices (user and scene) are thus necessary, and the system calibration aims to compute the pose of those devices with regard to the screen. The calibration process set up in this thesis is as follows: the user indicates the apparent projections in the screen of reference points from a known 3D object ; then the poses to estimate should minimize the 2D on-screen distance between those projections and the ones computed by the system. This is a non-convex problem difficult to solve without a sane initialization. We develop a direct estimation method by computing the extrinsic parameters of virtual cameras. Those are defined by their optical centers which coincide with user positions, and their common focal plane consisting of the screen plane. The user-entered projections are then the 2D observations of the reference points in those virtual cameras. A symmetrical thinking allows one to define virtual cameras centered on the reference points, and “looking at” the user positions. Those initial estimations can then be refined with a bundle adjustment. Meanwhile, 3D reconstruction is based on the triangulation of matches between images. Those matches can be sparse when computed by detection and description of image features or dense when computed through the minimization of a cost function of the whole image. A dense correspondence field is better because it makes it possible to reconstruct a 3D surface, useful especially for realistic handling of occlusions for augmented reality. However, such a field is usually estimated thanks to variational methods, minimizing a convex cost function using local information. Those methods are accurate but subject to local minima, thus limited to small deformations. In contrast, sparse matches can be made very robust by using adequately discriminative descriptors. We propose to combine the advantages of those two approaches by adding a feature-based term into a dense variational method. It helps prevent the optimization from falling into local minima without degrading the end accuracy. Our feature-based term is suited to feature with non-integer coordinates and can handle point or line segment matches while implicitly filtering false matches. We also introduce comprehensive handling of occlusions so as to support large deformations. In particular, we have adapted and generalized a local method for detecting selfocclusions. Results on 2D optical flow and wide-baseline stereo disparity estimation are competitive with the state of the art, with a simpler and most of the time faster method. This proves that our contributions enables new applications of variational methods without degrading their accuracy. Moreover, the weak coupling between the components allows great flexibility and genericness. This is the reason we were able to also transpose the proposed method to the problem of non-rigid surface registration and outperforms the state of the art methods
Veyret, Morgan. "Un guide virtuel autonome pour la description d'un environnement réel dynamique: interaction entre la perception et la prise de décision." Phd thesis, Université de Bretagne occidentale - Brest, 2009. http://tel.archives-ouvertes.fr/tel-00376176.
Full textLa description du réel consiste en la génération d'un exposé par le guide virtuel. Cette génération repose sur deux points: des connaissances a priori sous la forme d'explications et un comportement décrit par un automate hiérarchique. Nous considérons la visite guidée comme l'évolution conjointe du comportement du guide virtuel et des explications qu'il fournit aux visiteurs. Une explication permet de décrire l'enchaînement d'éléments de discours sur un sujet donné à l'aide d'un graphe. Chacun de ces éléments décrit une unité de discours indivisible décrivant l'utilisation des différentes modalités (parole, gestes, expression, ...) sous la forme d'un script. L'exécution d'un graphe d'explication est effectuée par le comportement qui intègre la notion d'interruption. Lorsqu'un processus d'explication est interrompu, il est suspendu et le sujet courant de la visite guidée est réévalué. Cette réévaluation repose sur l'utilisation d'un ensemble d'experts votant pour les différentes explications disponibles selon un point de vue particulier. Ce vote se base sur le contexte courant de la visite guidée (historique, temps écoulé/restant, ...) et l'état de l'environnement réel.
La perception consiste en la construction et la mise à jour d'une représentation de l'environnement. Ceci est effectué en temps réel par la coopération de différentes routines de perception. La complexité de l'environnement observé (quantité d'informations et variations des conditions d'éclairage) empêchent une analyse complète du flux vidéo. Nous proposons de surmonter ce problème par l'utilisation de stratégies de prise d'information adaptées. Ces stratégies de perception sont mises en oeuvre par certaines routines au travers du choix et du paramétrage des traitements qu'elles effectuent. Nous présentons un ensemble minimal de routines nécessaires à la construction d'une représentation de l'environnement exploitable dans le cadre de la description de cet environnement. Ce système repose sur la mise en oeuvre de trois stratégies de perception: la vigilance qui coordonne des traitements de détection dans le temps et dans l'espace; le suivi qui se charge de mettre à jour les propriétés spatiales des entités existantes dans la représentation; la reconnaissance dont le rôle est d'identifier ces entités. L'efficacité des stratégies de perception suppose une interaction entre la prise de décision (génération de l'exposé) et la perception (construction d'une représentation de l'environnement) de notre acteur virtuel autonome. Nous proposons de mettre en oeuvre cette interaction au travers de la représentation de l'environnement et des requêtes effectuées par le processus de prise de décision sur cette représentation.
Nous avons mené des expérimentations afin mettre en évidence le fonctionnement des différents aspects de notre proposition et de la valider des conditions contrôlées. Ces travaux sont appliqués à un cas concret d'environnement réel dynamique complexe au sein du projet ANR SIRENE. Cette application met en évidence les questions liées à notre problématique et montre la pertinence de notre approche dans le cadre de la présentation d'un aquarium marin d'Océanopolis.
Ferland, François. "Interfaces graphiques tridimentionnelles de téléopération de plateformes robotiques mobiles." Mémoire, Université de Sherbrooke, 2009. http://savoirs.usherbrooke.ca/handle/11143/1475.
Full textOuellet, Etienne. "Représentation et manipulation de données de simulation dans un environnement virtuel immersif." Thesis, Université Laval, 2012. http://www.theses.ulaval.ca/2012/28502/28502.pdf.
Full textOtis, Martin J. D. "Analyse, commande et intégration d'un mécanisme parallèle entraîné par des câbles pour la réalisation d'une interface haptique comme métaphore de navigation dans un environnement virtuel." Doctoral thesis, Université Laval, 2009. http://hdl.handle.net/20.500.11794/21963.
Full textBettaieb, Ghada. "Importance des facteurs d'accès dans l'expérience d'immersion et de présence dans un nouvel environnement commercial en ligne." Thesis, Lille 2, 2018. http://www.theses.fr/2018LIL2D019/document.
Full textAs part of the intersection of the fields of experiential marketing and the theories of information systems and human-computer interaction, this doctoral research work investigates the specificities of the shopping experience in a 3D commercial environment enriched with virtual reality devices. In particular, it studies the factors of access to the immersion and presence experience in thisenvironment and its consequences on behavioral intentions. The review of the literature and the triangulated qualitative phase made it possible to highlight the importance of three key factors of access to the experience and its enrichment as well as the central role of the immersion - presence process. An experiment implemented in a "real" commercial environment in 3D allowed us to studyconcomitantly the effects of the various factors namely: the navigability of the website (through a manipulation related to the presence / l lack of an interactive map), the sensory wealth of the commercial environment (through the manipulation of colors and diffused music) and sociability (through the manipulation of the presence / absence of 'a virtual seller) on sensory immersion and presence. The consequences on behavioral intentions have also been investigated. Theoretical,methodological and managerial contributions are numerous
Simon, Gilles. "Vers un système de réalité augmentée autonome." Nancy 1, 1999. http://docnum.univ-lorraine.fr/public/SCD_T_1999_0272_SIMON.pdf.
Full textSoufflard, Gauthier. "Réalité augmentée et droits fondamentaux." Master's thesis, Université Laval, 2018. http://hdl.handle.net/20.500.11794/29809.
Full textBallay, Jean-François. "Disparition de l'homme et machinerie humaine sur le scène contemporaine. Denis Marleau, Heiner Goebbels, Jean-François Perret." Thesis, Paris 3, 2012. http://www.theses.fr/2012PA030116.
Full textIs the actor thrown back into doubt again, one century after Maeterlinck, Craig and Jarry ? The topic happens to be brought up to date. But the purpose is no longer to get rid of the actor, so that he could be replaced by puppets. Artificial actors, like avatars, robots and other doubles, are likely to get their autonomy soon, on stage. The question is not only : what is missing, when the actor is missing ? But also, what is not missing ? This thesis is based upon three performances that stroke the minds on the first decade of the 21st century : Les Aveugles by Denis Marleau, Stifters Dinge by Heiner Goebbels, and Re :Walden by Jean-François Peyret. Our conjecture is about human disappearing on stage, with a special focus on anthropological aspects. The notion of « disappearing » means, at first sight, the withdrawing of actors, but we show that other deep challenges stand in the background : body instrumentation, interferences between life and artificial, disconnection to the phenomenal world, mankind decline and ecological disasters. If the human being is supposed to disappear soon, it’s probably on theatre stage that he will stand for a while. At the same time, isn’t it on stage that he has been playing for ever with appearing and disappearing, reality and illusion ? This thesis explores these problems, dealing with all the aspects : scenography, dramaturgy, actors and spectators, technology and new machines that are completely transforming the stage into a visual, sound, and highly confusing anamorphosis, by which the human being is involved in a vanishing process
Bayart, Benjamin. "Réalité augmentée haptique : théorie et applications." Phd thesis, Université d'Evry-Val d'Essonne, 2007. http://tel.archives-ouvertes.fr/tel-00419724.
Full textMasson, Lucie. "Suivi temps-réel d'objets 3D pour la réalité augmentée." Phd thesis, Université Blaise Pascal - Clermont-Ferrand II, 2005. http://tel.archives-ouvertes.fr/tel-00685727.
Full textPeillard, Etienne. "Vers une caractérisation des biais perceptifs en réalité mixte : une étude de facteurs altérant la perception des distances." Thesis, Ecole centrale de Nantes, 2020. http://www.theses.fr/2020ECDN0030.
Full textVirtual Reality, Augmented Reality, Mixed Reality, these words as well as their applications are gradually becoming common usage. However, the reality proposed by these technologies is not identical to our regular reality. This work aims to highlight some perceptual biases in Mixed Reality. First we study a perceptual bias linked to the observer: the anisotropy of the egocentric distances perception in virtual reality. In a second part, we study the exocentric perception of distances in Augmented Reality (AR). Indeed the under estimation of egocentric distances is a phenomen on frequently observed and it is therefore interesting to consider its potential transfer tothe exocentric perception. Then we further study other potential biases in AR by focusing in particular on evaluating the impact of depth cues on the perception of distances. In particular, we investigate in this chapter the effect of two depth cues in AR: the impact of the position and shape of shadows on distance perception, and then the influence of accommodation on distance perception using a specific display technology: retinal projection devices. Finally, we discuss the potential impact of interaction techniques on distance perception and propose a protocol to evaluate the effect of certain interactions on distance perception in AR, in order to perhaps bring it closer to real perception
Pusch, Andreas. "Conflits visuo-proprioceptifs de la main pour l'interaction 3D en réalité augmentée." Phd thesis, Grenoble INPG, 2008. http://tel.archives-ouvertes.fr/tel-00347430.
Full textDeux nouvelles méthodes sont introduites: un paradigme d'interaction intuitif pour toucher des objets virtuels et une technique pseudo-haptique active basée sur le déplacement de la main. Ces méthodes sont étudiées en considérant leurs bénéfices, limitations, effets sur le comportement de l'utilisateur et les conséquences sur la conception d'applications en environnements virtuels. Ces travaux montre que de nouvelles formes d'interaction 3D sont possible en exploitant les conflits visuo-proprioceptifs de la main. Des perspectives prometteuses sont présentées.
Zarrouati-Vissière, Nadège. "La réalité augmentée : fusion de vision et navigation." Phd thesis, Ecole Nationale Supérieure des Mines de Paris, 2013. http://pastel.archives-ouvertes.fr/pastel-00961962.
Full textLe, Chenechal Morgan. "Awareness Model for Asymmetric Remote Collaboration in Mixed Reality." Thesis, Rennes, INSA, 2016. http://www.theses.fr/2016ISAR0006/document.
Full textBeing able to collaborate remotely with other people can provide valuable capabilities in performing tasks that require multiple users to be achieved. Moreover, Mixed Reality (MR) technologies are great tools to develop new kinds of applications with more natural interactions and perception abilities compared to classical desktop setups. In this thesis, we propose to improve remote collaboration using these MR technologies that take advantages of our natural skills to perform tasks in 3D environments. In particular, we focus on asymmetrical aspects involved by these kind of collaboration: roles, point of view (PoV), devices and level of virtuality of the MR application. First, we focus on awareness issues and we propose a generic model able to accurately describe a collaborative MR application taking into account potential asymmetry dimensions. In order to address all these dimensions, we split our final model into two layers that separate real and virtual spaces for each user. In this model, each user can generate different kind of input and receive feedbacks with different meanings in order to maintain their own awareness of the shared Virtual Environment (VE). Then, we conduct an exploratory user study to explore the consequences of asymmetric PoVs and the involvement of users' representation in the level of awareness of others' collaborators. Second, we apply our findings to a remote guiding context that implies a remote guide to help an operator in performing a maintenance task. For this use case, we propose to the expert to use a Virtual Reality (VR) interface in order to help the operator through an Augmented Reality (AR) interface. We contribute to this field by enhancing the expert's perceptual abilities of the remote workspace as well as by providing more natural interactions to guide the operator through not intrusive guiding cues integrated to the real world. Last, we address an even more sensitive situation for awareness in remote collaboration that is virtual co-manipulation. It requires to target a perfect synchronization between collaborators in order to achieve the task efficiently. Thus, the system needs to provide appropriate feedbacks to maintain a high level of awareness, especially about what others are currently doing. In particular, we propose a hybrid co-manipulation technique, inspired from our previous remote guiding use case, that mixes virtual object and other's PoV manipulation in the same time
Dubois, Emmanuel. "Chirurgie augmentée : un cas de réalité augmentée ; Conception et réalisation centrées sur l'utilisateur." Phd thesis, Université Joseph Fourier (Grenoble), 2001. http://tel.archives-ouvertes.fr/tel-00004676.
Full textBertuzzi, Juan Pablo. "Mondes hybrides : expérimentations sociales pour analyser la relation avatar-utilisateur." Paris 8, 2014. http://octaviana.fr/document/182056708#?c=0&m=0&s=0&cv=0.
Full textWe already live in a hybrid world; a physical world that is constantly being nourished by parallel digital communicative worlds and in which projections of our own world manifest themselves via an enormous network of interaction points termed the Internet. Consequently, the individual experiences digital representation in different ways via these dimensions. This is a phenomenon which leads to a new projective and perceptive extension of the self which encounters the physical world. Hybrid Worlds contributes to the field of social communication. It offers detailed analysis of the socio-cultural effects of new information and communication technologies. Our work philosophy is based on the conceptualization of social experiments within spaces which constantly cohabit with simulation technologies and which pave the way for developing virtual and augmented realities. Our key research question focuses on properly evaluating and defining the influence that avatars -representatives of digital worlds- have upon their users; in particular, to what extent this influence can be detected in the everyday life of the individual. Hybrid Worlds presents two in design experiments: 1) Based on analysis of game theory, as well as that of the evolution of video products for leisure purposes in contemporary culture, we hereby present the project entitled ‘Augmented Cultural Heritage’. This project demonstrates the advantages of using technologies of virtual and augmented reality to apply hybrid worlds and social games to the fields of culture and education. 2) We also put forward the project entitled ‘Autonomous social Avatars (AsA)’ which is based on a study of the user habits, with particular attention paid to the evolution of his or her digital representations. This socially-interactive tool has been conceived in order to provide innovative experience within the domain of digital communities, whilst supporting the idea of integrating digital environments into physical spaces in real time. Finally, by managing these new aforementioned analytical tools, the ultimate objective of this investigation is to map out original fields of research for future studies within the information and communication sciences
Portela, Sotelo Miguel Alfredo. "Vidéosurveillance d’une salle de traitement en radiothérapie." Thesis, Lyon 1, 2011. http://www.theses.fr/2011LYO10260.
Full textThe various professionals (oncologists, medical physicists, radiation therapist, etc.) involved in the treatment of cancer by radiation therapy express more and more acutely a real need to have a global view of the treatment system in order to monitor the patient and all the equipment in the room — be it mobile (or even robotized) or not — to improve patient safety. This global view would help reduce the number of human interventions, errors in physical interaction (involuntary movements, collisions, etc.), and errors in the global configuration for the patient. To answer this need, this PhD manuscript presents a videosurveillance module using a numerical model of the elements in the scene (patient, couch, irradiation arm, etc.) to monitor the movement of these elements in order to avoid any event that could put the patient, staff or equipment in danger. Monitoring the treatment room means checking, at any moment, that its current configuration is consistent with what was planned upstream (in the Treatment Planning System [TPS]) and with the standards of radiotherapy, and if need be to, to inform the medical staff, so that correcting actions may be undertaken. We have developed a generic model which allows the creation of numerical models from the data contained in the patient record (in the TPS), enriched with other visual, geometric and “semantic” information. All the numerical models used to create a virtual environment correspond to the scene as seen by video cameras. Location and orientation of the elements are calculated by 3D registration, a choice justified by the characteristics of radiation treatment rooms (controlled environment, low dynamics, highly constrained construction specifications, very similar treatment rooms, etc.). The (geometric, physical and mechanical) information items in the model allow to reduce the overall complexity of the algorithms. The method for motion tracking we have implemented exploits the characteristics and constraints of the elements included in the numerical model, specifically the “descriptors” which correspond to the 3D modeling of primitives used to track the element in the video stream. We also present a dissimilarity function that we have defined, resulting from the merging of two well-known dissimilarity functions, respectively based on the chamfer distance and the notion of non-overlap. A fuzzy formalism improves the robustness of the method against the noise generated by acquisition and processing. When the treatment session takes place, the module evaluates the current configuration (positions acquired for elements, using the tracking module and global parameters of the scene), to interact with medical staff in relation to what has been defined in pretreatment. We present results of tests performed in a radiotherapy room but in the absence of irradiation and patient (the patient was either replaced by a phantom positioned on the couch or by one researcher playing his/her role). These results demonstrate the feasibility and efficiency of the surveillance module
Los profesionales involucrados en el tratamiento contra el cáncer con radioterapia (oncólogos, radiofísicos hospitalarios, tecnólogos médicos, etc.) expresaron la necesidad de tener una vista global del sistema de tratamiento con el fin de supervisar el paciente y todos los equipos presentes en la habitación - móvil (o robot) o no – para mejorar la seguridad del paciente. Esta vista global reduciría la cantidad de intervenciones humanas, los errores físicos (movimientos involuntarios, colisiones, etc.) y los errores en la configuración global con respecto al paciente tratado. Para satisfacer esta necesidad, en esta tesis presentamos un módulo de vídeovigilancia que explota un modelo digital de les elementos de la escena (el paciente, la camilla, la maquina de radiación, etc.) para vigilar el movimiento de estos elementos con el fin de evitar cualquier evento adverso que podría poner en peligro al paciente, el personal o los equipos. La supervisión de la sala de tratamiento implica la verificación, en cualquier momento, la consistencia entre la configuración actual de la sala con respecto a lo que estaba previsto antes (en el Sistema de Planificación del Tratamiento [SPT]) y con respecto a las normas relacionadas con la radioterapia, y en el caso contrario, informar al personal médico para que el tome las medidas necesarias. Hemos desarrollado un modelo genérico, que permite la creación de modelos digitales de los datos contenidos en el registro del paciente (obtenidas con el SPT), enriquecidas con otro tipo de información visual, geométrica y « semántica ». Los modelos digitales de todos los elementos son utilizados para crear un entorno virtual equivalente a la escena como es visto por las cámaras de vídeo. La ubicación y orientación de los elementos se calcula con la técnica de registro 3D, elección justificada por las características de las salas de tratamiento con radioterapia (entorno controlado, dinámica baja, especificación de la construcción con muchas restricciones : salas muy similares, etc.). Las informaciones (principalmente geométricas, físicas y mecánicas) contenidas en el modelo permiten la reducción de la complejidad general de los algoritmos utilizados. El método de seguimiento del movimiento implementado explota las características y las limitaciones de los elementos incluidas en sus modelos digitales, y plus exactamente los « descriptores », que corresponden au modelado 3D de las primitivas que permiten controlar el elemento de la secuencia de vídeo. También se presenta una función de disimilitud, que nosotros hemos definido, resultante de la fusión de dos funciones de disimilitud muy bien conocidas : distancia de chaflán y la noción de no-recubrimiento. Un formalismo difuso, basado en la teoría de conjuntos difusos, mejora la robustez del método contra el ruido generado por la adquisición y el procesamiento de datos. Cuando la sesión de tratamiento se lleva a cabo, el módulo evalúa la configuración actual (las posiciones adquiridas de los elementos mediante el módulo de seguimiento y los parámetros globales de la escena), para interactuar con el personal médico en relación con lo que se ha definido antes del tratamiento. Presentamos los resultados de las pruebas realizadas en una sala de radioterapia, pero en ausencia de la radiación y del paciente (un objeto reemplazado al verdadero paciente ha sido colocado sobre la camilla, o una persona de nuestro equipo ha jugado el papel del paciente). Estos resultados demuestran la viabilidad y la eficacia del módulo de seguridad
Sarlat, Ludivine. "Intégration multisensorielle, réalité virtuelle et personnalité schizotypique." Paris 6, 2007. http://www.theses.fr/2007PA066548.
Full textBailly, Charles. "Interagir en réalité mixte avec un casque : application à la chirurgie augmentée." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM064.
Full textThis thesis is in the field of Human-Computer Interaction (HCI) and specifically focuses on user interaction with Mixed Reality systems that rely on Head-Mounted Displays. Mixed Reality (MR) enables us to create mixed environments that combine virtual content with physical content. The entire workspace, including both physical and virtual objects, can then be used to interact with the system. Unlike traditional graphical interfaces, MR combines the advantages of the physical environment while providing the flexibility of virtual elements. The fields of application are many and varied, ranging from industrial manufacturing to medicine.Surgery is an application context in which MR is particularly promising. The ability to view medical data directly on the patient's body and around the operating table is a crucial benefit for surgeons. However, the existing techniques for interacting with this virtual information are not suited to the many constraints of the operating room. New approaches are needed to enable surgeons to view, manipulate and edit virtual content during an operation.Our research is driven by this need for MR interaction techniques for augmented surgery. Thanks to our partnership with the company Aesculap for this CIFRE thesis, our work is dedicated to knee prosthesis operations. We focus on the use of Head-Mounted Displays (HMDs), through which the augmented field of view is directly related to the position of the head.We start by providing a design space for MR head-based interaction. We explore this design space by devising new interaction techniques with menus. These techniques involve the entire reality-virtuality continuum by considering different physicalities for targets and implementing transitions between mixed reality and virtual reality. Our goal is to fulfill the surgery constraints by taking advantage of the objects already present in the operating room.After exploring head-based techniques, we broaden our area of research by considering surgical stages where surgeons have at least one hand available to interact with the system. Our contributions on this aspect are twofold. We first continue our study of menu techniques by considering a key aspect of the surgeon's work: visual attention to the operating field. We thus propose three new techniques allowing the surgeon to bring virtual widgets back into his field of vision without having to look away from the operating field. We then study the exploration of MR 3D scenes with multiple views. For instance, multiple views of the knee are displayed during the surgical planning step. The originality of the work lies in the different nature of the multiple views: virtual views and mixed views. We propose two new complementary interaction techniques that allow users to control the level of coupling between these different views and implement transitions between virtual reality and mixed reality
El, Rhabi Youssef. "Alignement de données 2D, 3D et applications en réalité augmentée." Doctoral thesis, Universitat Autònoma de Barcelona, 2017. http://hdl.handle.net/10803/405363.
Full textCette thèse s’inscrit dans le contexte de la réalité augmentée (RA). La problématique majeure consiste à calculer la pose d’une caméra en temps réel. Ce calcul doit être effectué en respectant trois critères principaux : précision, robustesse et rapidité. Dans le cadre de cette thèse, nous introduisons certaines méthodes permettant d’exploiter au mieux les primitives des images. Dans notre cas, les primitives sont des points que nous allons détecter puis décrire dans une image. Pour ce faire, nous nous basons sur la texture de cette image. Nous avons dans un premier temps mis en place une architecture favorisant le calcul rapide de la pose, sans perdre en précision ni en robustesse. Nous avons pour cela exploité une phase hors ligne, où nous reconstruisons la scène en 3D. Nous exploitons les informations que nous obtenons lors de cette phase hors ligne afin de construire un arbre de voisinage. Cet arbre lie les images de la base de données entre elles. Disposer de cet arbre nous permet de calculer la pose de la caméra plus efficacement en choisissant les images de la base de données jugées les plus pertinentes. Nous rendant compte que la phase de description et de comparaison des primitives n’est pas suffisamment rapide, nous en avons optimisé les calculs. Cela nous a mené jusqu’à proposer notre propre descripteur. Pour cela, nous avons dressé un schéma générique basé sur la théorie de l’information qui englobe une bonne part des descripteurs binaires, y compris un descripteur récent nommé BOLD [BTM15]. Notre objectif a été, comme pour BOLD, d’augmenter la stabilité aux changements d’orientation du descripteur produit. Afin de réaliser cela, nous avons construit un nouveau schéma de sélection hors ligne plus adapté à la procédure de mise en correspondance en ligne. Cela permet d’intégrer ces améliorations dans le descripteur que nous construisons. Procéder ainsi permet d’améliorer les performances du descripteur notamment en terme de rapidité en comparaison avec les descripteurs de l’état de l’art. Nous détaillons dans cette thèse les différentes méthodes que nous avons mises en place afin d’optimiser l’estimation de la pose d’une caméra. Nos travaux ont fait l’objet de 2 publications (1 nationale et 1 internationale) et d’un dépôt de brevet. Réalité augmentée: SFM,SLAM, estimation de pose temps réel, description, apprentissage, recalage 2D/3D
This thesis belongs within the context of augmented reality. The main issue resides in estimating a camera pose in real-time. This estimation should be done following three main criteria: precision, robustness and computation efficiency. In the frame of this thesis we established methods enabling better use of image primitives. As far as we are concerned, we limit ourselves to keypoint primitives. We first set an architecture enabling faster pose estimation without loss of precision or robustness. This architecture is based on using data collected during an offline phase. This offline phase is used to construct a 3D point cloud of the scene. We use those data in order to build a neighbourhood graph within the images in the database. This neighbourhood graph enables us to select the most relevant images in order to compute the camera pose more efficiently. Since the description and matching processes are not fast enough with SIFT descriptor, we decided to optimise the bottleneck parts of the whole pipeline. It led us to propose our own descriptor. Towards this aim, we built a framework encompassing most recent binary descriptors including a recent state-of-the-art one named BOLD. We pursue a similar goal to BOLD, namely to increase the stability of the produced descriptors with respect to rotations. To achieve this goal, we have designed a novel offline selection criterion which is better adapted to the online matching procedure introduced in BOLD. In this thesis we introduce several methods used to estimate camera poses more efficiently. Our work has been distinguished by two publications (a national and an international one) as well as with a patent application. Augmented Reality: SFM, SLAM, real time pose computation, keypoint description, Machine learning, 2D/3D registration
Bottecchia, Sébastien. "Système TAC : télé-assistance collaborative : réalité augmentée et NTIC au service des opérateurs et des experts dans le cadre d'une tâche de maintenance industrielle supervisée." Toulouse 3, 2010. http://thesesups.ups-tlse.fr/1268/.
Full textT. A. C. System was built in order to propose a new mode of remote communication. When an operator needs to be assisted on a manual task, classical technical support methods as phone or visioconference rapidly show their limits in terms of human interaction. By allowing a distant expert to see exactly what an operator is seeing, he could interact with him in interactive time thanks to augmented reality via an adequate interaction paradigm we named « Picking Outlining Adding ». In guiding the operator through visual guidance information, expert removes the ambiguities of language and communications difficulties are avoided. Operations are then easily performed. The experiments we have conducted go in this direction, showing the effectiveness of this new mode of communication. Moreover, interactions principles are sufficiently general to be applied to other use cases that go beyond the originally planned industrial maintenance
Marchand, Eric. "Commande d'une caméra réelle ou virtuelle dans des mondes réels ou virtuels." Habilitation à diriger des recherches, Université Rennes 1, 2004. http://tel.archives-ouvertes.fr/tel-00755302.
Full textNoël, Dominique. "La réalité virtuelle de la réalité virtuelle : éléments pour une sémiotique des environnements et créatures tridimensionnels de synthèse." Paris, EHESS, 2001. http://www.theses.fr/2001EHES0208.
Full textLourdeaux, Domitile. "Réalité virtuelle et formation : conception d'environnements virtuels pédagogiques." Phd thesis, École Nationale Supérieure des Mines de Paris, 2001. http://tel.archives-ouvertes.fr/tel-00006475.
Full textLa réalité virtuelle (RV) est souvent utilisée comme moyen technique pour immerger un formé dans des environnements le plus proche possible de la réalité. Les limitations technologiques actuelles ne permettent pas de s'approcher parfaitement de la réalité. De plus, les formateurs ont souvent besoin de fournir des explications s'appuyant sur des situations éloignées du réel afin d'aider les formés à prendre du recul et à mieux comprendre cette réalité. Les nombreuses potentialités de la RV permettent de proposer différents niveaux de réalisme.
Pour gérer ces niveaux de réalisme et optimiser les fonctionnalités offertes par la RV en fonction de objectifs pédagogiques et des difficultés des formés, nous proposons un Agent Pédagogique Intelligent (HAL : Help Agent for Learning)
HAL a été conçu pour aider les formateurs à construire un discours pédagogique en environnement virtuel en proposant deux types de stratégies pédagogiques adaptatives. Les premières modifient des aspects du scénario (pannes, conditions météorologiques, etc.). Les secondes fournissent des aides pour la compréhension de la situation (suggérer où le formé peut trouver la connaissance, expliquer une règle, montrer la conséquence de ses erreurs, etc.). Ces stratégies peuvent être mise en œuvre grâce à différentes formes d'assistance pédagogique gérant différents niveaux de réalisme (enrichissement, visualisation de mécanismes cachés, modélisation de concepts abstraits, etc.) HAL est basé sur un système multi-agent permettant de décrire une architecture modulaire et distribuée.
Une application professionnelle et industrielle réelle nous a permis de mettre en œuvre notre méthodologie de conception basée sur les aspects cognitifs, d'exploiter un grand nombre de potentialités de la RV et de mettre en évidence l'apport de HAL pour gérer ces fonctionnalités. L'objectif de cette application est de former des conducteurs de TGV à l'intervention sur Lignes à Grande Vitesse (descente sur les voies et manipulation d'appareils de voie.)